agentleFS
giulio333giulio333/ClaudeLens/.claude/skills/github-pr/SKILL.md

github-pr

Skill67 starsChanged 40 days agoMITView on GitHub

House rules for opening a pull request on this repo — English title and body, the sections the PR template expects, and the gates to run first. Use whenever a PR is being written, opened, or its description rewritten.

  • Commits and pushes

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use zeroclaw, skill-creator and 1 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.
  • openagenSkill

    zeroclaw

    Help users operate and interact with their ZeroClaw agent instance — through both the CLI (`zeroclaw` commands) and the REST/WebSocket gateway API. Use this skill whenever the user wants to: send messages to ZeroClaw, manage memory or cron jobs, check system status, configure channels or providers, hit the gateway API, troubleshoot their ZeroClaw setup, build from source, or do anything involving the `zeroclaw` binary or its HTTP endpoints. Trigger this even if the user just says things like 'check my agent status', 'schedule a reminder', 'store this in memory', 'list my cron jobs', 'send a message to my bot', 'set up Telegram', 'build zeroclaw', or 'my bot is broken' — these are all ZeroClaw operations.

    Also in 3 projects that use this

  • SentrySkill

    skill-creator

    Create new agent skills following the Agent Skills specification. Use when asked to "create a skill", "add a new skill", "write a skill", "make a skill", "build a skill", or scaffold a new skill with SKILL.md. Guides through requirements, writing, registration, and verification.

    Also in 8 projects that use this

  • SentrySkill

    commit

    Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.

    Also in 3 projects that use this

The file

Files
SKILL.md

Opening a PR

Everything is written in English — title, body, commit messages. No exceptions.

Before opening

npm run format:check && npm run typecheck && npm run lint && npm test && npm run build must all pass. Never launch the app to verify UI; say so and leave it to the user.

Title

One line, imperative, plain prose that says what the change does — not what file it touches. Append (#N) when it closes an issue. Conventional prefixes (feat(chat):, fix(live):) are fine for small scoped work; prose titles are the norm for anything bigger.

  • ✅ Recover the frontmatter fields around a bad line instead of dropping them all (#248)
  • ❌ fix parseFrontmatter · ❌ Various improvements

Body

Fill .github/pull_request_template.md; don't invent sections and don't drop the checklist.

  • What this changes — 2–5 sentences: the defect (or the gap) and the mechanism of the fix. Name the module and the line that mattered (electron/modules/x.ts:42); a short code block only when the bug is the snippet. Then Closes #N.
  • How to verify — what a reviewer runs, plus the real evidence you already have (test counts, a check against real ~/.claude/ data).
  • Checklist — tick honestly; leave unticked what you didn't do.
  • Screenshots — UI changes only, light + dark.

Describe behaviour, not the diff: no file-by-file walkthrough, no repetition of what the checklist already says. Flag anything left out and why.

Create it

gh pr create --title "…" --body-file <scratchpad>/pr-body.md

Nothing real from the host machine

A PR is public and permanent, so nothing that exists only on the machine it was written on goes into it — not in the title, the body, the commit messages, a reply to a review or a screenshot. No absolute path from this machine's home, no name of a project, folder or file outside this repo, no line of a real transcript, memory or conversation, and no personal identifier of any kind: a person, an address, an account, an employer, a client. Evidence gathered from real data is reported by shape and count ("14 row types the reader never mentions", "3 files of 261"), never by quoting what it says; a name that has to appear is a synthetic stand-in of the same shape — /Users/alice, "Acme2.0". Screenshots use mock data. It is the rule the fixtures already follow, applied to the text written around the change.

No authorship attribution

The PR reads as written by the maintainer. Never add the 🤖 Generated with Claude Code footer, a claude.ai/code session link, a co-author trailer, or any phrasing that says the change was produced by an assistant — not in the title, the body, or the commits. Claude Code stays in the text only as the subject of the app (the CLI whose data ClaudeLens reads, its transcripts, its SDK), never as the author.

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.