agentleFS
leonardourcileonardourci/pnyx/.agents/skills/write-skill/SKILL.md

write-skill

Skill4 starsChanged 2 days agoApache-2.0View on GitHub

Create or change an agent skill in Pnyx, either a contributor skill in .agents/skills or a skill shipped with the CLI in skills/. Covers naming, frontmatter, what belongs in a skill versus docs, keeping it short, and registering it. Read before writing any SKILL.md.

27 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use grill, write-docs and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • renatorozasSkill

    grill

    Adversarial code review. Don't let me ship until the changes pass your scrutiny.

    Also in 5 projects that use this

  • SentrySkill

    write-docs

    Create or update documentation pages for the Abacus docs site. Use when adding new documentation, updating existing pages, or ensuring docs stay in sync with code changes. Ensures pages follow Starlight patterns and build correctly.

    Also in 3 projects that use this

  • AWSSkill

    ship

    Finalize dev work on an issue branch — update docs, push, and open a PR.

    Also in 4 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 4 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 5 projects that use this

  • AWSSkill

    retro

    Conduct a retrospective on a coding session.

    Also in 3 projects that use this

The file

Files
SKILL.md

Write a skill

Skills follow the Agent Skills format: a folder holding a SKILL.md with YAML frontmatter and Markdown instructions. Pnyx has two kinds:

  • Contributor skills live in .agents/skills/<name>/ and guide work on this repository. Claude Code finds them through .claude/skills, a committed link to ../.agents/skills, so a new one needs no extra link.
  • Shipped skills live in skills/<name>/, are installed by Pnyx's setup and read by agents using Pnyx. Their names start with pnyx- except the owner-facing inscribe, and tests read them, so pnpm verify runs those tests when they change.

Naming and frontmatter

  • Name the action, verb first where it reads naturally (review-code, write-front-end, pnyx-manage-workers), not the tool that runs it or a vague category. Use lowercase letters, numbers and single hyphens. The frontmatter name must equal the folder name.
  • Give the frontmatter name and description. The description, under 1,024 characters, says what the skill does and when to read it, with the words a future agent would match on. Add paths only when the skill applies to a fixed set of files, as write-front-end does for web/**.

Body

  • Write instructions for doing the task: the checks, their order and what to report. Use checklists or numbered steps, with plain sentences.
  • Point to the rule's home (AGENTS.md, docs/, another skill) instead of restating it, so rules have one home and cannot drift apart. A skill holds what an agent needs only while doing that task.
  • Keep it short. Detail needed only sometimes goes in a references/ file the body links to.
  • Describe the current project. A skill never asks for session journals, handoff files or a running history of reviews and test results.
  • Apply deslop to the text.

Registration

  • For a shipped skill, add its name to src/setup/skill-names.ts, in GLOBAL_SKILLS for every agent or HYDRA_SKILLS for Hydra's own, so setup installs it, and to the skills/ row of the layout table in AGENTS.md.
  • For a contributor skill that is a required step, link it where the step is described (AGENTS.md, CONTRIBUTING.md or docs/development.md).
  • Re-check the hard rules before committing: name matches the folder, the description fits, and the file reads as plain Markdown.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.