fix-pr
Skill8 starsChanged 2 months agoMITView on GitHub
Fix PR Comments
15 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- pytorch/heliontheir own version, first seen Nov 8, 2026
- theam/claude-dev-kittheir own version, first seen Nov 1, 2026
- excatt/superclaude-plusplustheir own version, first seen Oct 13, 2026
- bjcoombs/ai-native-toolkittheir own version, first seen Oct 13, 2026
- grove/promise-to-prooftheir own version, first seen Oct 12, 2026
- tbhb/vale-ai-tellstheir own version, first seen Oct 11, 2026
Used with
Projects with it also use review-pr and release.
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
MicrosoftSkillrelease
Use ONLY when the user explicitly asks to cut/publish a Huabu desktop release or tag a version. Performs an outward action — bumps the version in apps/desktop/package.json, commits + annotated-tags vX.Y.Z, and pushes the branch + tag. That tag push auto-builds the macOS/Windows installers and publishes a GitHub Release. Provides `status`, `bump`, `tag-push`, and a one-command `run` (bump → tag-push).
Also in 3 projects that use this
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- deadlock-mod-manager/deadlock-mod-manager★ 58489% same
Wrote their own version · 14
- questdb/questdb★ 18ksame name
- pytorch/helion★ 979same name
- spiriMirror/libuipc★ 351same name
- tbhb/vale-ai-tells★ 118same name
- GiggleLiu/cryochamber★ 34same name
- bjcoombs/ai-native-toolkit★ 32same name
- Codagent-AI/agent-skills★ 31same name
- theam/claude-dev-kit★ 17same name
- excatt/superclaude-plusplus★ 14same name
- kbarendrecht/orchestrator★ 11same 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 repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .deepsec/AGENTS.mdAGENTS.md
- .cursor/rules/010-workflow.mdcCursor rule
- .cursor/rules/020-codebase-structure.mdcCursor rule
- .cursor/rules/030-coding-style.mdcCursor rule
- .cursor/rules/031-never-use-any.mdcCursor rule
- .cursor/rules/032-import-rules.mdcCursor rule
- .cursor/rules/050-testing.mdcCursor rule
- .cursor/rules/070-comments-defensive-programming.mdcCursor rule
- .cursor/rules/080-ai-interaction.mdcCursor rule
- .cursor/rules/090-changesets.mdcCursor rule
- .cursor/rules/095-calldiff.mdcCursor rule
- .cursor/rules/990-cursor-rule-editing-workaround.mdcCursor rule
- .cursor/rules/999-mdc-format.mdcCursor rule
- adversarial-reviewSkill
- agent-browserSkill
- calldiffSkill
- changesetSkill
- commitSkill
- deslopSkill
- git-conventionsSkill
- humanizerSkill
- improve-codebase-architectureSkill
- logging-best-practicesSkill
- opensrcSkill
- rebaseSkill
- recomposing-commitsSkill
- security-reviewSkill
- show-meSkill
- simplifySkill
- thermo-nuclear-code-quality-reviewSkill
- wait-whatSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 10 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
10
Distinctive
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
- Distinctive: line 56
If the user says "skip all remaining", skip the rest of the prompts and only apply already-confirmed fixes.
- Distinctive: line 58
Wait for all user responses before proceeding to the fix step.
- Distinctive: line 64
Read the relevant file(s)
- Distinctive: line 67
Follow all project coding conventions from 030-coding-style
- Distinctive: line 68
Do not make unrelated changes
- Distinctive: line 70
After all fixes are applied:
- Very specific: line 95
Use gh CLI for all GitHub interactions
- Distinctive: line 96
Never modify files not related to a specific comment being addressed
- Distinctive: line 97
If a comment is unclear, err on the side of asking rather than guessing
- Distinctive: line 99
Do not create a changeset unless a fix qualifies per 090-changesets
- Distinctive: line 111
Run lint and format
“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
Fix PR Comments
Review all open comments on the current branch's pull request, rank them by relevance, prompt for confirmation where ambiguous, then apply fixes.
Instructions
1. Gather Branch and PR Context
echo "=== BRANCH ===" && git rev-parse --abbrev-ref HEAD && echo "=== PR INFO ===" && gh pr view --json number,title,url,state,headRefName,baseRefName && echo "=== PR COMMENTS ===" && gh pr view --json comments --jq '.comments[] | {author: .author.login, body: .body, createdAt: .createdAt}' && echo "=== PR REVIEW COMMENTS ===" && gh pr view --json reviews --jq '.reviews[] | {author: .author.login, body: .body, state: .state, submittedAt: .submittedAt}' && echo "=== PR DIFF COMMENTS ===" && gh api "repos/{owner}/{repo}/pulls/$(gh pr view --json number --jq '.number')/comments" --jq '.[] | {author: .user.login, body: .body, path: .path, line: .line, diff_hunk: .diff_hunk, created_at: .created_at}'2. Rank Comments by Relevance
Analyze all gathered comments and categorize them:
Priority tiers:
- P1 - Must fix: Bug reports, broken functionality, security issues, failing tests, incorrect logic
- P2 - Should fix: Code style violations against project conventions, missing error handling, performance concerns, unclear naming
- P3 - Consider: Nitpicks, optional suggestions, cosmetic preferences, subjective style opinions
Display a ranked list grouped by priority:
P1 (Must Fix):
[1] <file>:<line> — <author>: "<comment body>"
...
P2 (Should Fix):
[2] <file>:<line> — <author>: "<comment body>"
...
P3 (Consider):
[3] <file>:<line> — <author>: "<comment body>"
...3. Prompt for Confirmation on Ambiguous Comments
For each P2 and P3 comment, ask the user:
Comment [N] —
<author>on<file>:<line>: "<comment body>"Fix this? (yes / no / skip all remaining)
- P1 comments are fixed automatically without prompting.
- P2/P3 comments require explicit user confirmation.
- If the user says "skip all remaining", skip the rest of the prompts and only apply already-confirmed fixes.
Wait for all user responses before proceeding to the fix step.
4. Apply Fixes
For each confirmed comment (all P1s + user-confirmed P2/P3s):
- Read the relevant file(s)
- Understand the context from the diff hunk
- Apply the minimal, focused fix that addresses the comment
- Follow all project coding conventions from 030-coding-style
- Do not make unrelated changes
After all fixes are applied:
pnpm lint:fix
pnpm format:fix5. Summarize
Show a concise summary:
Fixed:
[1] <file>:<line> — <brief description of fix>
...
Skipped:
[N] <file>:<line> — <reason or "user skipped">
...Then suggest staging and committing with the /commit command.
Key Points
- Use
ghCLI for all GitHub interactions - Never modify files not related to a specific comment being addressed
- If a comment is unclear, err on the side of asking rather than guessing
- Respect all rules in
.cursor/rules/when applying fixes - Do not create a changeset unless a fix qualifies per 090-changesets
Example Usage
User: "fix pr", "review pr comments", or /fix-pr
Response:
- Fetch branch, PR metadata, and all comment types
- Rank and display comments by priority
- Prompt user for P2/P3 confirmations
- Apply all approved fixes
- Run lint and format
- Show summary and suggest commit
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.

