pull-request-handoff
Skill0 starsChanged 22 days agoMITView on GitHub
Prepare a concise, evidence-backed pull request description and reviewer handoff from a known diff. Use after implementation; do not create or publish a PR unless explicitly requested.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- acceptance-qaSkill
- architecture-reviewSkill
- bug-fix-verificationSkill
- dependency-upgradeSkill
- docs-syncSkill
- idea-to-scopeSkill
- implementation-planSkill
- independent-reviewSkill
- migration-safetySkill
- performance-investigationSkill
- release-checkpointSkill
- root-cause-investigationSkill
- security-reviewSkill
- surgical-changeSkill
- test-gap-auditSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Read the patch, commit intent, tests, and affected contracts.
- Distinctive: line 12
Write a plain-English summary with user impact, key implementation decisions, compatibility or migration notes, and non-goals.
- Distinctive: line 33
If provenance cannot be established, present a draft labeled unverified diff instead of a final PR-ready claim.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Pull request handoff
Make review easy. A PR summary should explain why this diff exists, not narrate every line.
- Identify the intended base and exact change range. Check branch, HEAD, staged/unstaged state, and whether uncommitted changes are included. If the base is uncertain, do not invent it.
- Read the patch, commit intent, tests, and affected contracts. Separate changes shown in the diff from related work that is merely proposed.
- Write a plain-English summary with user impact, key implementation decisions, compatibility or migration notes, and non-goals.
- Report tests/checks by exact observed result. Mark skipped, blocked, or not-run checks explicitly. Do not convert "test command documented" into "tests passed".
- Give reviewers 2 to 4 concrete places to focus: a fragile assumption, API contract, migration boundary, concurrency path, error behavior, or risk-sensitive diff.
- Draft the PR description; do not stage, commit, push, open a PR, assign people, or publish release notes unless explicitly authorized.
Output
## Why
...
## What changed
...
## Evidence
- Ran: `<command>` (result)
- Not run: ... (reason)
## Review focus
...
## Rollout / rollback
... (when relevant)If provenance cannot be established, present a draft labeled unverified diff instead of a final PR-ready claim.
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.