Composite skill — research a question, challenge the conclusion, plan adoption, and capture the decision.
Composite skill — safely refactor a module end-to-end with sequencing, parallel implementation, post-refactor cleanup, and rationale capture.
Shortcut for security review on current change set. Runs layered checks (secret-scan, dep-audit, semgrep, OWASP patterns, prompt-injection review).
Route a task to the most fitting skill or agent. Parses user intent, checks installed-skill inventory, and picks the best match (single skill or chain).
Losslessly compress PNG and SVG assets in place and generate .webp siblings for every raster image. Use when the user asks to "compress assets", "optimize images", "shrink the…
Graceful degradation when primary approach fails. Try alternates in priority order; record which path succeeded for future routing.
Docker and container development agent skill and plugin for Dockerfile optimization, docker-compose orchestration, multi-stage builds, and container security hardening.
Define and manage recurring automated agent runs — CI monitoring, dep updates, security scans
Assemble a Jira/Linear/GitHub-Issue body from recent commits, diff, and branch context
Guide for creating specialized Claude Code subagents with proper YAML frontmatter, focused descriptions, system prompts, and tool configurations.
Composite skill — land a safe first PR in an unfamiliar repo without rediscovery loops or guessing at conventions.
Use when the user asks to generate API tests, create integration test suites, test REST endpoints, or build contract tests. — from LucasSantana-Dev/forgekit
Diff the Anthropic `claude-plugins-official` marketplace against installed plugins and surface the delta, filtering known-unwanted entries (language LSPs you don't use, SaaS…
Optimize context usage for the session by reducing bloat, improving token efficiency, and focusing on relevant areas.
Composite skill — configure a fresh or under-configured repo for the release-branch workflow in one pass.
Evaluate LLM outputs systematically — benchmarks, automated metrics, human preference, and regression tracking
Regenerate `docs/roadmap.md` for a repo from all specs under `docs/specs/` + their frontmatter (status, tags, pr). Produces Now/Next/Recently-shipped sections.
Composite skill — take a PR from "I think it's ready" to merged with full gate verification. Chains pr-merge-readiness (verdict) → ci-watch / gh-fix-ci (if blockers) →…
Manually improve corpus quality by adding missing docs and filling retrieval gaps
Run mutation testing against a project's test suite to verify the tests actually catch failures when source code is broken.
Sync Claude Code AI tooling (skills, MCP servers, rules) across Warp, Cursor, and VSCode. Idempotent — safe to re-run.
Audit and prune a bloated test suite down to the minimum tests that hit the coverage threshold and guard real behavior.
Run full quality gate suite before committing or creating a PR
Onboard into an unfamiliar repository fast before making any changes
Trigger a full or incremental reindex of the RAG corpus
Track and report token usage and estimated cost per session, agent, and phase
Sync durable project or session knowledge into the available memory systems
Meta-adder for toolkit artifacts. Single entry point to add a skill, pattern, best-practice, hook, agent, or guide with correct frontmatter + sync to 4 publish targets.
Build and debug Retrieval-Augmented Generation pipelines — chunking, embedding, retrieval, reranking
Commit, push, and open a pull request with a conventional commit message
Evaluate retrieval quality from the local RAG index
Deep research on a topic using web search, docs, and codebase analysis
Examine what's actually stored in the index for specific items
Local build-error triage. Detects common compile errors and suggests fixes
Git-level WIP safety net. Stashes uncommitted work, tags, and pushes to remote
Verify work before committing, pushing, or requesting review
Auto-extract reusable patterns from the current session into skills or memory