framework

Run a single-session AI optimization audit on the codebase

Run a single-session code review audit on the codebase

Run a single-session engineering productivity audit on the codebase

Run a comprehensive enhancement audit across the entire project - code, product, UX, content, workflows, infrastructure, external services, and meta-tooling.

Run a single-session performance audit on the codebase

Run a comprehensive multi-stage automation audit with parallel agents

Run a single-session refactoring audit on the codebase

Run a single-session security audit on the codebase

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Structured discovery-first planning for complex tasks. Ask exhaustive categorized questions, build a standalone decision record, then produce a detailed implementation plan with audit checkpoints for user approval before any code is written.

Add technical debt items to MASTER_DEBT.jsonl. Supports two workflows: PR-context deferred debt (with PR number) and manual ad-hoc debt discovery. Automatically detects which workflow to use based on whether a PR number is provided.

Intelligent health dashboard with scoring, benchmarks, trends, and interactive alert-by-alert workflow. Triggers: "alerts", "check alerts", "what needs attention", "system health", "show warnings", "pending issues". Default mode (--limited) checks 16 categories. Use --full for comprehensive reporting with all 36 categories.

Aggregate and deduplicate findings from multiple audit reports

Run all 9 domain audits in staged waves and aggregate results

Run a multi-stage parallel documentation audit with 18 specialized agents

Meta-check for audit system health — runs diagnostics on domain audits and ecosystem audits, suggests next audits

Save session state for recovery after compaction or failures. Default: save to local files (.claude/state/). With --mcp: also save to MCP memory for cross-session persistence.

Ad-hoc code review skill. Includes automated code analysis, best practice checking, security scanning, and review checklist generation. Use when reviewing changes, providing code feedback, identifying issues, or ensuring code quality standards.

Orchestrates all 7 ecosystem audits in staged waves with 4-concurrent-agent limit, aggregates results into a unified health report with cross-audit insights, domain heat maps, and priority-ranked findings.

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing process from solo effort to collaborative partnership.

Interactive wizard to scaffold a new audit type with skill, template, and directory

Comprehensive diagnostic of the documentation ecosystem — 16 categories across 5 domains with composite health scoring, trend tracking, patch suggestions, and interactive finding-by-finding walkthrough. Covers index sync, link integrity, content quality, generation pipelines, and documentation coverage.

Scan all docs, auto-fix formatting/headers/links, report issues as JSONL, and generate enhancement recommendations

Check documentation sync and auto-update doc artifacts. Combines sync checking (template-instance validation) with update automation (index regeneration, cross-doc dependencies, archive verification).

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope.

Comprehensive diagnostic of the Claude hooks ecosystem — 19 categories across 6 domains with composite health scoring, trend tracking, patch suggestions, and interactive finding-by-finding walkthrough. Covers hook configuration, code quality, pre-commit pipeline, functional correctness, state integration, and CI/CD pipeline health.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Interactive orchestrator for multi-AI consensus audits with any-format input support

Comprehensive diagnostic of the PR review ecosystem — 18 categories across 5 domains with composite health scoring, trend tracking, patch suggestions, and interactive finding-by-finding walkthrough. Triggers: "pr ecosystem audit", "audit pr ecosystem", "review health", "ecosystem health".

PR Review Retrospective -- actionable analysis of a PR's review cycle

PR Code Review Processor

Automatically fix pre-commit hook failures and retry the commit. Use when a git commit fails due to ESLint errors, pattern compliance violations, missing document headers, cross-document dependency issues, or documentation index staleness. Spawns a targeted subagent to fix each category of failure, then re-stages and re-commits. Reduces context waste from manual fix-commit-retry cycles.

Comprehensive diagnostic of the script infrastructure — 18 categories across 5 domains with composite health scoring, trend tracking, patch suggestions, and interactive finding-by-finding walkthrough. Covers scripts for module consistency, safety patterns, reachability, code quality, and testing.

Complete verification steps before starting any work session

Comprehensive diagnostic of the Session Ecosystem — 16 categories across 5 domains with composite health scoring, trend tracking, patch suggestions, and interactive finding-by-finding walkthrough. Covers session lifecycle hooks, state persistence, compaction resilience layers, cross-session safety, and integration configuration.

Complete verification steps before ending the session

Interactive behavioral quality audit for individual skills. This skill should be used when evaluating a skill against 10 quality categories to identify gaps, improve attention management, and produce actionable decisions. Produces a decision record and updated skill files.

Comprehensive diagnostic of the skill ecosystem — 21 categories across 5 domains with composite health scoring, trend tracking, patch suggestions, and interactive finding-by-finding walkthrough. Covers all skills, cross-references, bloat detection, and agent orchestration health.