This skill should be used when the user asks to "browse RAG memory", "search captures", "list memory files", "find past inputs", "show knowledge base", or "review stored context". It browses and searches the RAG memory archive indexed in rag-index.json. Use this skill whenever the user mentions memory browsing, RAG search, captured files, or knowledge base exploration.

This skill should be used when the user asks to "create a new SDD skill", "scaffold a skill", "forge a skill", "build a new command", or mentions "skill creator". It manufactures production-grade SDD/IIKit skills with full scaffolding: SKILL.md, scripts, templates, references, hooks, evals, and knowledge graph registration. Use this skill whenever a new pipeline phase, utility command, or experience skill is needed — even if the user just says "I need a new /sdd command".

This skill should be used when the user asks to "check status", "show pipeline status", "view progress", "what phase am I on", "show feature stages", or "display pipeline overview". It runs the status script to display a visual pipeline table with phase dots, feature stages, and next step recommendations. Use this skill whenever the user mentions status, progress, pipeline overview, or current phase.

This skill should be used when the user asks to "sync upstream", "update from IIC/kit", "pull latest framework", "sync intent integrity chain", "update SDD engine", or "reapply brand overlay". It syncs the upstream IIC/kit repository and reapplies the MetodologIA brand layer. Use this skill whenever the user mentions sync, upstream, IIC/kit update, or brand reapplication.

This skill should be used when the user asks to "start tour", "onboard me to SDD", "show me around", "walk me through the pipeline", "how does SDD work", or "give me a guided introduction". It runs an 8-step interactive walkthrough of the SDD pipeline covering constitution, specs, plan, checklist, testify, tasks, analyze, implement, and ship. Use this skill for onboarding, orientation, or learning SDD.

This skill should be used when the user asks to "verify project", "run verification", "check integrity", "validate structure", "audit assertions", "verify brand compliance", or "run checks". It executes the 8-check verification suite covering structure, brand, tokens, assertions, and workspace integrity. Use this skill whenever the user mentions verify, validate, integrity check, or compliance audit.

SDD Phase 1 — User Specs from natural language. FR-NNN, SC-NNN, acceptance scenarios. Enhanced: bug-fix intent detection, semantic diff on re-run, workspace RAG capture.

SDD Phase 5 — Dependency-ordered task breakdown with parallel markers and story labels.

SDD Phase 0 — Define governance principles, coding standards, quality gates, and TDD policy. Enhanced: validates context.json, updates pipeline state, suggests workspace creation.

This skill should be used when the user asks to "build knowledge graph", "trace requirements", "show traceability", "map dependencies between artifacts", "visualize requirement flow", or "detect orphan nodes". It builds a knowledge graph tracing Constitution principles to requirements, tests, and tasks with edge types (governs, verified_by, implemented_by, validates). Use this skill whenever the user mentions knowledge graph, traceability, orphan detection, or requirement mapping.

Generate a structured plugin concept brief from a user idea. Trigger: ideate plugin, brainstorm plugin, plugin concept, new plugin idea, create plugin concept. Researches existing plugins for overlap, proposes movement structure and component counts.

Design MOAT asset strategy per skill: which subdirectories needed, what content they contain, naming conventions. Trigger: plan MOAT, MOAT strategy, asset planning, reference planning, plan skill assets.

Validates plugin directory layout against the official Claude Code plugin spec. Triggers: validate structure, check layout, directory audit, plugin skeleton check.

Generate production-ready agent .md and command .md files from designs. Enforces plugin subagent constraints and alias linkage. Trigger: spec agent, spec command, generate agent file, write command file, create agent specification.

Create MOAT directory structures and populate asset files (references/, examples/, prompts/, scripts/, assets/) for plugin skills. Trigger: build MOAT assets, create skill assets, populate references, generate examples, build skill directories.

Scaffold a complete plugin directory from architecture plans and specs. Creates all files, then validates structure. Trigger: build plugin, scaffold plugin, create plugin directory, assemble plugin, generate plugin files.

Design a plugin agent: role, tool allowlist, skill assignments, execution flows, operating principles. Trigger: design agent, agent design, create agent spec, plan agent, draft agent. Enforces plugin subagent constraints (no hooks/mcpServers/permissionMode in frontmatter).

Generate production-ready SKILL.md and MOAT asset files from a skill design. Enforces MOAT quality dimensions (>=7 on all 6), 500-line body limit, progressive disclosure. Trigger: spec skill, generate skill spec, write SKILL.md, create skill specification, produce skill MOAT.

Design a plugin skill in detail: frontmatter, procedure outline, quality criteria, anti-patterns, edge cases, tool selection. Trigger: design skill, skill design, create skill spec, plan skill, draft skill.

THE CRITICAL SKILL -- validates hooks.json structure, event names, and type-event compatibility. Detects prompt/agent hooks on events lacking ToolUseContext. Triggers: validate hooks, check hooks.json, hooks audit, hook safety check.