ship-it

In the author's own words, from each skill's SKILL.md.

• chaos-engineering

  Adversary of /do-task — read the implemented change, map the attack surface, write adversarial unit/E2E tests that try to break it (boundaries, nulls, broken money, hostile dependencies, concurrency, malicious payloads, unexpected state), run them locally, classify each KILLED/SURVIVED/INCONCLUSIVE, promote the useful ones to permanent regressions, and deliver a Chaos Report. Never touches produc…

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

• create-product

  Turn an idea, a conversation, or loose notes into a product document ready for /create-tasks — no PM required. Runs a sparring interview to fill the gaps, synthesizes the document, and publishes it where the project tracks work.

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

• create-tasks

  Break a product scope — a product doc, a tracker item, or a whole project/milestone — into technical cards ready for AI execution via /do-task. Deterministic split heuristics, mandatory preview before creating anything.

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

• do-task

  Execute a card end to end — pick it up, implement following the guidelines, validate, open the PR, chain into /watch-pr. Full flow authorized by invocation (automode) — zero questions in the happy path; escalations park-and-notify instead of hanging. Use when the user asks to execute, implement, or do a card/task/issue.

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

• groundwork

  One-time per-project setup for the ship-it pipeline — detects tracker, repo, reviewer and notifier, asks the minimum, writes docs/agents/ config so no other skill ever asks again.

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

• make-guidelines

  Interview the dev to generate an engineering guideline — for the whole codebase (/make-guidelines) or one module (/make-guidelines <path>). Detects existing patterns first and proposes them as answers; module guidelines override codebase guidelines.

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

• watch-pr

  Monitor a pull request until merge or block — evaluate every review comment (apply reasonable fixes, always reply), rerun flaky CI once, and notify the author on approval, lock, or silence. Auto-chained by /do-task after opening a PR; also invocable standalone on any PR. Use when the user asks to watch, babysit, or monitor a PR.

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

No skill matches that filter.

Similar skills

• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• 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. 220k stars · 1 skill
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 164k stars · 6 skills
• ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms. 136k stars · 7 skills
• graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs… 127k stars · 1 skill