gh-address-comments
Skill4 starsChanged 7 months agoMITView on GitHub
Fetch all review comments and threads on the current branch's open GitHub PR using the gh CLI, present a numbered summary, and address the ones the user selects.
32 other projects use a version of this.
Adopted by
Most recently taken up by
- informaticolorenzo/skill-maestra-publictheir own version, first seen Nov 8, 2026
- AgnesAI-Labs/agnet-skills-cntheir own version, first seen Nov 1, 2026
- taljeon/plzdotheir own version, first seen Nov 1, 2026
- damacus/agent-skillstheir own version, first seen Oct 29, 2026
- hmjBill/skillstheir own version, first seen Oct 29, 2026
- davidanthonyn/claude-skillstheir own version, first seen Oct 20, 2026
Used with
Projects with it also use email-draft-polish, codebase-migrate and 10 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.
ComposioHQSkillemail-draft-polish
Draft, rewrite, or condense emails with target tone, length, and audience; use for cold outreach, replies, status updates, or escalations where clarity and brevity matter.
Also in 4 projects that use this
ComposioHQSkillcodebase-migrate
Run large codebase migrations and multi-file refactors. Uses the Composio CLI to coordinate issue tracking, batched PRs, and CI verification while the agent executes the transforms locally across hundreds of files.
Also in 4 projects that use this
petestewartSkilldatadog-logs
Query Datadog logs via the Logs Search API v2. Use when the user asks to "check the logs", "search logs", "find errors in Datadog", "look up logs for", "show me production logs", "check for errors", "search Datadog", or any request involving log search, error investigation, or production debugging that requires Datadog log data.
Also in 3 projects that use this
MicrosoftSkilldeploy-pipeline
Triggers a Power Platform Pipeline deployment run for a Power Pages solution. Selects a target stage, validates the package, optionally configures deployment settings (environment variables, connection references), then deploys and polls for completion. Use when asked to: "deploy pipeline", "run pipeline", "trigger deployment", "deploy to staging", "deploy to production", "run power platform pipeline", "deploy solution via pipeline", "promote solution", "push to staging", "push to production".
Also in 3 projects that use this
- +8 more from ComposioHQ
Other versions32 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 32
- openai/skills★ 27ksame name
- ComposioHQ/awesome-codex-skills★ 17ksame name
- composio-community/awesome-codex-skills★ 16ksame name
- JetBrains/skills★ 386same name
- ulises-jeremias/agent-toolkit★ 19same name
- PSPDFKit-labs/pi-skills★ 17same name
- taljeon/plzdo★ 9same name
- airborne12/agent-skills★ 6same name
- yeaight7/agent-powerups★ 6same name
- whz39coding/zh-awesome-codex-skills★ 4same name
22 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 repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- code-reviewSkill
- code-simplifierSkill
- comment-analyzerSkill
- conventions-improverSkill
- feature-devSkill
- frontend-designSkill
- frontend-layoutSkill
- gh-fix-ciSkill
- mcp-server-devSkill
- review-toolkitSkill
- security-threat-modelSkill
- silent-failure-hunterSkill
- test-analyzerSkill
- type-design-analyzerSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 30 edited versions we read keep these.
5
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 14
Verify gh authentication before doing anything else:
- Very specific: line 20
If unauthenticated, ask the user to run gh auth login, then stop.
- Distinctive: line 38
Run the following to get all review threads (inline) and conversation comments:
- Distinctive: line 65
If GraphQL is unavailable, fall back to:
- Distinctive: line 85
If the user already provided numbers in the skill argument, proceed with those.
- Distinctive: line 93
Read the relevant file and context.
- Distinctive: line 99
After all fixes, provide a brief summary listing which comments were addressed and any that were skipped (with reason).
“Common” is measured: kept by at least 6 in 10 of the 30 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 Comments
Fetch all review comments for the current branch's open PR, present a numbered summary, and apply fixes for the comments the user selects.
Prerequisites
Verify gh authentication before doing anything else:
gh auth statusIf unauthenticated, ask the user to run gh auth login, then stop.
Workflow
1. Resolve the PR
# if the user specified a PR number or URL:
gh pr view <number-or-url> --json number,url,headRefName
# otherwise (current branch):
gh pr view --json number,url,headRefNameExtract owner and repo from the returned url field — PR URLs have the form https://github.com/<owner>/<repo>/pull/<number>, so split on / to get the 4th and 5th segments. These are the base (target) repository coordinates, and are reliable even for cross-fork PRs.
2. Fetch comments
Run the following to get all review threads (inline) and conversation comments:
gh api graphql -f query='
query($owner:String!, $repo:String!, $number:Int!) {
repository(owner:$owner, name:$repo) {
pullRequest(number:$number) {
number url title state
comments(first:100) {
nodes { id body author { login } createdAt }
}
reviews(first:100) {
nodes { id state body author { login } submittedAt }
}
reviewThreads(first:100) {
nodes {
id isResolved isOutdated path line
comments(first:100) {
nodes { id body author { login } createdAt }
}
}
}
}
}
}' -F owner=<owner> -F repo=<repo> -F number=<pr-number>If GraphQL is unavailable, fall back to:
gh pr view <pr-number> -R <owner>/<repo> --json reviews,reviewRequests,commentsNote: the fallback output does not include thread-level isResolved/isOutdated fields. In fallback mode, treat all returned comments as actionable.
3. Present a numbered summary
List every unresolved comment/thread (or all comments in fallback mode) with a number, author, file/line (if inline), and a one-line description of the requested change. Example:
1. @alice [src/auth.ts:42] — Use bcrypt instead of MD5 for password hashing
2. @bob — Nit: rename `doThing` to `processPayload` for clarity
3. @alice [src/auth.ts:88] — Add input validation before DB query4. Ask which to address
If the user already provided numbers in the skill argument, proceed with those. Otherwise ask:
Which comments should I address? (e.g. "1 3" or "all")
5. Apply fixes
For each selected comment:
- Read the relevant file and context.
- Apply the requested change.
- Note any cases where the comment is unclear or the fix has side effects — confirm with the user before proceeding.
6. Summarize
After all fixes, provide a brief summary listing which comments were addressed and any that were skipped (with reason).
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.

