Explore skills

Apply the same change across multiple repos simultaneously using parallel agent teams. Creates worktrees, applies changes, runs tests, commits, and creates PRs. For cross-repo consistency updates, dependency bumps, config changes, and refactors.

Extracts a reusable project template from a mature project — captures architecture, pipeline, conventions, CI/CD, Docker, testing, linting, and pitfalls into a portable template. Trigger: extract template, save as template, capture conventions, reusable template, templatize project, snapshot conventions.

Save the current conversation context as a reloadable snapshot. Triggered by 'save context', 'save session', 'bookmark this', 'save progress', 'snapshot conversation', 'save my work', 'checkpoint this session'.

Test a skill's quality before publishing — validate SKILL.md frontmatter schema, check instruction structure for phases and guardrails, score against the marketplace rubric out of 100, simulate a dry run to find failure points, and report a pass/fail verdict with specific fixes

Create a reusable, self-healing, self-evolving global skill — either from the current conversation context OR from a plain-language description of a workflow. Triggers on: 'turn this into a skill', 'make a skill from this', 'skillify this', 'capture this as a skill', 'save this workflow as a skill', 'create a skill for this', 'make this repeatable', 'skill this up', 'build me a skill that does X',

Set up pre-commit hooks for linting, formatting, and type-checking with commit message enforcement using conventional commits. Auto-detects stack and configures husky, lefthook, or pre-commit framework with lint-staged. Use when you want to enforce code quality on every commit, add conventional commits, prevent bad code from being committed, or set up CI-mirrored hook checks.

Configure linting, formatting, and editor integration for any stack. Sets up ESLint 9 or Biome for JS/TS, Ruff for Python, golangci-lint for Go, Clippy for Rust, RuboCop for Ruby, or dart analyze for Flutter. Adds Prettier or equivalent formatter, .editorconfig, and VS Code format-on-save. Use when you need to add a linter, fix formatting inconsistencies, migrate from legacy lint tools, or set up

Set up automated releases with semantic versioning, changelog generation, and package publishing. Configures semantic-release, changesets, release-please, goreleaser, or cargo-release based on stack. Generates GitHub Actions CI workflow for automated version bumps, git tags, and npm/PyPI/crates.io publishing. Use when you want automated versioning, need to publish packages, want changelogs from co

Scaffolds a new project from a saved template with CLAUDE.md, initial memory, recommended pipeline, known pitfalls, and foundation validation.

Self-improving skill system. Reads /recall and /metrics output, identifies which skills need patching based on rework patterns and regression data, generates additive patches, and logs changes. Evolves skills based on learnings from any tech stack.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Automated app improvement cycles. Assesses each app's health, prioritizes by staleness and debt, consumes recall/metrics/evolve findings from cron, then runs targeted fix pipelines per app. Fully autonomous — runs unattended via cron or manually. Triggers: tend my apps, improve my apps, app maintenance, run improvement cycle, garden, maintain apps.