resolve-pr-parallel
Skill1 starsChanged 5 months agoMITView on GitHub
Resolve all PR comments using parallel processing. Use when addressing PR review feedback, resolving review threads, or batch-fixing PR comments.
In this repository30 other files it gives its agents.
- .codex/AGENTS.mdAGENTS.md
- compound-engineeringSkill
- compound-engineeringSkill
- agent-browserSkill
- agent-native-architectureSkill
- agent-native-auditSkill
- brainstormingSkill
- cavemanSkill
- compound-docsSkill
- compound-engineeringSkill
- compounding-operating-systemSkill
- compound-refreshSkill
- create-agent-skillsSkill
- document-reviewSkill
- file-todosSkill
- finishing-branchSkill
- frontend-designSkill
- gemini-imagegenSkill
- git-worktreeSkill
- grill-meSkill
- ideateSkill
- i-have-adhdSkill
- laravel-conventionsSkill
- orchestrating-swarmsSkill
- rcloneSkill
- setupSkill
- skill-creatorSkill
- systematic-debuggingSkill
- ubiquitous-languageSkill
- xml-tag-structureSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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
- Distinctive: line 25
All PR comments and review threads
- Distinctive: line 35
Ask the user to paste the PR/MR review comments.
- Distinctive: line 69
Create a TodoWrite list of all unresolved items grouped by type:
- Distinctive: line 81
If there are 3 comments, spawn 3 agents:
- Distinctive: line 87
Always run all in parallel subagents/Tasks for each Todo item.
- Distinctive: line 91
Commit changes with a clear message referencing the PR feedback
- Very specific: line 108
Should return an empty array [].
- Distinctive: line 117
All unresolved review threads addressed
≈ “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
Resolve PR Comments in Parallel
Resolve all unresolved PR review comments by spawning parallel agents for each thread.
Context Detection
Claude Code automatically detects git context:
- Current branch and associated PR
- All PR comments and review threads
- Works with any PR by specifying the number
Workflow
1. Analyze
Gather unresolved review comments. Use one of these methods:
Option A: User pastes comments Ask the user to paste the PR/MR review comments. This is the most reliable method and works with any Git platform.
Option B: GitHub CLI (gh)
bash ${CLAUDE_PLUGIN_ROOT}/skills/resolve-pr-parallel/scripts/get-pr-comments PR_NUMBER [OWNER/REPO]Option C: GitLab CLI (glab)
glab mr view MR_NUMBER --commentsOption D: Platform API (if access token is available)
For GitHub:
gh api repos/OWNER/REPO/pulls/PR_NUMBER/reviews
gh api repos/OWNER/REPO/pulls/PR_NUMBER/commentsFor GitLab:
curl --header "PRIVATE-TOKEN: $GITLAB_TOKEN" \
"https://YOUR_GITLAB_HOST/api/v4/projects/PROJECT_ID/merge_requests/MR_IID/discussions"For Bitbucket:
curl -u "$BITBUCKET_USER:$BITBUCKET_TOKEN" \
"https://api.bitbucket.org/2.0/repositories/WORKSPACE/REPO/pullrequests/PR_ID/comments"2. Plan
Create a TodoWrite list of all unresolved items grouped by type:
- Code changes requested
- Questions to answer
- Style/convention fixes
- Test additions needed
3. Implement (PARALLEL)
Spawn a pr-comment-resolver agent for each unresolved item in parallel.
Before dispatching pr-comment-resolver, use the platform's file-search tool against the bundled agent directory to look for pr-comment-resolver.md, then use the file-read tool to load the full template. Only if the bundled template cannot be loaded should you fall back to ov_load_global_agent "pr-comment-resolver". Before dispatching, quote the first non-empty line of the loaded template and record the source used. If you cannot quote the template because it was not found or could not be read, stop execution, raise the missing-template issue, and do not dispatch. Never dispatch a named agent by name alone.
If there are 3 comments, spawn 3 agents:
- Task pr-comment-resolver(comment1)
- Task pr-comment-resolver(comment2)
- Task pr-comment-resolver(comment3)
Always run all in parallel subagents/Tasks for each Todo item.
4. Commit & Resolve
- Commit changes with a clear message referencing the PR feedback
- Resolve each thread programmatically (GitHub):
bash ${CLAUDE_PLUGIN_ROOT}/skills/resolve-pr-parallel/scripts/resolve-pr-thread THREAD_ID- Push to remote
5. Verify
Re-fetch comments to confirm all threads are resolved:
bash ${CLAUDE_PLUGIN_ROOT}/skills/resolve-pr-parallel/scripts/get-pr-comments PR_NUMBERShould return an empty array []. If threads remain, repeat from step 1.
Scripts
- scripts/get-pr-comments - GraphQL query for unresolved review threads (GitHub)
- scripts/resolve-pr-thread - GraphQL mutation to resolve a thread by ID (GitHub)
Success Criteria
- All unresolved review threads addressed
- Changes committed and pushed
- Threads resolved (marked as resolved on the Git platform)
- Empty result from get-pr-comments on verify
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.

