github-deep-review — Claude Code skill: bug analysis and PR review with evidence
github-deep-review — a skill for in-depth GitHub issue and PR review. Reads code, traces the root cause, proposes the best fix, and identifies what must be verified before merge.
MIT 275 installs ★ 7,554 updated 2026-10-20
npx skills add steipete/agent-scripts --skill github-deep-review -a claude-codeWhat github-deep-review does
github-deep-review teaches an agent to analyze GitHub issues and pull requests like an experienced reviewer: code first, conclusions second. Instead of generic remarks, the skill demands proof — git history, test coverage, CI results, behavior on the current main branch. The agent gathers author context, follows the call chain from entry point through validation and routing to the persistence boundary, and checks dependency contracts from their documentation rather than assumptions.
For each bug, the skill requires answers to: what breaks, where in the code, who introduced it and when (verified through raw commits, not dates alone), whether the proposed fix is optimal, and if a larger refactor would prevent similar bugs. For PRs, it identifies specific correctness issues by file and line, lists the evidence checked, and flags remaining risks. Output is a structured report with code references and commit links, without vague suggestions.
Installation requires the gh CLI for querying GitHub and local repository access for history analysis. The skill runs on Claude Code, Codex, Cursor, GitHub Copilot, and Gemini CLI.
What it helps with
- pinpoint what breaks in a bug and locate it in the codebase
- trace the actual root cause through commit history instead of speculation
- determine whether a proposed fix is the best option available
- review a PR for correctness with references to specific code lines
- spot whether a larger refactor would eliminate a whole class of bugs
Example prompts for the agent
- Review PR #42 in our repo: what breaks, where is the root cause, what's the best fix?
- Analyze issue #15 on GitHub, reproduce the problem, and suggest a fix with a test
- Check this commit: who introduced it, why is it a regression, and how should we fix it?
How to install github-deep-review
1Skills CLI (Vercel)
npx skills add steipete/agent-scripts --skill github-deep-review -a claude-code2Manually: put the files in place
~/.claude/skills/github-deep-review/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/github-deep-review/
1Skills CLI (Vercel)
npx skills add steipete/agent-scripts --skill github-deep-review -a codex2Manually: put the files in place
.agents/skills/github-deep-review/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add steipete/agent-scripts --skill github-deep-review -a cursor2Manually: put the files in place
.cursor/skills/github-deep-review/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install steipete/agent-scripts skills/github-deep-review2Manually: put the files in place
.github/skills/github-deep-review/SKILL.md1Skills CLI (Vercel)
npx skills add steipete/agent-scripts --skill github-deep-review -a gemini-cli2Platform CLI
gemini skills install https://github.com/steipete/agent-scripts --path skills/github-deep-reviewManually: put the files in place
.devin/skills/github-deep-review/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add steipete/agent-scripts --skill github-deep-review -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about github-deep-review
How do I install github-deep-review in Claude Code?
Run npx skills add steipete/agent-scripts --skill github-deep-review -a claude-code. After installation, open ~/.claude/skills/github-deep-review/SKILL.md for full documentation.
What does github-deep-review do?
The skill trains an agent to review GitHub issues and PRs like a senior developer: follow the call chain through code, find the real bug source in commit history, evaluate fix quality, and list remaining risks with concrete evidence.
Which platforms support this skill?
github-deep-review works on Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. It requires local gh CLI access for GitHub queries and repository access for history analysis.
Source text
SKILL.md · MIT
--- name: github-deep-review description: "GitHub deep review: bugs, PRs, best fix, stale-or-real, read code first." --- # GitHub Deep Review Review like Peter: high-confidence, evidence-first, code-aware, and willing to say "not proven" when the trail is weak. The goal is not a generic summary. The goal is to understand the bug class, find the real cause if possible, decide the best fix after reading enough code, and call out whether a larger refactor would improve the design. ## Start Use `gh`, not web browsing, for GitHub refs: ```bash gh issue view <n> --json number,title,state,author,body,comments,labels,updatedAt,url gh pr view <n> --json number,title,state,author,body,comments,reviews,files,commits,statusCheckRollup,mergeStateStatus,headRefName,headRepositoryOwner,url gh pr diff <n> --patch ``` For PRs, collect author context by default unless the author is Peter (`steipete` or an obvious Peter-owned account). Use the local workflow in `~/Projects/agent-scripts/skills/github-author-context/SKILL.md` and include a short `Author context:` block near the top of the review when the author is not Peter. After merge/rejection/close/review, use that same author-context workflow to append a contributor note only when the interaction creates durable future-review signal. For repo-local review, also inspect: ```bash git status --short --branch git fetch origin git log --oneline --decorate -20 rg "<key symbol/error/config/endpoint>" ``` If the repo has local instructions, issue/PR skills, docs lists, test guidance, or maintainer runbooks, read those before deciding. ## Review Contract Always answer these, explicitly: - URL/ref: issue or PR number and affected surface. - What is the bug or behavior being fixed? - Can we identify the root cause? If yes, where in code and why. If no, what evidence is missing. - For regressions, who/what introduced it and when? Include commit/PR provenance when traceable by bounded history; say unknown instead of guessing. - Is the current/proposed fix the best possible fix after reading adjacent code? - Would a bigger refactor improve correctness, clarity, or future maintainability? - What proof exists: tests, live repro, CI checks, docs, dependency docs/source, shipped/current behavior. - What remains risky or unverified. ## Code Reading Depth Read past the first touched file. Follow the real call path: - entrypoint -> validation/parsing -> routing/dispatch -> owner module -> shared helper -> persistence/network/runtime boundary - config/schema/docs -> runtime usage -> doctor/migration/fix path - provider/channel/plugin owner code -> generic core seam, only if multiple owners need it - tests around the touched surface plus adjacent regression tests When behavior depends on a dependency, read the upstream docs/source/types or current package contract before assuming. Prefer current source and executable proof over issue comments. Treat stale comments, old CI, and old release behavior as hints until rechecked. ## Provenance For bug/regression reviews, include a compact `Provenance:` answer when feasible: - Use `git log -S/-G`, `git blame`, and linked PRs/issues to locate candidates, not prove introduction. Before saying `introduced by`, inspect raw parents with `git --no-replace-objects cat-file -p <sha>` and verify that `git --no-replace-objects diff --no-ext-diff --no-textconv <raw-parent> <sha> -- <path>` changed the implicated behavior, using tests/repro when feasible. A genuine root needs raw-header proof that it has no parents. - Blame `^sha`, porcelain `boundary`, and shallow/grafted history alone are not introduction proof. `--root` can hide boundary markers; `git show` and `rev-list --parents` can disguise a shallow boundary as a root. An available raw parent permits explicit comparison even at a shallow boundary; missing parents or an unverifiable patch require `unknown` with the gap, not inference from a subject, date, or author. - Separate code author, introducing PR author, merger, committer, automation trigger, and current PR author. Verify identities and triggers from explicit metadata/events; a role is not proof of causation, and an unverified identity stays unknown. - Use `made visible by` only for a verified trigger and `carried forward by` only for verified preexisting behavior. Apply the same evidence bar to summaries and owner hints, not just a `Provenance:` field. Include confidence: `clear`, `likely`, or `unknown`. - For features, docs, and refactors, write `N/A`; for untraceable bugs, report `unknown` with the missing evidence. Missing provenance does not invalidate an independently proven bug. ## Fix Quality Bar Good fixes usually: - live at the ownership boundary where the bug belongs - preserve public/backward-compatible behavior unless the issue is about retiring it - add a regression test at the smallest meaningful seam - avoid broad special cases, hidden migrations, semantic sentinels, and provider/channel IDs in generic core - update docs/changelog when user-visible behavior changes - fail clearly in runtime paths and repair through doctor/migration paths when that is the established contract Call out when a fix is only symptom-level. If a slightly larger refactor makes the invariant obvious and reduces future bugs, recommend it. If the refactor widens risk without improving the bug class, say so. ## PR Review Shape Lead with findings when reviewing a PR. Findings need file/line/symbol references and a concrete failure mode. Avoid vague "consider" comments. If no blocking issues: - say no blocking correctness issues found - list the strongest proof checked - name residual risk/test gaps - answer whether the design is the best available shape Do not approve, comment, close, merge, push, or land unless the user asked for that action. ## Issue Review Shape For bugs/issues: 1. Reconstruct the reporter's scenario and affected version/surface. 2. Check whether current `main` already fixes it. 3. Reproduce or create a minimal local/live proof when feasible. 4. If clear, identify root cause and proposed fix. 5. If solved on `main`, only comment/close when the user asks; include proof and the canonical commit/PR if known. If reproduction is not feasible, say exactly what blocks it and what evidence would make the decision reliable. ## Output Template Use this shape when the user asks "what is this about", "is this the best fix", or "what did we fix": ```text Ref: #123 / PR #456 Surface: <runtime/CLI/provider/channel/docs> Bug: <one or two sentences> Cause: <code path + confidence> Provenance: <introduced/made visible/carried forward by commit/PR/date, or N/A/unknown> Best fix: <what should change and why> Refactor: <yes/no, specific shape> Proof: <tests/live/CI/source/dependency docs> Risk: <remaining uncertainty> ``` Keep it concise, but do not skip the cause/fix/refactor/proof decision.
© steipete · MIT · steipete/agent-scripts