draft-pr
Skill1 starsChanged 44 days agoMITView on GitHub
Writes a PR title and description to .workflow/<KEY>/pr.md from the branch's commits, the plan and the recorded verification. Use when opening a PR or asked for a PR description.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- flavio-portela/skillstheir own version, first seen Nov 1, 2026
- gigio1023/agent-skillstheir own version, first seen Oct 13, 2026
- gigio1023/gigio-skillstheir own version, first seen Oct 13, 2026
- arklexai/arksimtheir own version, first seen Oct 8, 2026
- wordpress-mobile/WordPress-Androidtheir own version, first seen Oct 8, 2026
- ComplianceAsCode/contenttheir own version, first seen Oct 8, 2026
Used with
Projects with it also use interview and frontend-design.
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.
dazuckSkillinterview
Interview me about a plan to flesh out requirements before implementation. Asks non-obvious questions one at a time until all ambiguities are resolved.
Also in 3 projects that use this
BlockSkillfrontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Also in 3 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
- wordpress-mobile/WordPress-Android★ 3.2ksame name
- ComplianceAsCode/content★ 2.8ksame name
- multigres/multigres★ 2.7ksame name
- microsoft/roosterjs★ 1.3ksame name
- arklexai/arksim★ 234same name
- g2i-ai/agents★ 52same name
- gigio1023/agent-skills★ 2same name
- gigio1023/gigio-skills★ 2same name
- zahardev/aicontext★ 2same name
- k3forx/skills★ 1same 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 repository9 other files it gives its agents.
- address-reviewSkill
- frame-productSkill
- implement-changeSkill
- plan-changeSkill
- review-diffSkill
- trace-incidentSkill
- triage-taskSkill
- write-commitSkill
- write-handoverSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 22
Check
_missing: If it lists plan or verification, that artifact does not exist. - Very specific: line 61
Close the ticket: if the backlog is local: task done <KEY>.
- Distinctive: line 70
Reviewers read the diff, not a retelling of it: Do not list every file. Explain the decisions, point at the risk.
- Distinctive: line 72
Name the critical zones: If the change touches billing, auth, user data or a migration, that belongs in the description, not discovered in …
- Distinctive: line 79
Nothing beyond what is needed: No restating the diff, no attribution footer, no "as requested", no unticked template box.
“Common” is measured: kept by at least 6 in 10 of the 13 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.
Files
draft-pr
wb <args> # wb not on PATH: python <this skill's directory>/../../lib/wb.py <args>This skill writes the description. Opening the PR is the user's call.
Steps
- Assemble the inputs.
pr context <KEY>. One call returns the branch and base, the commits on it, the changed files, the critical zones, the plan's summary and open questions, the verification verdict with each command's exit code, and ashapetelling you how much description this change earns. For a PR onto a validation branch:pr context <KEY> --target homolog. - Check
_missing. If it listsplanorverification, that artifact does not exist. Say so in the description — do not write around the gap and do not claim a check that was never run. - Write the title in the repo's commit style (
commit conventionif you have not already). One line, imperative, specific enough that a reviewer scanning a list knows what this is. Write only the shape you were given.
trivialis a title and one sentence, no headings at all.smallis What and Verification. Onlylargeearns the full template, and even then a section with nothing to say is deleted rather than left as an empty heading.## What One or two sentences. What changes, and why now. ## Why The problem, with the ticket link. Skip if the title says it. ## How Only the decisions a reviewer cannot infer from the diff — a trade-off, an approach considered and dropped, a constraint that forced the shape. ## Verification The actual commands and their results, from `pr context`. ## Risk and rollback Critical zones touched, and how to undo this. ## Open questions From the plan. An empty section is better deleted than left blank.- Check and save.
pr check --file <path> --shape <shape> --key <KEY>rejects empty sections, placeholders, unticked boxes and filler, and a PR whose plan still owes its handover. Then save to.workflow/<KEY>/pr.mdand show it. - Close the ticket if the backlog is local:
task done <KEY>. A real tracker owns its own state, andwbrefuses there rather than recording a status only this checkout believes. Say the PR is open, not that it merged.
Rules
- Only claim what was verified.
pr contextgives the real verdict and exit codes. If verification failed or was refused, the description says that. A PR claiming green tests that never ran is worse than one admitting they did not. - Reviewers read the diff, not a retelling of it. Do not list every file. Explain the decisions, point at the risk.
- Name the critical zones. If the change touches billing, auth, user data or a migration, that belongs in the description, not discovered in review.
- Name the amendments.
amendedinpr contextlists files added after the plan passed its audit. List each one with its reason under Risk, because a reviewer has to know that the plan widened mid-flight. - Carry the open questions across. A question the plan could not answer does not disappear because the code is written.
- Nothing beyond what is needed. No restating the diff, no attribution footer, no "as requested", no unticked template box.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

