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

github-issue

Skill67 starsChanged 40 days agoMITView on GitHub

House rules for filing a GitHub issue on this repo — English, evidence-first, with the sections maintainer issues use. Use whenever an issue is being written, filed, or reworded.

22 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 4 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

Filing an issue

English only. Maintainer issues go through gh issue create and skip the web forms in .github/ISSUE_TEMPLATE/ (those are for outside reporters). Label with bug or enhancement.

Title

One line naming the observed behaviour, not the fix. Specific enough to be recognised in a list; a colon may add the cause.

  • ✅ Transcript drops mid-turn messages: Claude replies to something the view never shows
  • ❌ Bug in session reader · ❌ Fix the SDK read

Bug body

  • ## What happens — the wrong behaviour in user terms, then the mechanism: the module and file.ts:line that produce it, and the snippet if the bug is in it.
  • ## Verified — the evidence from this machine: what's in the JSONL vs. what the read path returns, counts, how many real sessions show it. An unverified claim is marked as a hypothesis.
  • ## Possible directions — optional, one bullet per approach with its cost. Do not write the patch here.

Enhancement body

  • ## The gap — what you can't do today and what you do instead.
  • ## What it would look like — the view or namespace it lands in, and what it shows. Concrete, no mockup prose.
  • ## Notes — the modules it would touch, prior art in the repo, open questions.

Rules

Short beats complete: no logs dumped whole, no restating the architecture — link CLAUDE.md instead. One defect per issue; split a shared root cause into linked issues and say so ("Split out of #245"). Search gh issue list --state all for a duplicate first.

Nothing real from the host machine: an issue is public and permanent, so the evidence in it is described, never pasted. ## Verified reports what the read path returns against what the file holds — row types, subtypes, how many sessions out of how many — and not the content of any of them. 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 or memory, no personal identifier: a person, an address, an account, an employer, a client. A name that has to appear is a synthetic stand-in of the same shape (/Users/alice, "Acme2.0"), and an excerpt is trimmed to the field under discussion. The same holds for every comment on the issue.

No authorship attribution: the issue reads as written by the maintainer — no 🤖 Generated with Claude Code footer, no claude.ai/code session link, no "I asked Claude to…". Claude Code appears only as the subject (the CLI whose data ClaudeLens reads), never as the author; evidence is reported as observed on this machine, not as something an assistant found.

gh issue create --title "…" --label bug --body-file <scratchpad>/issue-body.md

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.