Tags every claim with [HECHO]/[INFERENCIA]/[SUPUESTO] evidence classification for zero-hallucination output. Trigger: "classify evidence", "tag claims", "evidence levels", "zero hallucination", "fact check output".

Applies a 10-point quality rubric to every artifact with iterative refinement until excellence criteria are met. Trigger: "excellence check", "quality rubric", "review artifact", "quality loop", "refine output".

Crafts technical business cases with ROI justification, value pillars, and executive-ready framing. Trigger: "executive summary", "business case", "pitch the solution", "ROI".

Generates specific file create/modify/delete plans with impact analysis and dependency tracking. Trigger: "plan file changes", "what files need to change", "impact analysis for changes".

Discover, evaluate, and install agent skills from the open ecosystem (skills.sh, GitHub, local plugins). Searches across Skills CLI, skills.sh leaderboard, and local plugin catalogs to recommend the best match. Trigger: find a skill, how do I do X, is there a skill for, can you do X, extend capabilities, search skills, install skill, discover skill, skill marketplace, skills.sh.

Create a feature specification from a natural language description — generates user stories with Given/When/Then scenarios, functional requirements (FR-XXX), success criteria, and a quality checklist. Use when starting a new feature, writing a PRD, defining user stories, capturing acceptance criteria, or documenting requirements for a product idea.

Create or update a CONSTITUTION.md that defines project governance — establishes coding standards, quality gates, TDD policy, review requirements, and non-negotiable development principles with versioned amendment tracking. Use when defining project rules, setting up coding standards, establishing quality gates, configuring TDD requirements, or creating non-negotiable development principles.

Maps business processes, data flows, and integration points into visual sequence diagrams and dependency graphs. Trigger: "map the flow", "show me how data moves", "integration diagram".

Systematic scan across 10 friction categories affecting development velocity. Trigger: "detect friction", "what's slowing us down", "friction analysis", "velocity blockers".

Produces structured functional specifications including use cases, business rules, and complexity/risk matrices. Trigger: "write the spec", "functional requirements", "use case analysis".

Phased execution plans with dependencies, checkpoints, rollback strategies, and file change plans. Trigger: plan implementation, create phases, design rollback, file change plan.

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

Validates plugin.json completeness, field correctness, and consistency with actual plugin contents. Triggers: validate manifest, check plugin.json, manifest audit.

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.

Validates cross-reference integrity across all plugin components. Detects broken references, orphaned skills, missing aliases, and settings.json inconsistencies. Triggers: validate cross-refs, check references, dependency audit, orphan detection.

Validates frontmatter and body structure of all skills, agents, and commands in a plugin. Triggers: validate components, check frontmatter, component audit, skill validation.

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.

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.

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.

Post-incident analysis, timeline reconstruction, contributing factor identification, and prevention recommendations. Trigger: analyze incident, post-mortem, outage review, incident timeline, blameless review.