AI Agent Skills

[]()

A skill collection that enables collaborative development with a team of specialized AI agents.

Features

• 123 Specialized Agents - Covering bug investigation, testing, security, UI/UX, AI/ML, observability, and more
• Nexus Orchestrator - Analyzes tasks and automatically designs optimal agent chains
• Platform Agnostic - Works with Claude Code, Codex CLI, Antigravity CLI, and others

Quick Start

Installation

# For Claude Code
git clone https://github.com/simota/agent-skills.git ~/.claude/skills
For other platforms
git clone https://github.com/simota/agent-skills.git /path/to/your/skills

Usage

/Nexus I want to implement a login feature
/Scout Investigate the cause of this bug
/Radar Improve test coverage
/Vision I want to redesign the dashboard with a modern look

Overview

This repository contains 123 specialized AI agents covering various aspects of software development. Each agent specializes in a specific domain and is coordinated by the Nexus orchestrator.

Agent Catalog

Category-by-category catalog for all 123 agents.

Orchestration

| Agent | Description | Output | |-------|-------------|--------| | Nexus | "The right agent at the right time changes everything." - Team orchestrator. Decomposes requests and designs optimal agent chains | Prompts, progress management | | Sherpa | "The mountain doesn't care about your deadline. Plan accordingly." - Task decomposition guide. Breaks complex tasks into atomic steps completable within 15 minutes | Checklists | | Architect | "Every agent is a possibility. Every SKILL.md is a birth certificate." - Meta-designer that creates new skill agents. Ecosystem gap analysis, duplication detection, SKILL.md generation | SKILL.md, references | | Rally | "One task, many hands. Parallel by design." - Multi-session parallel orchestrator. Spawns and manages multiple Claude instances via Claude Code Agent Teams API for concurrent task execution | Team management, parallel execution | | Titan | "Give me a dream. I'll give you the product." - Product lifecycle meta-orchestrator. Coordinates all agents across 9 phases (DISCOVER→BUILD→LAUNCH→EVOLVE) to deliver complete products from ambiguous goals | Product delivery | | Sigil | "Every project has patterns waiting to become power." - Dynamic skill generator. Analyzes project codebases, discovers patterns and conventions, and generates optimized Claude Code skills for the project's .claude/skills/ directory | Project-specific skills | | Orbit | "Give me a goal. I'll give you a runner that finishes." - Nexus-autoloop completion specialist. Generates completion scripts, operation contracts, and audits for autonomous loop execution | Runner scripts, contracts | | Darwin | "Ecosystems that cannot sense themselves cannot evolve themselves." - Ecosystem self-evolution orchestrator. Detects project lifecycle phase, evaluates agent relevance, integrates cross-cutting knowledge, and evolves the entire ecosystem | Ecosystem Fitness Score, evolution proposals | | Lore | "Forgotten lessons are lessons repeated. Institutional memory is the compound interest of experience." - Memory curator for cross-ecosystem knowledge integration. Discovers common patterns from agent journals, catalogs them, and distributes to relevant agents. Knowledge decay detection and best practice propagation | METAPATTERNS.md, knowledge insights | | Gauge | "What gets measured gets managed. What gets audited gets normalized." - SKILL.md normalization auditor and self-evolving compliance agent. Scans all skills against the 19-item checklist, classifies violations with P0-P3 priority, generates concrete fix snippets, and evolves detection patterns via web research. No code written | Compliance reports, fix plans, dashboards | | Atelier | "Design decided upstream. Assets produced downstream. atelier is the studio floor in between." - Design-to-implementation pipeline orchestrator for the code-to-visual-to-code closed loop. Coordinates Vision → Muse/Frame → Forge → Artisan → Vitrine → Canvas to deliver design extraction, prototypes, visual assets, slides, and production together while persisting a project design system across downstream agents | Design system package, integrated deliverables | | Bazaar | "A landing page is one promise, one path, one decision. bazaar runs the studio that delivers all three." - Super-premium LP studio chain orchestrator. Composes Field → Cast → Pulse → Funnel → Vision → Saga → Compete → Muse → Flow → Artisan → Growth → Bolt → Judge → Launch into a recipe-selected, stage-gated pipeline (Discover → Audience → Strategy → Structure → Design → Build → Optimize → Verify → Launch) enforcing 6 craft axes — Design, Animation, Branding, Marketing, SEO, IA — each with explicit rubric and ship threshold | 6-axis-rubric-passed LP package, CVR-tuned production code, brand-coherent visuals, motion on tokens, schema-valid SEO, GEO citation-ready, analytics live | | Compass | "When in doubt, ask Compass. It finds the right skill for you among 123." - Skill ecosystem navigator and onboarding guide. Lists agents, recommends best fit for tasks, and helps newcomers discover the right specialist | Recommendations, agent maps | | Loom | "Many threads, one fabric — design the operating layer as a system." - Project operating-layer designer. Blueprints the coherent set of project-local skills, repo-tailored recipes, and skill-plus-agent workflows a repository needs together as one system, then delegates body authoring to Sigil and runtime routing to Nexus | Operating-layer blueprint, routing map, recipe/workflow specs | | Prune | "A garden grows by what you cut, not what you plant." - Ecosystem cleanup auditor. Audits the agent roster for overlap, redundancy, and inactivity, then proposes merge candidates and sunset plans with evidence and archive instructions. Propose-only, no execution | Merge/sunset proposals, archive instructions |

Investigation & Planning (Non-coding)

| Agent | Description | Output | |-------|-------------|--------| | Scout | "Every bug has a story. I read the ending first." - Bug investigation and root cause analysis (RCA). Identifies reproduction steps and fix locations | Investigation report | | Ripple | "Every change sends ripples. Know where they land before you leap." - Pre-change impact analysis. Evaluates risk from both vertical (dependencies, affected files) and horizontal (pattern consistency, naming conventions) perspectives | Impact analysis report | | Spark | "The best feature is the one users didn't know they needed." - Feature proposals. Suggests features leveraging existing data/logic as Markdown specs | Specification document | | Compete | "Know your enemy. Know the market. Know yourself." - Competitive research, differentiation, and positioning. SWOT analysis, feature matrices | Competitive analysis report | | Voice | "Feedback is a gift. Analysis is unwrapping it." - User feedback collection, NPS survey design, sentiment analysis, and insight extraction | Feedback report | | Plea | "I am your user. I feel every day what you overlook." - Synthetic user advocate. Role-plays as diverse end-user personas to generate authentic feature requests, surface unmet needs, and challenge team assumptions | Feature request report | | Field | "Good research asks the right questions. Great research changes what you thought was the question." - User research design, interview guides, qualitative analysis, persona/journey map creation | Research report | | Trace | "Every click tells a story. I read between the actions." - Session replay analysis, per-persona behavioral pattern extraction, UX problem storytelling. Works with Field/Echo | Behavioral analysis report | | Canon | "Standards are the accumulated wisdom of the industry. Apply them, don't reinvent them." - Investigates and analyzes using global/industry standards. Evaluates compliance with OWASP/WCAG/OpenAPI/ISO 25010, detects violations, and suggests improvements | Compliance report | | Lens | "See the code, not just search it." - Codebase comprehension specialist. Systematically investigates code structure, feature exploration, and data flow tracing for questions like "Does feature X exist?", "How does flow Y work?", "What is this module's responsibility?" | Investigation report | | Magi | "Three minds, one verdict. Consensus through diversity." - Multi-perspective decision making from three viewpoints (Logic, Empathy, Pragmatism). Architecture selection, tradeoff analysis, Go/No-Go decisions | Decision report | | Flux | "Bend the light. See what was always there." - Thinking refraction engine. Challenges assumptions, combines cross-domain knowledge, and shifts perspectives to produce reframed problem statements. Cynefin-based framework selection, Serendipity Injection, 10+ thinking frameworks. No code written | Reframing package, Insight Matrix, Blind Spot Report | | Riff | "The best ideas don't arrive. They evolve — one riff at a time." - Interactive brainstorming partner that deepens ideas through iterative dialogue using four thinking modes (Expand/Propose/Evaluate/Subtract). No code written | Brainstorming session output | | Cast | "Personas are not invented. They are discovered, born, and evolved." - Persona casting agent. Rapid generation, registry management, lifecycle tracking, and cross-agent distribution of personas from diverse inputs | Persona registry | | Helm | "A ship without a destination has no favorable wind. A ship without a helm has no direction at all." - Business strategy simulation agent. Integrates financial/market/competitive data for short/mid/long-term simulations. SWOT/PESTLE/Porter analysis, scenario planning, KPI forecasting, strategy roadmap generation. No code written | Strategy simulation report | | Accord | "Three teams, one truth." - Cross-team specification architect. Creates integrated spec packages across Business, Development, and Design teams using progressive refinement templates (L0 Vision > L1 Requirements > L2 Team-specific details > L3 Acceptance criteria). No code written | Integrated spec package, traceability matrix | | Matrix | "Infinite combinations, finite resources. Matrix finds the minimum that covers the maximum." - Universal multi-dimensional analysis agent. Controls combinatorial explosion from arbitrary axis×value inputs. Minimum coverage set selection, execution planning, and prioritization across all domains (testing, deployment, UX validation, risk assessment, compatibility). No code written | Matrix analysis, coverage optimization plan | | Saga | "Every product has a story. Every story has a hero. Make the customer the hero." - Narrative design agent. Structures product and feature use cases as customer-centric stories. StoryBrand SB7, Pixar Story Spine, Hero's Journey, JTBD frameworks, pitch narratives, onboarding stories, transformation arcs. No code written | Narrative document | | Omen | "Plan for the worst. Build for the best." - Pre-mortem analysis and failure mode enumeration. Systematically identifies failure scenarios, scores with RPN/AP. No code written | Pre-mortem report | | Rank | "Every priority tells a story of trade-offs." - Priority quantification. Scores and orders competing items using ICE/RICE/WSJF/MoSCoW/Kano frameworks. No code written | Priority report | | Sage | "Tell me what you're avoiding." - YC-style office hours advisory. Surfaces the #1 bottleneck via socratic probing, gives pattern-matched honest feedback, detects founder anti-patterns, and extracts concrete 1-2 week action items. No code written | Office hours session output (bottleneck + actions) | | PDM | "Show where the project stands — planned, built, and the gap between." - Project delivery status navigator (PdM-style, read-only). Reconciles planned scope (specs/issues/roadmap/PRD) against implemented code to produce feature inventories, unimplemented-feature lists, roadmap rollups, and WBS views | Feature inventory, gap list, roadmap rollup | | Summon | "Channel the mind, not the mouth — documented thinking, never fabricated words." - Notable-figure thinking lenses. Channels the documented mental models, heuristics, and decision-style of named figures and applies them to your problem as advisory lenses. No code | Multi-perspective advisory lenses |

Scout > Ripple > Builder chain: Scout (bug investigation) > Ripple (fix impact analysis) > Builder (implementation) Ripple > Guardian chain: Ripple (impact analysis) > Guardian (PR strategy) Field > Trace > Echo chain: Field (persona definition) > Trace (real-data validation) > Echo (simulation confirmation) Sentinel > Canon > Builder chain: Sentinel (vulnerability detection) > Canon (OWASP compliance evaluation) > Builder (fix implementation) Gateway > Canon > Gateway chain: Gateway (API design) > Canon (OpenAPI/RFC compliance check) > Gateway (corrections) Echo > Canon > Palette chain: Echo (UX issues) > Canon (WCAG compliance evaluation) > Palette (accessibility fixes) Field > Cast > Echo chain: Field (research data) > Cast (persona integration) > Echo (UI validation) Trace > Cast chain: Trace (behavioral data) > Cast (persona evolution)

Git/PR Management

| Agent | Description | Output | |-------|-------------|--------| | Guardian | "Every commit tells a story. Make it worth reading." - Git/PR gatekeeper. Signal/Noise analysis of changes, commit granularity optimization, branch naming, PR strategy proposals | Analysis report, PR preparation | | Harvest | "Code writes history. I harvest its meaning." - PR information collection and report generation. Fetches PR info via gh commands to auto-generate weekly/monthly reports and release notes | Work reports, release notes | | Launch | "Shipping is not the end. It's the beginning of accountability." - Release management. Versioning strategy, CHANGELOG generation, release notes, rollback plans, feature flag design | Release plans, CHANGELOG | | Trail | "Every bug has a birthday. Every regression has a parent commit. Find them." - Git history investigation, regression root cause analysis, code archaeology. Travels back in time to uncover the truth | History investigation report |

Guardian > Judge > Zen chain: Guardian (PR preparation) > Judge (review) > Zen (fixes) Guardian > Launch chain: Guardian (change analysis) > Launch (release plan) Trail > Scout chain: Trail (regression identification) > Scout (detailed investigation)

Quality Assurance

| Agent | Description | Output | |-------|-------------|--------| | Radar | "Untested code is unfinished code." - Unit/integration test addition, flaky test fixing, coverage improvement | Test code | | Voyager | "E2E tests are the user's advocate in CI/CD." - E2E test specialist. Playwright/Cypress setup, Page Object design, visual regression, CI integration | E2E test code | | Sentinel | "Security is not a feature. It's a responsibility." - Static security analysis (SAST), vulnerability pattern detection, input validation | Security fixes | | Probe | "A system is only as secure as its weakest endpoint." - Dynamic security testing (DAST), OWASP ZAP/Nuclei integration, penetration testing | Vulnerability report | | Vigil | "Detection is not a feature. It is the immune system of your infrastructure." - Detection Engineering agent. Sigma/YARA rule design, detection coverage mapping (MITRE ATT&CK), threat hunting hypothesis design, Purple Team Blue side execution, Detection-as-Code CI/CD integration | Detection rules, coverage maps | | Cull | "The worm leaves a husk. Find it before it sheds again — but never pull the husk while the worm is still inside." - Supply-chain malware infection scanner. IoC-based local scan + safe eradication for npm/PyPI worm campaigns (Mini Shai-Hulud, S1ngularity, lottie-player). Detects OS persistence (LaunchAgent/systemd), IDE-hook implants, lockfile pins, and known C2/exfil traces. Persistence-first ordering prevents rm -rf ~/ retaliation; rotation runbook is gated on eradication-verified | Infection report, eradication runbook | | Judge | "Good code needs no defense. Bad code has no excuse." - Code review via codex review, automated PR review, pre-commit checks, AI hallucination detection | Review report | | Zen | "Clean code is not written. It's rewritten." - Refactoring and code quality improvement (behavior unchanged) | Code improvements | | Sweep | "Dead code is technical debt that earns no interest." - Unused file detection, dead code identification, orphaned file discovery, safe deletion proposals | Cleanup proposals | | Attest | "Specs are truth. Code is evidence. Attest finds the gaps." - Specification compliance verifier. Extracts acceptance criteria from specs, generates BDD scenarios, and adversarially probes for gaps between spec and implementation. Issues CERTIFIED/CONDITIONAL/REJECTED verdicts | Compliance report, BDD scenarios | | Siege | "Break it before users do. Fix it before they notice." - Advanced testing specialist. Load testing (k6/Locust/Artillery), contract testing (Pact CDC), chaos engineering, mutation testing, resilience pattern verification | Test results, resilience reports | | Void | "The best code is the code that was never written." - YAGNI enforcement, scope cutting, complexity reduction proposals. Challenges existence of every feature/abstraction with 5 questions and Cost-of-Keeping Score | Subtraction proposals | | Mint | "Good tests deserve great data." - Test data and fixture generation specialist. Factory patterns, boundary value generation, synthetic data, seed management | Test data, fixtures | | Oath | "Trust is earned through evidence, not intention." - Regulatory compliance and audit agent. SOC2/PCI-DSS/HIPAA/ISO 27001 control mapping, audit trail design, Policy as Code | Reports, checklists | | Breach | "Think like an attacker. Defend like an engineer." - Red team engineering. Attack scenario design, threat modeling, MITRE ATT&CK/OWASP frameworks, Purple Team exercises, AI/LLM red teaming | Security assessment | | Cloak | "Privacy is not a feature. It's a right." - Privacy engineering and data governance. PII detection, data flow mapping, consent management, GDPR/CCPA-compliant code implementation | Privacy assessment | | Chain | "Treat every third-party skill like an npm install. Audit before invoking." - Skill/plugin/MCP supply-chain auditor. Treats SKILL.md, bundled scripts, MCP server defs, hooks, and .claude/ config as third-party software. Generates sha256 manifests, scans for Unicode Tag injection, detects curl-pipe + credential-exfil patterns, and pins MCP tool descriptions against rug-pulls | Supply-chain audit, sha256 manifest | | Snap | "Identifier first, snapshot always." - iOS UI automation specialist. XCUITest targets, accessibility-identifier-driven queries, programmatic screenshot capture, Swift Page Objects, status-bar-clean sessions, and fastlane snapshot pipelines for App Store assets with xcodebuild+xcresulttool CI | XCUITest code, screenshot pipelines |

Implementation

| Agent | Description | Output | |-------|-------------|--------| | Builder | "Types are contracts. Code is a promise." - Production implementation. Type-safe craftsman with TDD, Event Sourcing, CQRS, and performance optimization. Detects spec ambiguity, supports auto-handoff from Forge | Production code | | Artisan | "Prototypes promise. Production delivers." - Production frontend implementation craftsman. React/Vue/Svelte, Hooks design, state management, Server Components, form handling, data fetching | Frontend code | | Forge | "Done is better than perfect. Ship it, learn, iterate." - Prototyping. Prioritizes working software over perfection. Outputs types.ts, errors.ts, forge-insights.md for Builder handoff | MVP/PoC | | Native | "Every pixel ships. Every platform matters." - Pure-native mobile implementation specialist for iOS (Swift 6.3 + SwiftUI + Liquid Glass) and Android (Kotlin 2.4+ + Jetpack Compose + Material 3 Expressive). Production-quality features with @Observable / Swift Concurrency, Compose Strong Skipping + Type-safe Navigation, SwiftData / Room, Credential Manager + Passkeys, Privacy Manifest, edge-to-edge, predictive back, Live Activities, App Intents, Foundation Models / Gemini Nano, store compliance, and per-store staged rollout. React Native / Flutter / KMP / CMP are out of scope | Code | | Pixel | "Every pixel matters. Fidelity is non-negotiable." - Faithful reproduction agent. Generates pixel-accurate HTML/CSS from image mockups (PNG/JPG/screenshots) and performs visual verification | HTML/CSS code |

AI/ML

| Agent | Description | Output | |-------|-------------|--------| | Oracle | "AI is only as good as its architecture. Design it, measure it, trust nothing." - AI/ML design and evaluation specialist. Prompt engineering, RAG architecture, LLM application patterns, safety guardrails, evaluation frameworks, MLOps, cost optimization | Design specs, evaluation reports |

Oracle > Builder > Radar chain: Oracle (AI/ML design) > Builder (implementation) > Radar (tests) Oracle > Stream > Builder chain: Oracle (RAG design) > Stream (data pipeline) > Builder (implementation) Oracle > Sentinel > Oracle chain: Oracle (safety design) > Sentinel (security review) > Oracle (refinement)

Performance

| Agent | Description | Output | |-------|-------------|--------| | Bolt | "Speed is a feature. Slowness is a bug you haven't fixed yet." - Application performance improvement. Frontend (re-render reduction) and backend (N+1 fix) optimization | Optimized code | | Tuner | "A fast query is a happy user. A slow query is a lost customer." - DB performance optimization. EXPLAIN ANALYZE analysis, index recommendations, slow query improvement | Query optimization |

Observability/SRE

| Agent | Description | Output | |-------|-------------|--------| | Beacon | "You can't fix what you can't see. You can't see what you don't measure." - Observability and reliability engineering specialist. SLO/SLI design, distributed tracing, alerting strategy, dashboard design, capacity planning, toil automation | SLO definitions, observability specs |

Beacon > Gear > Builder chain: Beacon (observability design) > Gear (monitoring implementation) > Builder (instrumentation) Triage > Beacon > Gear chain: Triage (incident postmortem) > Beacon (monitoring improvements) > Gear (implementation)

UI/UX

| Agent | Description | Output | |-------|-------------|--------| | Vision | "Design is not how it looks. Design is how it feels." - Creative direction. Design direction decisions, Design System creation, Muse/Palette/Flow/Forge orchestration | Design strategy | | Palette | "Usability is invisible when done right, painful when done wrong." - Usability improvement, cognitive load reduction, a11y support | UX improvements | | Muse | "Tokens are the DNA of design. Mutate them with care." - Design token application, spacing/border-radius/shadow unification, dark mode support | Visual improvements | | Flow | "Motion creates emotion. Animation breathes life." - UI animation, hover effects, loading states, modal transitions | Animations | | Echo | "I don't test interfaces. I feel what users feel." - Persona validation. Embodies users to report confusion points in UI flows | UX report | | Vitrine | "Components without stories are components without context." - Storybook story creation, catalog management, Visual Regression integration. CSF 3.0 format | Storybook Stories | | Prose | "Words are the smallest unit of design. Get them wrong, and nothing else matters." - User-facing text specialist. Microcopy, error messages, voice & tone framework, onboarding copy, accessibility text | Copy guidelines, content specs | | Frame | "Design speaks in pixels. I translate it to code." - Figma MCP Server bridge agent. Extracts and structures design context from Figma for implementation agents. Design-to-code bridging, Code Connect management, design system rule extraction. No code written | Structured design context, design system rules | | Ink | "Every stroke serves a purpose." - SVG icon/illustration generation, icon system design, and sprite symbol construction | SVG assets |

Documentation

| Agent | Description | Output | |-------|-------------|--------| | Scribe | "A specification is a contract between vision and reality." - Document writer for PRD/SRS/HLD/LLD, implementation checklists, and test specifications | Specs, design docs | | Quill | "Code tells computers what to do. Documentation tells humans why." - JSDoc/TSDoc additions, README updates, typing any to proper type definitions | Documentation | | Morph | "A document is timeless. Its format is temporary." - Document format conversion (Markdown <> Word/Excel/PDF/HTML). Converts Scribe specs and Harvest reports to various formats | Converted documents | | Tome | "Changes are forgotten. Knowledge endures." - Transforms repository changes into detailed learning documentation. Explains terminology, flows, design decisions, and anti-patterns | Learning docs | | Clause | "Every clause carries weight. Every omission carries risk." - Legal document review for Terms of Service, Privacy Policy, and Tokushoho compliance. Clause gap detection and risk flagging | Legal review report | | Zine | "The hook earns the second paragraph." - External-facing tech blog/article series authoring for note/Zenn/Qiita/dev.to. Hook design, article structure, platform-specific tuning, multi-episode series management | Published articles, series index |

Scribe vs Quill vs Morph vs Tome vs Zine responsibilities:

• Scribe: Project documentation (PRD, SRS, design docs, checklists, test specifications)
• Quill: Code documentation (JSDoc/TSDoc, README, type definitions)
• Morph: Format conversion (Markdown > PDF/Word/HTML, etc.)
• Tome: Change-based learning materials (design decisions, terminology, anti-patterns from diffs)
• Zine: External-facing articles for public platforms (note/Zenn/Qiita/dev.to), series management

Visualization

| Agent | Description | Output | |-------|-------------|--------| | Canvas | "A diagram is worth a thousand lines of documentation." - Design visualization. Converts code, specs, and context into Mermaid diagrams or ASCII art (flowcharts, sequence diagrams, state machines, class diagrams, ER diagrams, etc.) | Mermaid diagrams / ASCII Art | | Sketch | "From words to worlds, prompt to pixel." - AI image generation code craftsman. Produces production-ready Python code for image generation via Gemini API. Prompt engineering, batch generation, cost estimation | Python code | | Cue | "Every frame tells a story." - Video script, storyboard, and narration design for product videos, explainer videos, and onboarding content | Video scripts, storyboards | | Stage | "Every slide is a stage." - Marp/reveal.js/Slidev slide generation, story composition design, conference talk optimization | Slide decks |

Architecture

| Agent | Description | Output | |-------|-------------|--------| | Atlas | "Dependencies are destiny. Map them before they map you." - Dependency analysis, circular reference detection, ADR/RFC creation | Design documents | | Port | "From web to native. Translate the experience, not just the code." - Web-to-native porting design specialist (2026 spec — Liquid Glass / Material 3 Expressive / Swift 6.3 / targetSdk 36 / Privacy Manifest / 5.1.2(i) AI disclosure aware). Designs porting blueprints from Web (React/Vue/Svelte/Angular) to iOS Swift / Android Kotlin pure-native. Produces feature parity matrices, native architecture maps, regulatory-compliance plans, and Strangler-Fig phased roadmaps. Optionally proposes a hybrid path (Pure-Native UI + KMP shared logic) | Porting blueprint, parity matrix, roadmap | | Gateway | "APIs are promises to the future. Design them like contracts." - API design, review, OpenAPI spec generation, versioning strategy, breaking change detection | API specifications | | Grove | "A well-structured repository is a well-structured mind." - Repository structure design, optimization, and auditing. Directory design, docs/ organization, test structure, anti-pattern detection | Structure design, audit reports | | Nest | "Structure what reaches the model, and the model structures the rest." - LLM-optimized folder structure design. Audits and restructures project directories for context efficiency, progressive disclosure, and prompt cache performance | Structure reports, layout plans | | Weave | "Every state tells a story. Every transition is a contract." - Workflow and state machine design specialist. State transition design, invalid transition detection, Saga patterns, approval flows | Designs, diagrams | | Seek | "The right result at the right time in the right order." - Search engine and vector DB design specialist. Full-text search, vector search, hybrid search, RAG retrieval layer | Code, configs | | Crypt | "Trust no channel. Verify every key." - Cryptographic architecture design: algorithm selection, key management, E2E encryption, KMS integration, TLS configuration | Crypto design specs | | Shard | "Isolation is the foundation of trust in multi-tenancy." - Multi-tenant architecture design. Tenant isolation strategies, RLS, routing, and scale design for SaaS | Architecture design | | Trawl | "Design the web that catches the web." - Crawl system architecture design. Distributed crawler design, URL frontier management, politeness policies, legal compliance | Architecture specs | | Tempo | "Time is not a scalar — it's a minefield of conventions." - Scheduling and time-aware logic architect. Cron expression design, timezone/DST handling, retry/backoff policies, idempotency keys, backfill strategies, and business-calendar design (JP holidays, fiscal year, banking days) | Schedule specs, cron configs, retry policies | | Grok | "Understand the shape before writing the parser." - Pattern, regex, parser, and DSL design specialist. Grammar authoring (EBNF/PEG), ReDoS-safe regex, parser-generator selection (ANTLR4/tree-sitter/Chevrotain), internal DSL architecture, AST transformation | Grammar specs, parser designs, DSL specs |

Communication

| Agent | Description | Output | |-------|-------------|--------| | Relay | "Every message finds its way. Every channel speaks the same language." - Messaging integration, bot development, and real-time communication specialist. Channel adapters, webhook handlers, WebSocket servers, event-driven architecture | Channel adapters, message handlers, bot framework |

Relay > Builder > Radar chain: Relay (messaging design) > Builder (implementation) > Radar (tests) Gateway > Relay chain: Gateway (webhook API spec) > Relay (handler design)

Data

| Agent | Description | Output | |-------|-------------|--------| | Schema | "A schema is a contract with the future." - DB schema design, migration creation, ER diagram design | Migrations / schema definitions | | Stream | "Data flows like water. My job is to build the pipes." - Data pipelines. ETL/ELT design, Kafka/Airflow/dbt, batch/streaming selection, data quality management | Pipeline design, DAGs, dbt models |

Schema > Stream chain: Schema (data model) > Stream (pipeline design)

DevOps

| Agent | Description | Output | |-------|-------------|--------| | Anvil | "The terminal is the first interface. Make it unforgettable." - Terminal UI construction, CLI development support, dev tool integration (Linter/test runner/build) | CLI/TUI code | | Gear | "The best CI/CD is the one nobody thinks about." - Dependency management, CI/CD optimization, Docker configuration, operational monitoring | Configuration files | | Scaffold | "Infrastructure is the silent foundation of every dream." - Cloud infrastructure (Terraform/CloudFormation/Pulumi), local dev environments (Docker Compose), IaC design | Infrastructure config | | Hearth | "Your tools should feel like home." - Personal dev environment craftsman. Generates, optimizes, and audits config files (zsh/tmux/neovim/ghostty), dotfile management, shell/terminal/editor setup | Config files | | Hone | "A sharp blade cuts clean. A sharp config cuts friction." - AI CLI configuration auditor (Codex CLI / Antigravity CLI / Claude Code). Collects official best practices via web, audits config.toml/settings.json/CLAUDE.md/GEMINI.md/AGENTS.md/permissions/commands/hooks/rules/MCP/extensions, proposes Before/After diff improvements. Never edits config directly | Audit reports, proposals | | Latch | "Every event is an opportunity. Hook it before it slips away." - Claude Code hook specialist. Proposes, configures, debugs, and maintains Claude Code hooks (PreToolUse/PostToolUse/Stop/SessionStart etc.) for workflow automation, quality gates, and security validation | Hook configurations | | Pipe | "Workflows are pipelines. Pipelines are promises." - GitHub Actions workflow expert. Trigger strategies, security hardening, performance optimization, PR automation, Reusable Workflow design | GHA workflows | | Ledger | "Every dollar has a story. Make it a short one." - FinOps and cloud cost optimization. IaC cost estimation, right-sizing, RI/SP recommendations, cost anomaly detection | Reports, configs | | Shift | "Migration is not moving. It's transforming." - Migration and upgrade orchestrator. Framework, library, API, database, and infrastructure migrations end-to-end with codemod generation and incremental strategies | Migration plans |

Hearth vs Hone vs Gear vs Scaffold vs Latch vs Pipe responsibilities:

• Hearth: Personal environment (dotfiles, shell, editor, terminal)
• Hone: AI CLI tool config audit (Codex CLI ~/.codex/, Antigravity CLI ~/.gemini/, Claude Code ~/.claude/ settings)
• Gear: Project-level DevOps (CI/CD, Docker, monitoring, Git hooks)
• Scaffold: Infrastructure provisioning (cloud, Docker Compose, IaC)
• Latch: Claude Code event hooks (settings.json hooks for workflow automation)
• Pipe: GitHub Actions workflows (advanced GHA design, reusable workflows, security)

Internationalization

| Agent | Description | Output | |-------|-------------|--------| | Polyglot | "Every language deserves respect. Every user deserves their mother tongue." - i18n support. Replaces hardcoded strings with t() functions, formats dates/currencies with Intl API | i18n implementation |

Growth

| Agent | Description | Output | |-------|-------------|--------| | Growth | "Traffic without conversion is just expensive vanity." - SEO (meta/OGP/JSON-LD), SMO (social share display), CRO (CTA improvement) | Growth initiatives | | Bond | "Acquisition is expensive. Retention is profitable." - Retention strategies, re-engagement, churn prevention. Gamification, habit-forming design | Retention initiatives | | Funnel | "Above the fold is your one shot. Make every pixel convert." - LP (Landing Page) structure designer and conversion strategist. Framework-based structure design (AIDA/PAS/BAB/4Ps), hero section craft, CTA placement strategy, social proof hierarchy, mobile-first responsive implementation | LP structure, copy, specs | | Crest | "Your brand is what people say when you're not in the room." - Engineer self-branding strategist. GitHub/LinkedIn/blog/conference/SNS positioning, profile optimization, content strategy | Branding strategy |

Analytics

| Agent | Description | Output | |-------|-------------|--------| | Pulse | "What gets measured gets managed. What gets measured wrong gets destroyed." - KPI definition, tracking event design, dashboard spec creation | Metrics design | | Experiment | "Every hypothesis deserves a fair trial. Every decision deserves data." - A/B test design, hypothesis documentation, sample size calculation, feature flag implementation | Experiment reports |

Operations

| Agent | Description | Output | |-------|-------------|--------| | Triage | "In chaos, clarity is the first act of healing." - Incident response, impact assessment, recovery procedures, postmortem creation | Operations reports | | Mend | "Known failures deserve known fixes. Speed of recovery defines reliability." - Auto-repair agent for known failure patterns. Receives Triage diagnostics and Beacon alerts, executes runbooks based on safety tier classification, performs staged verification, and manages rollback | Repair results, verification reports |

Triage > Mend > Beacon chain: Triage (diagnosis) > Mend (auto-repair) > Beacon (monitoring recovery)

Browser Automation

| Agent | Description | Output | |-------|-------------|--------| | Vector | "The browser is a stage. Every click is a scene." - Browser automation via Playwright/Chrome DevTools. Data collection, form interaction, screenshots, network monitoring | Automation scripts | | Director | "A demo that moves hearts moves products." - Feature demo video production using Playwright 1.59 page.screencast. 3-sec layered hook, archetype-based scenarios (30s/60s/90s/180s), multi-aspect (16:9/9:16/4:5/1:1), WCAG 2.2 + Audio Description, VMAF/PSNR/SSIM quality gate, transcript + VideoObject JSON-LD for AI citation | Demo videos + transcript + JSON-LD + /97 quality report |

Director vs Vitrine responsibilities:

• Director: Browser (Web UI) demo videos (Playwright, .webm output)

Workflows

Basic Usage

• Invoke an agent with /AgentName
• The agent executes the task
• Suggests handoff to other agents as needed

Orchestration with Nexus

Use Nexus for complex tasks. Nexus operates in the following modes:

| Mode | Trigger | Behavior | Interaction | |------|---------|----------|-------------| | Full Auto | ## NEXUS_AUTORUN + simple task | Fully automatic execution | Only on errors | | Guided | ## NEXUS_GUIDED or default | Confirms at decision points | Option-based interaction | | Interactive | ## NEXUS_INTERACTIVE | Confirms at each step | Always interactive | | Continue | ## NEXUS_HANDOFF | Result handoff | Interaction as needed |

Interactive Execution (Guided/Interactive)

Each agent asks for user confirmation at important decision points (using the platform's interaction capabilities):

• Start confirmation: Confirms approach after chain design, before execution
• Decision point confirmation: Security risks, destructive changes, multiple approaches, etc.
• Questions as options: Choose from 2-4 options ("Other" is always available)

# Example option-based question
questions:
  - question: "A potential security vulnerability was found. How would you like to proceed?"
    header: "Security"
    options:
      - label: "Audit with Sentinel (Recommended)"
        description: "Request review from the security specialist agent"
      - label: "Continue with acknowledged risk"
        description: "Proceed at your own risk"
      - label: "Abort investigation"
        description: "Stop for safety"

Automatic Mode Selection by Complexity

| Indicator | SIMPLE | COMPLEX | |-----------|--------|---------| | Estimated steps | 1-2 | 3+ | | Affected files | 1-3 | 4+ | | Security-related | No | Yes | | Destructive changes | No | Yes |

• SIMPLE + NEXUS_AUTORUN: Fully automatic execution
• COMPLEX: Automatically switches to Guided mode (interaction required)

Chain Templates by Task Type

Investigation & Understanding

| Task | Description | Chain | |------|-------------|-------| | INVESTIGATE/feature | Feature existence/implementation investigation | Lens | | INVESTIGATE/flow | Data flow/processing flow tracing | Lens > Canvas | | INVESTIGATE/onboarding | Full codebase understanding | Lens > Scribe | | INVESTIGATE/pre-impl | Investigation then implementation | Lens > Builder > Radar |

Lens vs Scout: Lens = codebase understanding and feature exploration ("Does X exist?", "How does Y flow?"), Scout = bug investigation and root cause analysis ("Why did it break?")

Bug Fixes

| Task | Description | Chain | |------|-------------|-------| | BUG/simple | Simple bug fix | Scout > Builder > Radar | | BUG/complex | Complex bug (RCA required) | Scout > Sherpa > Builder > Radar > Sentinel | | BUG/frontend | Frontend bug | Scout > Artisan > Radar |

Feature Development

| Task | Description | Chain | |------|-------------|-------| | FEATURE/S | Small feature | Builder > Radar | | FEATURE/M | Medium feature | Sherpa > Forge > Builder > Radar | | FEATURE/L | Large feature | Spark > Sherpa > Forge > Builder > Radar > Quill | | FEATURE/frontend | Frontend feature | Sherpa > Forge > Artisan > Radar | | FEATURE/fullstack | Full-stack feature | Sherpa > Forge > Artisan > Builder > Radar | | FEATURE/api | API development | Gateway > Builder > Radar |

UI/UX

| Task | Description | Chain | |------|-------------|-------| | UI/new | New UI implementation | Vision > Forge > Vitrine > Muse > Artisan > Radar | | UI/redesign | UI redesign | Vision > Muse > Palette > Flow > Artisan > Radar | | UI/component | Component creation | Forge > Vitrine > Muse > Artisan > Radar | | UI/animation | Animation addition | Flow > Artisan > Radar | | UX/research | UX research | Field > Echo > Palette | | UX/improve | UX improvement | Echo > Palette > Artisan > Radar | | UX/session-analysis | Session analysis | Trace > Echo > Palette | | UX/persona-validation | Persona validation | Field > Trace > Echo |

Refactoring

| Task | Description | Chain | |------|-------------|-------| | REFACTOR/small | Small refactor | Zen > Radar | | REFACTOR/arch | Architecture improvement | Atlas > Sherpa > Zen > Radar | | REFACTOR/legacy | Legacy modernization | Shift (detect) > Sherpa > Zen > Radar |

Performance

| Task | Description | Chain | |------|-------------|-------| | PERF/frontend | Frontend optimization | Bolt > Artisan > Radar | | PERF/backend | Backend optimization | Bolt > Builder > Radar | | PERF/db | Database optimization | Tuner > Schema > Builder > Radar |

AI/ML

| Task | Description | Chain | |------|-------------|-------| | AI/rag | RAG pipeline design | Oracle > Stream > Builder > Radar | | AI/llm-app | LLM application design | Oracle > Builder > Radar | | AI/safety | AI safety review | Oracle > Sentinel > Oracle | | AI/prompt-ops | Prompt engineering & evaluation | Oracle > Radar |

Observability/SRE

| Task | Description | Chain | |------|-------------|-------| | SRE/slo | SLO definition & monitoring | Beacon > Gear > Builder | | SRE/observability | Full observability setup | Beacon > Gear > Builder > Radar |

Security

| Task | Description | Chain | |------|-------------|-------| | SECURITY/audit | Static analysis | Sentinel > Builder > Radar | | SECURITY/pentest | Dynamic testing | Probe > Builder > Radar > Probe | | SECURITY/full | Full audit | Sentinel > Probe > Builder > Radar > Sentinel |

Testing

| Task | Description | Chain | |------|-------------|-------| | TEST/unit | Unit test addition | Radar | | TEST/e2e | E2E test addition | Voyager | | TEST/coverage | Coverage improvement | Radar > Voyager | | TEST/load | Load testing | Siege > Bolt | | TEST/chaos | Chaos engineering | Siege > Triage > Builder | | TEST/contract | Contract testing | Gateway > Siege > Radar | | TEST/mutation | Mutation testing | Siege > Radar |

Review

| Task | Description | Chain | |------|-------------|-------| | REVIEW/pr | PR review | Judge > Zen/Builder/Sentinel | | REVIEW/security | Security review | Judge > Sentinel |

Git/PR

| Task | Description | Chain | |------|-------------|-------| | GIT/pr-prep | PR preparation | Guardian > Judge | | GIT/commit-split | Commit splitting | Guardian | | GIT/pr-full | Implement > PR > Review | Builder > Guardian > Judge > Zen | | GIT/release | Release notes generation | Guardian |

Decision Making

| Task | Description | Chain | |------|-------------|-------| | DECISION/arch | Architecture selection | Magi > Builder/Zen | | DECISION/strategy | Strategic decisions | Magi > Spark | | DECISION/office-hours | Founder office hours advisory | Sage > Builder/Plea/Sherpa | | DECISION/retro | Postmortem on a recent decision/outcome | Sage |

Analysis

| Task | Description | Chain | |------|-------------|-------| | ANALYSIS/impact | Change impact analysis | Ripple > Builder > Radar | | ANALYSIS/standards | Standards compliance check | Canon > Builder > Radar | | ANALYSIS/cleanup | Code cleanup | Sweep > Zen > Radar |

Subtraction & Culture

| Task | Description | Chain | |------|-------------|-------| | SUBTRACT/feature-gate | Feature proposal subtraction gate | Spark > Void > Magi | | SUBTRACT/scope-check | Scope validation | Sherpa > Void > Sherpa | | SUBTRACT/arch-simplify | Architecture over-engineering detection | Atlas > Void > Zen |

Documentation

| Task | Description | Chain | |------|-------------|-------| | DOCS/prd | PRD creation | Scribe | | DOCS/srs | SRS creation | Scribe | | DOCS/design | Design document creation | Scribe | | DOCS/spec-to-build | Spec to implementation | Spark > Scribe > Sherpa > Builder | | DOCS/code | Code documentation | Quill | | DOCS/component | Component documentation | Vitrine > Quill | | DOCS/architecture | Architecture diagrams | Canvas | | DOCS/convert | Format conversion | Morph | | DOCS/report | PR report | Harvest > Morph | | DOCS/learning | Change-based learning doc | Tome | | DOCS/onboarding | Onboarding material from changes | Trail > Tome |

Demo & Recording

| Task | Description | Chain | |------|-------------|-------| | DEMO/prototype | Prototype demo | Forge > Director > Growth |

Infrastructure & DevOps

| Task | Description | Chain | |------|-------------|-------| | INFRA/ci | CI/CD setup | Gear > Radar | | INFRA/cloud | Cloud setup | Scaffold > Gear | | INFRA/cli | CLI development | Anvil > Radar |

Deploy & Release

| Task | Description | Chain | |------|-------------|-------| | DEPLOY/release | Release execution | Guardian > Launch | | DEPLOY/full | Full pipeline | Radar > Guardian > Launch > Harvest |

Modernization

| Task | Description | Chain | |------|-------------|-------| | MODERNIZE/stack | Tech stack refresh | Lens > Shift (detect+modernize) > Sherpa > Builder > Radar | | MODERNIZE/i18n | Internationalization | Polyglot > Artisan > Radar | | MODERNIZE/structure | Repository structure improvement | Grove > Sherpa > Zen > Radar |

Strategy & Growth

| Task | Description | Chain | |------|-------------|-------| | STRATEGY/seo | SEO improvement | Growth > Artisan > Radar | | STRATEGY/compete | Competitive analysis to implementation | Compete > Spark > Builder > Radar | | STRATEGY/feedback | Feedback integration | Voice > Spark > Builder > Radar | | STRATEGY/metrics | Metrics infrastructure | Pulse > Builder > Radar | | STRATEGY/retention | Retention initiatives | Bond > Spark > Builder > Radar | | STRATEGY/ab-test | A/B test design | Experiment > Builder > Radar | | STRATEGY/data | Data pipeline | Stream > Schema > Builder > Radar |

Game Development

| Task | Description | Chain | |------|-------------|-------|

Parallel Execution (Rally Integration)

For large-scale tasks where parallel execution is beneficial, Nexus escalates to Rally.

| Task | Description | Parallel Chain | |------|-------------|---------------| | FEATURE/L (parallel) | Large-scale full-stack | Sherpa > Rally(Artisan + Builder + Radar) | | FEATURE/fullstack (parallel) | Frontend + Backend | Rally(Artisan, Builder, Radar) | | FEATURE/multi (parallel) | Multiple independent features | Sherpa > Rally(Builder x N, Radar) | | BUG/multiple (parallel) | Multiple independent bug fixes | Rally(Builder x N) > Radar | | REFACTOR/arch (parallel) | Multi-module refactoring | Atlas > Sherpa > Rally(Zen x N) > Radar | | SECURITY/full (parallel) | Static + dynamic parallel scan | Rally(Sentinel, Probe) > Builder > Radar | | TEST/coverage (parallel) | Unit + E2E parallel testing | Rally(Radar, Voyager) | | MODERNIZE/stack (parallel) | Multi-area modernization | Shift (detect+modernize) > Sherpa > Rally(Builder x N) > Radar | | DOCS/full (parallel) | Code docs + diagrams + stories | Rally(Quill, Canvas, Vitrine) |

Rally Escalation Criteria: Rally is triggered when there are 2+ independent implementation steps, changes span 4+ files across 2+ domains, or Sherpa detects a parallel_group.

Nexus parallel vs Rally: Nexus's built-in PARALLELBRANCHES is for lightweight parallelism (each branch < 50 lines). Rally's multi-session parallelism is used for substantial implementation work.

Product Lifecycle (Titan)

| Task | Description | Chain | |------|-------------|-------| | PROJECT/full | Full product from ambiguous goal | Titan (9-phase lifecycle via Nexus) | | PROJECT/mvp | MVP-focused delivery | Titan (DISCOVER→BUILD→VALIDATE→LAUNCH) |

Titan vs Nexus: Titan = product-level orchestration (what to build, when, and which agents). Nexus = task-level execution (how to chain agents for each task). Titan issues task chains to Nexus.

Other

| Task | Description | Chain | |------|-------------|-------| | INCIDENT | Incident response | Triage > Scout > Builder | | TEST/quality | Iterative quality improvement | Judge > Zen > Radar | | INVESTIGATE/regression | Regression investigation | Trail > Scout > Builder > Radar |

Messaging & Real-time

| Task | Description | Chain | |------|-------------|-------| | MESSAGING/bot | Bot development | Relay > Builder > Radar | | MESSAGING/webhook | Webhook handler | Gateway > Relay > Builder > Radar | | MESSAGING/realtime | Real-time communication | Relay > Scaffold > Builder > Radar | | MESSAGING/multi-channel | Multi-channel integration | Relay > Builder > Radar |

Shared Knowledge

Agents share knowledge through the .agents/ directory:

| File | Purpose | When to Update | |------|---------|---------------| | PROJECT.md | Shared knowledge + activity log | Required for all agents after completing work | | {agent}.md | Agent-specific learnings | When domain-specific discoveries are made |

PROJECT.md Structure

• Architecture Decisions - Record of architecture choices
• Domain Glossary - Unified terminology
• API & External Services - External service constraints
• Known Gotchas - Known pitfalls
• Security Considerations - Security constraints
• Performance Budgets - Performance targets
• Activity Log - Agent work history

Agent Principles

All agents follow these principles:

Common Rules

• Changes under 50 lines - Aim for small, safe changes
• Respect existing patterns - Follow project conventions
• Run tests - Run tests before and after changes
• Journal only significant learnings - Don't record routine work

Boundary Types

| Marker | Meaning | |--------|---------| | Always do | Must always be done | | Ask first | Requires confirmation | | Never do | Must never be done |

Directory Structure

skills/
├── _common/
│   └── INTERACTION.md  # Shared interaction rules
├── _templates/
│   └── PROJECT.md      # Project knowledge template
├── architect/SKILL.md  # Agent design meta-designer
├── anvil/SKILL.md      # CLI/TUI construction
├── artisan/SKILL.md    # Frontend implementation
├── atelier/SKILL.md    # Design-to-implementation pipeline orchestrator
├── atlas/SKILL.md      # Architecture
├── attest/SKILL.md     # Specification compliance verification
├── beacon/SKILL.md     # Observability/SRE
├── bolt/SKILL.md       # Performance
├── builder/SKILL.md    # Production implementation
├── canon/SKILL.md      # Standards compliance (OWASP/WCAG/OpenAPI/ISO)
├── canvas/SKILL.md     # Visualization
├── cast/SKILL.md       # Persona casting & registry management
├── compass/SKILL.md    # Skill ecosystem navigator and onboarding guide
├── compete/SKILL.md    # Competitive research
├── darwin/SKILL.md     # Ecosystem self-evolution orchestrator
├── director/SKILL.md   # Demo video recording
├── echo/SKILL.md       # Persona validation
├── experiment/SKILL.md # A/B test design
├── flow/SKILL.md       # Animation
├── forge/SKILL.md      # Prototyping
├── funnel/SKILL.md     # LP structure design and conversion strategy
├── frame/SKILL.md      # Figma design-to-code bridge
├── gauge/SKILL.md      # SKILL.md normalization audit & self-evolution
├── gateway/SKILL.md    # API design
├── gear/SKILL.md       # DevOps
├── grove/SKILL.md      # Repository structure design
├── growth/SKILL.md     # SEO/CRO
├── guardian/SKILL.md   # Git/PR management
├── harvest/SKILL.md    # PR info collection & report generation
├── hearth/SKILL.md     # Personal dev environment config
├── helm/SKILL.md       # Business strategy simulation
├── hone/SKILL.md       # Codex CLI config audit & optimization
├── judge/SKILL.md      # Code review (codex review)
├── latch/SKILL.md      # Claude Code hook management
├── launch/SKILL.md     # Release management
├── lens/SKILL.md       # Codebase comprehension & investigation
├── lore/SKILL.md       # Cross-ecosystem knowledge curator
├── bazaar/SKILL.md       # Premium LP studio chain orchestrator
├── magi/SKILL.md       # Multi-perspective decision making
├── matrix/SKILL.md     # Universal multi-dimensional analysis
├── mend/SKILL.md       # Known failure auto-repair
├── morph/SKILL.md      # Document format conversion
├── muse/SKILL.md       # Design
├── vector/SKILL.md  # Browser automation
├── nexus/SKILL.md      # Orchestrator
├── orbit/SKILL.md      # Nexus-autoloop completion specialist
├── oracle/SKILL.md     # AI/ML design & evaluation
├── palette/SKILL.md    # UX
├── polyglot/SKILL.md   # i18n
├── prose/SKILL.md      # UX writing & content strategy
├── pipe/SKILL.md       # GitHub Actions workflow design
├── probe/SKILL.md      # Dynamic security testing (DAST)
├── pulse/SKILL.md      # Metrics design
├── quill/SKILL.md      # Documentation
├── radar/SKILL.md      # Testing
├── rally/SKILL.md      # Multi-session parallel orchestrator
├── relay/SKILL.md      # Messaging integration & real-time communication
├── field/SKILL.md # User research
├── ripple/SKILL.md     # Pre-change impact analysis
├── bond/SKILL.md     # Retention
├── trail/SKILL.md     # Git history investigation
├── riff/SKILL.md       # Interactive brainstorming partner
├── sage/SKILL.md       # YC-style office hours advisory
├── scaffold/SKILL.md   # Infrastructure
├── schema/SKILL.md     # DB schema design
├── siege/SKILL.md      # Advanced testing (load/contract/chaos/mutation)
├── scribe/SKILL.md     # Project documentation (PRD/SRS/design docs)
├── accord/SKILL.md     # Cross-team integrated spec packages
├── scout/SKILL.md      # Bug investigation
├── sentinel/SKILL.md   # Static security analysis (SAST)
├── sherpa/SKILL.md     # Task decomposition
├── sigil/SKILL.md      # Dynamic project-specific skill generation
├── vitrine/SKILL.md   # Storybook story management
├── sketch/SKILL.md     # AI image generation (Gemini API)
├── spark/SKILL.md      # Feature proposals
├── stream/SKILL.md     # Data pipelines
├── sweep/SKILL.md      # Dead code detection
├── titan/SKILL.md      # Product lifecycle meta-orchestrator
├── tome/SKILL.md       # Change-to-learning documentation
├── trace/SKILL.md      # Session replay analysis
├── triage/SKILL.md     # Incident response
├── tuner/SKILL.md      # DB performance optimization
├── vision/SKILL.md     # Creative direction
├── void/SKILL.md       # YAGNI enforcement & complexity reduction
├── voice/SKILL.md      # User feedback
├── voyager/SKILL.md    # E2E testing
└── zen/SKILL.md        # Refactoring

Usage Examples

Single Agent Usage

Category-by-category examples for all 123 agents.

Orchestration

Chain Design (Nexus)

/Nexus
I want to implement a login feature. What steps should I follow?

Output: Task classification (FEATURE/M), recommended chain (Sherpa > Forge > Builder > Radar), prompt for the first step

Task Decomposition (Sherpa)

/Sherpa
The payment feature implementation task is too complex to organize. Please break it down.

Output: List of atomic steps completable within 15 minutes, progress checklist, specific instructions for the first task to start

Agent Design (Architect)

/Architect
Design an agent specialized in input validation.
I want it to handle Zod/Yup schema validation and error message generation.

Output: SKILL.md (complete specification), reference/*.md (3-7 domain-specific knowledge files), Nexus integration design

Product Delivery (Titan)

/Titan
Build me a task management SaaS with team collaboration features.

Output: 9-phase product lifecycle execution — market analysis, architecture design, parallel implementation via Rally, security hardening, E2E validation, documentation, and launch preparation. All decisions logged autonomously.

Project Skill Generation (Sigil)

/Sigil
Analyze this project and generate useful skills for the team.

Output: Tech stack analysis, skill opportunity discovery, Micro/Full skills generated to .claude/skills/ (e.g., new-page, new-api-route, deploy-flow)

Targeted Skill Creation (Sigil)

/Sigil
Generate a skill for creating new API routes in this Express project.

Output: Project-specific new-route.md skill with templates matching the project's existing patterns and conventions

Architect vs Sigil responsibilities:

• Architect: Designs universal ecosystem agents (400-1400 lines, SKILL.md)
• Sigil: Generates project-specific skills from live context (10-400 lines, .claude/skills/)

Autoloop Completion Scripts (Orbit)

/Orbit
Generate completion scripts for the Nexus autoloop that deploys and validates a staging environment.
Ensure the loop halts on test failures.

Output: Runner script with halt conditions, operation contract (SLA/budget/guardrails), audit checklist

Investigation & Planning

Bug Investigation (Scout)

/Scout
Users are reporting they can't log in. Please investigate the cause.

Output: Investigation report including reproduction steps, root cause, files to fix, and recommended fix approach

Feature Proposal (Spark)

/Spark
Suggest features to improve this application's usability.

Output: Feature proposal specification (Markdown) leveraging existing data/logic

Session Replay Analysis (Trace)

/Trace
The checkout flow has a high abandonment rate. Please analyze actual session data.

Output: Frustration signal detection, per-persona behavioral patterns, UX problem report

Persona Validation (Trace)

/Trace
Validate the "Mobile-First Millennial" persona defined by Field against real data.

Output: Persona definition validity check, sub-segment discovery, handoff to Field

Trace vs Echo vs Field responsibilities:

• **Fie