gh-address-comments
Skill1 starsChanged 5 months agoMITView on GitHub
Address actionable GitHub pull request review feedback. Use when the user wants to inspect unresolved review threads, requested changes, or inline review comments on a PR, then implement selected fixes. Use the GitHub app for PR metadata and flat comment reads, and use the bundled GraphQL script via `gh` whenever thread-level state, resolution status, or inline review context matters.
We split this skill into the rules it gives an agent
16 rules. 0 are common, 11 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 28 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Run all gh commands with elevated network access.
- Distinctive: line 15
If the user provides a repository and PR number or URL, use that directly.
- Very specific: line 16
If the request is about the current branch PR, use local git context plus gh auth status and gh pr view --json number,url to resolve it.
- Distinctive: line 18
Use the GitHub app from this plugin to fetch PR metadata and patch context when the repo and PR are known.
- Very specific: line 19
Use the bundled scripts/fetch_comments.py workflow whenever the task depends on unresolved review threads, inline review locations, or …
- Distinctive: line 20
Use connector-only comment reads only for lightweight top-level PR comment summaries.
- Distinctive: line 26
If the user did not ask to fix everything, ask which threads to address.
- Distinctive: line 27
If the user asks to fix everything, interpret that as all unresolved actionable threads and call out anything ambiguous.
- Distinctive: line 29
Keep each code change traceable back to the thread or feedback cluster it addresses.
- Distinctive: line 30
If a comment calls for explanation rather than code, draft the response rather than forcing a code change.
- Distinctive: line 36
Do not reply on GitHub, resolve review threads, or submit a review unless the user explicitly asks for that write action.
- Distinctive: line 37
If review comments conflict with each other or would cause a behavioral regression, surface the tradeoff before making changes.
- Distinctive: line 38
If a comment is ambiguous, ask for clarification or draft a proposed response instead of guessing.
- Distinctive: line 39
Do not treat flat PR comments from the connector as a complete representation of review-thread state.
- Very specific: line 40
If gh hits auth or rate-limit issues mid-run, ask the user to re-authenticate and retry.
- Very specific: line 44
If neither the connector nor gh can resolve the PR cleanly, tell the user whether the blocker is missing repository scope, missing PR …
“Common” is measured: kept by at least 6 in 10 of the 28 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
GitHub PR Comment Handler
Use this skill when the user wants to work through requested changes on a GitHub pull request. Use the GitHub app from this plugin for PR metadata and patch context, but treat thread-aware review data as a gh api graphql problem because the connector comment surface is flat and does not preserve full review-thread state.
Run all gh commands with elevated network access. If CLI auth is required, confirm gh auth status first and ask the user to authenticate with gh auth login if it fails.
Workflow
- Resolve the PR.
- If the user provides a repository and PR number or URL, use that directly.
- If the request is about the current branch PR, use local git context plus
gh auth statusandgh pr view --json number,urlto resolve it.
- Inspect review context with thread-aware reads.
- Use the GitHub app from this plugin to fetch PR metadata and patch context when the repo and PR are known.
- Use the bundled
scripts/fetch_comments.pyworkflow whenever the task depends on unresolved review threads, inline review locations, or resolution state. That script fetchesreviewThreads,isResolved,isOutdated, and file and line anchors that the connector comment surface does not preserve. - Use connector-only comment reads only for lightweight top-level PR comment summaries.
- Cluster actionable review threads.
- Group comments by file or behavior area.
- Separate actionable change requests from informational comments, approvals, already-resolved threads, and duplicates.
- Confirm scope before editing.
- Present numbered actionable threads with a one-line summary of the required change.
- If the user did not ask to fix everything, ask which threads to address.
- If the user asks to fix everything, interpret that as all unresolved actionable threads and call out anything ambiguous.
- Implement the selected fixes locally.
- Keep each code change traceable back to the thread or feedback cluster it addresses.
- If a comment calls for explanation rather than code, draft the response rather than forcing a code change.
- Summarize the result.
- List which threads were addressed, which were intentionally left open, and what tests or checks support the change.
Write Safety
- Do not reply on GitHub, resolve review threads, or submit a review unless the user explicitly asks for that write action.
- If review comments conflict with each other or would cause a behavioral regression, surface the tradeoff before making changes.
- If a comment is ambiguous, ask for clarification or draft a proposed response instead of guessing.
- Do not treat flat PR comments from the connector as a complete representation of review-thread state.
- If
ghhits auth or rate-limit issues mid-run, ask the user to re-authenticate and retry.
Fallback
If neither the connector nor gh can resolve the PR cleanly, tell the user whether the blocker is missing repository scope, missing PR context, or CLI authentication, then ask for the missing repo or PR identifier or for a refreshed gh login.
Other versions30 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- yeaight7/agent-powerups★ 668% same
- damacus/agent-skills★ 231% same
Wrote their own version · 28
- 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
- whz39coding/zh-awesome-codex-skills★ 4same name
- dokuczacz/OmniFlowBeta★ 2same name
18 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.
Used alongsideProjects 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
In this repository31 other files it gives its agents.
- skills/book-to-skill/AGENTS.mdAGENTS.md
- skills/book-to-skill/CLAUDE.mdCLAUDE.md
- ai-paper-digestSkill
- battery-statusSkill
- book-to-skillSkill
- codebase-mapSkill
- codebase-overviewSkill
- codebase-summarySkill
- concept-wiki-htmlSkill
- frontend-designSkill
- gh-fix-ciSkill
- githubSkill
- grounded-file-qaSkill
- imagegenSkill
- learn-codebaseSkill
- lecture-note-writerSkill
- ning-python-scientific-plottingSkill
- openai-docsSkill
- plugin-creatorSkill
- ponytail-auditSkill
- ponytail-debtSkill
- ponytail-gainSkill
- ponytail-helpSkill
- ponytail-reviewSkill
- ponytailSkill
- repo-quick-scanSkill
- review-agentSkill
- skill-creatorSkill
- skill-installerSkill
- use-code-wikiSkill
- yeetSkill
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.

