Claude Skills

Surfaces expert frameworks and proven methodologies before creating OR evaluating skills, hooks, agents, or commands. Helps select approaches from domain masters. Triggers: methodology, framework, expert approach, best practices, masters, proven method, domain expertise, how should I approach, what's the best way, evaluate skill, review methodology, is this grounded, optimization check. Use when starting creation workflows, evaluating methodology gaps, or seeking domain expertise. Do not use if you already have a specific methodology or are fixing syntax/structural issues.

Transform project brief into detailed, testable specifications using spec-driven development methodology

Interactive selector and router for architecture paradigms. Triggers: architecture selection, pattern comparison, system design, ADR creation, architecture decision, paradigm evaluation, new system architecture, architecture planning, which architecture, compare architectures Use when: selecting architecture patterns for new systems, comparing paradigm trade-offs, creating architecture decision records, evaluating architecture fit for team size and domain complexity, planning implementation roadmaps DO NOT use when: implementing a specific known paradigm - use the specific architecture-paradigm-* skill (hexagonal, layered, microservices, etc.) instead. DO NOT use when: reviewing existing architecture - use architecture-review instead. Use this skill BEFORE making architecture decisions. Check even if unsure about needs.

Triggers: source, cite, reference, factual claim, verify, attribution Intelligent sourcing that requires citations only for high-value factual claims, balancing accuracy with token efficiency.

Socratic questioning and ideation methodology for project conception using structured brainstorming frameworks

Architect skills as modular blocks to control token usage and complexity. Triggers: skills, architecture, modular, design-patterns, modularity, skill design, skill architecture, modularization, token optimization, skill structure, refactoring skills, new skill creation, skill complexity. Use when creating skills >150 lines, breaking down monolithic skills, or planning new architecture. Do not use for evaluating existing skills (use skills-eval) or writing human-facing prose (use writing-clearly-and-concisely). Check this skill before starting any new skill development.

Evaluate and improve Claude skill quality through auditing. Triggers: quality-assurance, skills, optimization, tool-use, performance-metrics, skill audit, quality review, compliance check, improvement suggestions, token usage analysis, skill evaluation, skill assessment, skill optimization, skill standards, skill metrics, skill performance. Use when reviewing skill quality, preparing skills for production, or auditing existing skills. Do not use when creating new skills (use modular-skills) or writing prose (use writing-clearly-and-concisely). Use this skill before shipping any skill to production.

Configure GitHub Actions workflows for CI/CD (test, lint, typecheck, publish)

Triggers: refine, code quality, clean code, refactor, duplication, algorithm efficiency, complexity reduction, code smell, anti-slop, craft Analyze and improve living code quality: duplication, algorithmic efficiency, clean code principles, architectural fit, anti-slop patterns, and error handling robustness. Use when: improving code quality, reducing AI slop, refactoring for clarity, optimizing algorithms, applying clean code principles DO NOT use when: removing dead/unused code (use conserve:bloat-detector). DO NOT use when: reviewing for bugs (use pensive:bug-review). DO NOT use when: selecting architecture paradigms (use archetypes skills). This skill actively improves living code, complementing bloat detection (dead code removal) with quality refinement (living code improvement).

Inline reversibility assessment for embedded War Room escalation from other commands

Triggers: safety, critical, NASA, power of 10, defensive coding, assertions, bounds checking Guidelines from NASA's Power of 10 rules for writing robust, verifiable code. Adapted for general software development with context-appropriate rigor. Use when: Writing critical code paths, reviewing for robustness, improving code quality DO NOT use: As rigid requirements for all code - match rigor to consequence

Detect and flag AI-generated content markers in documentation and prose. Triggers: ai slop, ai-generated, llm markers, chatgpt phrases, claude tells, slop detection, ai cleanup, humanize text, remove ai markers, detect chatgpt, detect llm, writing quality, ai tells. Use when reviewing documentation for AI markers, cleaning up LLM-generated content, or auditing prose quality. Do not use when generating new content (use doc-generator) or learning writing styles (use style-learner).

Diagnoses and fixes CI/CD pipeline failures. Use when user mentions CI failures, build errors, test failures, or pipeline issues. Do NOT load for: local builds, standard implementation work, reviews, or setup.

Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent setup, PM coordination, Cursor setup, or 2-agent operations. Do NOT load for: solo operation, workflow execution, or handoff processing.

Cleans up and organizes project files. Use when user mentions cleanup, archive, file bloat, or organizing Plans.md/session logs. Do NOT load for: implementation work, reviews, new feature development, or deployment.

Search for package-specific usage rules and best practices from Elixir packages. Use when you need coding conventions, patterns, common mistakes, or good/bad examples for packages like Ash, Phoenix, Ecto, etc.

Sets up new projects and generates workflow files like CLAUDE.md, AGENTS.md, Plans.md. Use when user mentions setup, initialization, new projects, or workflow file generation. Do NOT load for: implementation work, reviews, build verification, or deployments.

Guides diagnosis and resolution when problems occur. Use when user mentions something broken, errors, or that it doesn't work. Do NOT load for: successful builds, new feature implementation, or reviews.