address-review
Skill10 starsChanged 28 days agoApache-2.0View on GitHub
Use when the owner asks to address review feedback on an open AIP pull request - enumerate every review surface, separate clear defects from design questions, fix accepted material findings with evidence, validate once, self-review the resulting diff, and report what is ready. Commit or push only when the owner explicitly asks. Never merge.
21 other projects use a version of this.
Adopted by
Most recently taken up by
- angusfretwell/skillstheir own version, first seen Nov 4, 2026
- azarakovskiy/skillstheir own version, first seen Nov 1, 2026
- osrim/skillstheir own version, first seen Nov 1, 2026
- enocgit/sdlc-kittheir own version, first seen Oct 31, 2026
- paologum/claude-skillstheir own version, first seen Oct 25, 2026
- pedroclobo/skillstheir own version, first seen Oct 20, 2026
Used with
Projects with it also use open-pr, pr-description and 4 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.
Google CloudSkillopen-pr
Commits local changes to a new Git branch and opens a GitHub pull request through the configured GitHub MCP server. Use when proposing code changes in a new pull request. Don't use for local-only commits without a remote GitHub repository.
Also in 3 projects that use this
MicrosoftSkillpr-description
Draft Nacelle PR titles, pull request descriptions, commit titles, commit descriptions, and squash commit messages. Use when asked for PR or commit wording, a branch summary, or a PR description that can be used in a commit. Omit validation sections from commit bodies and remove filler.
Also in 3 projects that use this
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 3 projects that use this
MicrosoftSkillpr-review
Verify the technical accuracy of a vscode-docs pull request against the VS Code source code in microsoft/vscode. Use when reviewing a docs PR for factual correctness: setting names, command IDs, default values, API shapes, keybindings, versioned availability, and described behavior.
Also in 3 projects that use this
Hugging FaceSkillimplement
Make tests pass. Invoke after /write-tests produces failing tests.
Also in 3 projects that use this
- +1 more from microsoft
Other versions21 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 21
- oxcaml/oxcaml★ 932same name
- cashew-labs/libretto★ 911same name
- saffron-health/libretto★ 911same name
- gittower/git-flow-next★ 458same name
- finos/git-proxy★ 263same name
- fpindej/netrock★ 234same name
- saffron-health/opencode-gui★ 59same name
- fedemelo/agent-config★ 4same name
- lestrrat/claude-code★ 4same name
- magnusrodseth/dotfiles★ 3same name
11 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.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- post-merge-syncSkill
- release-publicationSkill
- specification-driven-implementationSkill
- address-reviewSkill
- post-merge-syncSkill
- release-publicationSkill
- specification-driven-implementationSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 21 edited versions we read keep these.
4
Distinctive
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 9
Do not turn reviewer preferences into new product semantics.
- Distinctive: line 13
Verify the live PR and branch: Read the PR state, head branch/head SHA, base branch and current checks from GitHub.
- Distinctive: line 31
Validate economically: Run targeted checks while iterating.
- Distinctive: line 48
Every material review finding is either fixed with evidence or explicitly returned to the owner as a design/specification decision.
“Common” is measured: kept by at least 6 in 10 of the 21 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
Address PR review feedback
This skill is procedural. The governing specification, ROADMAP and AGENTS.md remain authoritative. Do not turn reviewer preferences into new product semantics.
Procedure
- Verify the live PR and branch. Read the PR state, head branch/head SHA, base branch and current checks from GitHub. Work in the PR's existing dedicated worktree when available; otherwise create a worktree for the PR branch. Never switch the shared checkout merely to address a review.
- Enumerate every comment surface before editing: top-level review submissions, inline review comments/threads, and issue-level PR comments. Cross-reference duplicates and retain a disposition for each material finding.
- Classify before fixing.
- Clear correctness/contract/evidence/documentation defect: fix it.
- Specification or design question: do not guess; present the decision to the owner and stop that item.
- MINOR/NIT or preference: fix only when cheap and in scope; never expand the PR to satisfy it.
- Make evidence-backed fixes. For a behavior defect, add or strengthen a regression test when that test provides real proof. For a documentation/claim defect, verify the corrected claim against the actual code, schema, fixture or pinned evidence rather than inventing a test solely for ceremony. When a material finding exposes a repeated pattern within the changed surface, inspect and fix the same class of occurrence there rather than patching only the cited line; do not widen this into unrelated repository cleanup. Preserve the retained plan and reconciliation for specification-governed work.
- Validate economically. Run targeted checks while iterating. After the final source-relevant change, run the full AGENTS.md gate once. If the complete fix is documentation-only, use the documentation-only exemption. Any source change after the full gate invalidates that gate.
- Run the independent self-review when required by AGENTS.md. Invoke
.claude/agents/aip-reviewer.mdon the complete updated diff unless the change qualifies for the strict documentation-only exemption. Resolve BLOCKER/MAJOR findings; return semantic ambiguities to the owner. After material fixes, rerun affected validation and the reviewer once, not an open-ended nit loop. - Stop before commit/push unless explicitly authorized. Asking to "address review feedback"
authorizes editing and validation, not committing or pushing. Report the fixes, validation and
self-review result, then wait for an explicit owner instruction to commit/push. If that
authorization is given, verify the PR head branch, commit/push there only, capture the pushed SHA
from
git rev-parse HEAD, update the PR body/reconciliation when needed, post one concise summary comment, and re-check all comment surfaces once after the push. Never merge.
Completion condition
Every material review finding is either fixed with evidence or explicitly returned to the owner as a design/specification decision; required validation is green; and any required independent self-review has no BLOCKER/MAJOR findings. If the same material finding is recurring across PRs, report a candidate reusable guard separately rather than expanding the current PR. If commit/push was not explicitly authorized, finish by reporting that the fixes are ready but uncommitted. Leave merge to the owner.
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.

