agent-skills

In the author's own words, from each skill's SKILL.md — showing the first 30 of 83 files.

• agents-md

  Make AGENTS.md the canonical project-instructions file, with CLAUDE.md and GEMINI.md as stubs that import it, and audit it for drift and lessons. Use when onboarding a project, auditing AGENTS.md, or updating agent instructions.

  .agents/skills/agents-md/SKILL.md on GitHub (opens in a new tab)

• architect

  Take a feature from an idea to a spec and plan by running the research, spec, grill, and plan skills in order. Use when architecting a feature from an idea or this session's discussion, or exploring a design before planning.

  .agents/skills/architect/SKILL.md on GitHub (opens in a new tab)

• bcp

  Branch, commit, and open a PR in one step.

  .agents/skills/bcp/SKILL.md on GitHub (opens in a new tab)

• branch

  Create a git feature branch named for the current session's work. Use when the user asks to start, create, or cut a branch.

  .agents/skills/branch/SKILL.md on GitHub (opens in a new tab)

• changelog

  Add an entry to the project's CHANGELOG.md from the uncommitted diff or the branch's changes against main. Use when the user asks to update the changelog, add a changelog entry, or record changes.

  .agents/skills/changelog/SKILL.md on GitHub (opens in a new tab)

• clarify

  Pin down the user's intent before starting work. Use when a request is too vague to act on ("help me with this", "I need something", "let's work on…"), or when another skill hits a vague request.

  .agents/skills/clarify/SKILL.md on GitHub (opens in a new tab)

• cleanup

  Audit a codebase or paths for AI slop and clean it up with you steering each fix. Use when asked to find and remove sloppy, AI-generated code patterns.

  .agents/skills/cleanup/SKILL.md on GitHub (opens in a new tab)

• code-module-design

  Vocabulary and principles for designing deep modules. Use when designing or improving a module's interface, looking for deepening opportunities, deciding where a seam goes, making code more testable or easier for agents to navigate, or when another skill needs the deep-module vocabulary.

  .agents/skills/code-module-design/SKILL.md on GitHub (opens in a new tab)

• code-module-review

  Explain and review how a scoped piece of code is structured. Use when the user asks how a feature or package is put together; whether a PR or existing code has clean module boundaries; where new logic should live or which module should own it; or how the code could be reshaped.

  .agents/skills/code-module-review/SKILL.md on GitHub (opens in a new tab)

• code-review-feedback

  Pressure-test code-review feedback before acting on it. Use when receiving review feedback or evaluating suggested code changes.

  .agents/skills/code-review-feedback/SKILL.md on GitHub (opens in a new tab)

• code-review

  Review a PR or local changes with parallel read-only reviewer subagents, verify each finding, and check the change against its project's spec and plan. Use when reviewing a remote PR or local code, including unpushed or uncommitted changes. Pass --plan=<path> to name the plan or task list.

  .agents/skills/code-review/SKILL.md on GitHub (opens in a new tab)

• commit

  Create git commits with intelligent file grouping. Use when committing changes or drafting a commit message.

  .agents/skills/commit/SKILL.md on GitHub (opens in a new tab)

• conventions-go

  MANDATORY for any work on Go files (*.go). Load this before editing, reviewing, or creating any *.go file. Go coding conventions and style guide covering naming, error handling, testing, HTTP handlers, caching, concurrency, and observability.

  .agents/skills/conventions-go/SKILL.md on GitHub (opens in a new tab)

• conventions-markdown

  MANDATORY for any work on Markdown files (*.md). Load this before editing or creating any *.md file. Markdown formatting, repository-link, and linting conventions.

  .agents/skills/conventions-markdown/SKILL.md on GitHub (opens in a new tab)

• conventions-mermaid

  MANDATORY for any work on Mermaid files (*.mmd, *.mermaid) or Mermaid diagram blocks in Markdown. Load this before creating, editing, or validating Mermaid diagrams.

  .agents/skills/conventions-mermaid/SKILL.md on GitHub (opens in a new tab)

• conventions-python

  MANDATORY for any work on Python files (*.py). Load this before editing, reviewing, or creating any *.py file. Python coding conventions and style guide covering modern typing, tooling (ruff, mypy, uv), project structure, error handling, and testing.

  .agents/skills/conventions-python/SKILL.md on GitHub (opens in a new tab)

• conventions-sql

  MANDATORY for any work on SQL files (*.sql). Load this before editing or creating any *.sql file. SQL migration conventions covering simple DDL, idempotency, batching ALTER statements, comments, and formatting.

  .agents/skills/conventions-sql/SKILL.md on GitHub (opens in a new tab)

• critique

  Critique a document for logical fallacies and weaknesses, with a fix for each issue. Use when reviewing a plan, proposal, or other document before acting on it.

  .agents/skills/critique/SKILL.md on GitHub (opens in a new tab)

• decide

  Decision memo with a contrarian check, saved to docs/decisions/. Use when the user wants help making a consequential, hard-to-reverse, or multi-stakeholder decision.

  .agents/skills/decide/SKILL.md on GitHub (opens in a new tab)

• distill

  Condense long text without losing anything needed to act on it, checked by an inventory and audit. Use for a plan, technical guide, runbook, agent instructions, or any prose too long or hard to follow, especially before an agent executes it.

  .agents/skills/distill/SKILL.md on GitHub (opens in a new tab)

• domain-modeling

  Build and sharpen a project's domain model. Use when creating or editing a `GLOSSARY.md`, updating a legacy `CONTEXT.md`, or writing an ADR, even when the request is simply to write or update the file; when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision; or when another skill needs to maintain the domain model.

  .agents/skills/domain-modeling/SKILL.md on GitHub (opens in a new tab)

• durable-rules

  Turn friction from a coding session, or patterns from finished work, into checks, conventions, instruction changes, or skill changes so they don't recur. Use when a session ran slow, hit repeated errors, or had tool or context friction; when the user asks what should be codified so it doesn't happen again; or at the end of a plan or piece of work.

  .agents/skills/durable-rules/SKILL.md on GitHub (opens in a new tab)

• eval

  Run a skill's eval cases in a sandbox and grade them against the previous run, drafting or refreshing the cases first. Use when the user wants to test a skill in this repo, add eval cases, or check a skill edit for regressions.

  .agents/skills/eval/SKILL.md on GitHub (opens in a new tab)

• execute-plan

  Implement a whole project plan slice by slice, committing each task. Pass auto to run without prompts.

  .agents/skills/execute-plan/SKILL.md on GitHub (opens in a new tab)

• explain-code

  Explain what a PR, branch diff, commit, uncommitted change, or scoped code does and why it matters, for someone new to the repo and its parent systems. Use for a newcomer walkthrough or to understand the purpose of code; not for finding defects, approving a merge, or a stakeholder update.

  .agents/skills/explain-code/SKILL.md on GitHub (opens in a new tab)

• fix-failing-tests

  Diagnose and fix test failures from saved test output. Use when the user shares test output or says "tests fail".

  .agents/skills/fix-failing-tests/SKILL.md on GitHub (opens in a new tab)

• git-metadata

  Collect a diagnostic snapshot of a repo's git history: churn hotspots, bus factor, bug clusters, commit velocity, and crisis patterns. Use when another skill needs history signals to judge risk or where to look first.

  .agents/skills/git-metadata/SKILL.md on GitHub (opens in a new tab)

• go-testing

  Write unit and integration tests for Go services. Use when creating, editing, or updating tests, test helpers, mocks, fuzz tests, or benchmarks in Go projects.

  .agents/skills/go-testing/SKILL.md on GitHub (opens in a new tab)

• grill-me

  A relentless interview to sharpen a plan, decision, or idea.

  .agents/skills/grill-me/SKILL.md on GitHub (opens in a new tab)

• grill-with-docs

  Grill relentlessly to sharpen a plan, decision, or idea while recording ADRs and domain glossary inline. Use when stress-testing a design or plan against domain models and capturing architectural decisions.

  .agents/skills/grill-with-docs/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 418k stars · 5 skills
• superpowersby obra An agentic skills framework & software development methodology that works. 311k stars · 15 skills
• skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory. 309k stars · 30 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 295k stars · 30 skills
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 228k stars · 1 skill
• skillsby anthropics Public repository for Agent Skills 186k stars · 19 skills