file-issue
Skill2 starsChanged 5 days agoMITView on GitHub
File a termherd GitHub issue completely — English body, native issue type, area labels, and the board fields Horizon, Effort and Class or Severity — then check it took with just board-check. Use when asked to open, file or report an issue or bug for termherd, or when a session finds a defect worth tracking.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- pushprove-max/Commandecktheir own version, first seen Nov 8, 2026
- razbakov/skillstheir own version, first seen Nov 8, 2026
- enes-alatas/spooltheir own version, first seen Nov 8, 2026
- Sma1lboy/rovetheir own version, first seen Nov 6, 2026
- rome-os/rometheir own version, first seen Oct 21, 2026
- ultimatile/development-skillstheir own version, first seen Oct 20, 2026
Used with
Projects with it also use review-pr.
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.
DockerSkillreview-pr
Review one or more incoming Docker documentation pull requests as a maintainer. Independently validate technical claims, assess editorial fit and information architecture, choose a verdict, and draft exact inline or PR-wide feedback behind a confirmation gate. Use for requests such as "review PR 123", "is this PR correct?", "does this information belong here?", "validate this PR", or "help review backlog PRs". Do not use to maintain or fix a PR you own; use maintain-pr for that.
Also in 4 projects that use this
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- marin-community/marin★ 4.1ksame name
- rilldata/rill★ 3ksame name
- levy-street/world-of-claudecraft★ 2.3ksame name
- rome-os/rome★ 894same name
- open-thoughts/OpenThoughts-Agent★ 309same name
- Sma1lboy/rove★ 184same name
- enes-alatas/spool★ 48same name
- mlz11/ClaudeNotifier★ 36same name
- razbakov/skills★ 4same name
- pushprove-max/Commandeck★ 3same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- drive-termherdSkill
- mutation-testSkill
- run-termherdSkill
The file
Files
File an issue
Filing is half done until the issue is classified on the board; an
unclassified issue appears in no prioritised view. Board ids are in
docs/agents/tooling.md (Filing an issue on the board).
- Body, in English. Observed, expected, steps to reproduce; a guess is
labelled as one. No AI signature. Write it with the Write tool to a file
under the scratchpad and pass
--body-file <absolute path>:$TMPDIRdiffers inside and outside the sandbox. - Create with
gh issue create --title … --body-file … --label area:…outside the sandbox (ghfails TLS inside it). - Type. Fetch the type ids, never guess them, then set the type with
updateIssue(input: {id, issueTypeId}). A guessed id answers cannot be found, which reads as a missing type. - Board fields. The auto-add puts the issue on the board; fill
Horizon,Effort, andClass(Feature) orSeverity(Bug) — a Task carries neither. A security bug is 🟡 Minor at most. One literalgh project item-editper field; a worktree session refuses loops and variables, and GraphQL with inline braces (pass-F query=@file). - Check with
just board-checkoutside the sandbox: inside it the recipe reports unchecked (exit 2), which is not clean. - Link. A scoped epic's issue is cited in its
.roadmap/features/file, and the file in the issue.
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
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.

