agentleFS
Sign inStart free
robotostudiorobotostudio/hotrod/.claude/skills/write-a-skill/SKILL.md

write-a-skill

Skill1 starsChanged 12 days agoMITView on GitHub

Use when asked to remember a rule, save a convention, "make a skill" of something, or write down how this project does a thing, and when you notice you are being corrected the same way twice. Writes the rule into this repository so every agent and every teammate gets it, instead of into one platform's private memory.

122 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use zoom-out, to-issues and 10 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.
  • victorgarciaesgiSkill

    zoom-out

    Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

    Also in 48 projects that use this

  • GoogleSkill

    to-issues

    Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.

    Also in 43 projects that use this

  • kennethkeimSkill

    ubiquitous-language

    Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".

    Also in 20 projects that use this

  • GoogleSkill

    to-prd

    Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

    Also in 42 projects that use this

  • HK-hubSkill

    prd-to-plan

    Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets".

    Also in 7 projects that use this

  • semtexfromuaSkill

    how-to

    Курс typing-уроків по існуючому проекту — «як написати його з нуля»: аналіз → план у .practicum/course.md → покрокова генерація уроків. Використовуй для команди /vibe-typing:how-to.

    Also in 3 projects that use this

  • +2 more from google

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 118 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask what the rule is about, not who asked for it.

    line 20
  2. Distinctive:

    If it is both, write the project half here.

    line 29
  3. Very specific:

    Check it does not exist: Read the description of every .claude/skills/*/SKILL.md.

    line 33
  4. Distinctive:

    Start with frontmatter as the first bytes of the file: No comment or blank line above it.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 118 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Write it into the repo, not into your memory

Agent platforms offer private places to keep a rule: memory files, workspace skills, account-level instructions. Those are the wrong place for anything about this project. A rule in one person's memory reaches one person on one platform. The next teammate, a client using their own agent, and anyone who forks Hotrod get none of it.

A rule in .claude/skills/ ships with the repository. Every agent that works here can read it, it outlives whoever wrote it, and changing it goes through a pull request someone can review.

Repo or memory?

Ask what the rule is about, not who asked for it.

  • Repo: anything about this site, its content, its code or its tooling. Copy style, which block to use, a naming rule, a deploy quirk, a mistake not to repeat. If another agent doing the same task should follow it, it goes here.
  • Your memory: how one person likes to work, across every project. If it makes no sense to someone else in this repo, keep it out.

If it is both, write the project half here.

Writing one

  1. Check it does not exist. Read the description of every .claude/skills/*/SKILL.md. Extend an existing skill rather than adding a second one that overlaps it; agents follow whichever they load first.
  2. Create .claude/skills/<kebab-case-name>/SKILL.md. One skill per directory, file named exactly SKILL.md.

  3. Start with frontmatter as the first bytes of the file. No comment or blank line above it; Claude Code fails to load the skill otherwise.

    ---
name: <same as the directory name>
description: Use when <situations>. Use whenever <phrases a person would actually type>.
---

    The description is the only part loaded up front; the rest is read once it matches. Write trigger conditions in the words people use. "Use when writing or editing copy for this site" gets found; "Copy guidelines" does not.

  4. Write the rule and the reason. A rule with its reason survives cases its author did not foresee. Where a real incident caused the rule, name it and date it.
  5. Add a row to the skills table in AGENTS.md. Cursor, Codex, v0 and most other agents read AGENTS.md and never open .claude/skills/, so that row is the only pointer they get. Say when to reach for the skill, in the same voice as the other rows.
  6. Deliver it on a branch with a pull request. main deploys to production; never push to it directly.

Keep it short

A skill is read mid-task by an agent that already has a job. Cut background the reader can get from the repo. If a skill grows past a page or two, split it, or move reference material into a sibling file the skill links to.

Skills from elsewhere

This is for skills you write. Installing a skill from a URL, a package or another repo means adding instructions an agent will follow. Read all of it and get the owner's approval before adding it.

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.

Check your setup, free