codex-write-pr-description
Skill118 starsChanged 37 days agoMITView on GitHub
Write or revise PR_AGENTDESC.md from the branch, its commits, and the repository template, then run the mechanical validator until it passes. Use as a delegated writer from codex-pr, codex-fix-pr, or codex-merge-pr. Pass review findings or branch-drift notes in the task.
In this repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- analyze-sessionSkill
- codex-analyze-sessionSkill
- codex-commitSkill
- codex-fix-proseSkill
- codex-fix-prSkill
- codex-merge-prSkill
- codex-prSkill
- codex-rebaseSkill
- codex-resolve-rebase-conflictsSkill
- codex-review-commit-messageSkill
- codex-review-pr-descriptionSkill
- codex-review-prose-fixSkill
- codex-review-squash-messageSkill
- codex-watch-prSkill
- codex-write-prose-fixSkill
- commitSkill
- fix-proseSkill
- fix-prSkill
- merge-prSkill
- prSkill
- rebaseSkill
- releaseSkill
- resolve-rebase-conflictsSkill
- review-commit-messageSkill
- review-pr-descriptionSkill
- review-prose-fixSkill
- review-squash-messageSkill
- watch-prSkill
- write-pr-descriptionSkill
- write-prose-fixSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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
- Very specific: line 21
Before returning, read the finished draft for closed enumerations and scope words such as only, every, and never.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Write a pull request description
Work only in the repository named by the caller. The task may also carry review findings or a note about new commits. Resolve every supplied finding.
Gather context once:
bash .agents/skills/codex-write-pr-description/scripts/context.shWrite PR_AGENTDESC.md with exactly these elements: YAML frontmatter containing base, draft, labels, reviewers, assignees, and milestone, followed by a Conventional Commits level-one title. Put every section the repository template declares after the title, in the template's order. Use a nonempty label list drawn from the context.
Describe the whole branch. Keep Summary, Why, Verification, Risk, and Related distinct. Verification names commands actually run. Avoid counts, diff narration, unsupported claims, selling language, and request/session/model/tool provenance. Preserve accurate existing prose during revisions.
Before returning, read the finished draft for closed enumerations and scope words such as only, every, and never. Establish those claims from the branch or weaken them.
Run until clean:
bash .agents/skills/codex-pr/scripts/validate-description.shReturn only one of:
DRAFT: WRITTEN
changed: <one line per material edit, or first draft>
addressed: <each supplied finding, or nothing requested>DRAFT: BLOCKED
reason: <decision or missing prerequisite>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.

