Use when reviewing an incoming GitHub pull request — runs the multi-level (L1-L5) audit against the PR's real diff range, posts findings as one batched review (inline, summary, or local-only), offers the standard fix chain on NEEDS_FIX, and optionally merges. The maintainer-side counterpart to /hyperflow:issue. Trigger with /hyperflow:pr, "review PR #N", "review this pull request <url>", "audit the PR", "check this contribution".
76
98%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
GitHub-native inbound review: point it at a pull request and the existing L1-L5 audit machinery runs over the
PR's real code — then the verdict flows back to GitHub as one batched review, behind a gate. This skill owns
ingestion, the untrusted-code boundary, posting, and the merge exit; the review itself is
/hyperflow:audit unchanged. The outbound counterpart is
/hyperflow:issue.
#N, or number against origin). gh auth status once; unauthenticated →
local-only mode (review runs, nothing posts, wrap-up prints the manual gh pr review command).gh pr view <n> --json title,body,author,state,baseRefName,headRefName,isCrossRepository,maintainerCanModify,files,commits,url.
Closed/merged PR → confirm intent (Review anyway / Stop — binary, no marker).git fetch origin pull/<n>/head:pr-<n>. The review range is <baseRefName>..pr-<n> —
audit reads actual files with full context, never just the diff text.A PR branch is untrusted input:
Run the PR's tests? This executes contributor code. Yes / No — binary, no marker). Headless mode never runs contributor code.pr-<n> ref — the working branch is never mutated by review.Pick the level, then invoke Skill with skill: audit and args: "<baseRefName>..pr-<n> level=<L>":
| Signal | Level |
|---|---|
| Docs/comments-only diff | L1 |
| Internal contributor, small surface | L2-L3 (default L3) |
External contributor (isCrossRepository), or touches auth/secrets/CI/dependency manifests | L4 |
Security-sensitive path + external author, or level=5 requested | L5 |
Audit dispatches the matching domain specialists (Brain-decided roster), writes
.hyperflow/audits/<timestamp>-pr-<n>.md, and returns PASS / NEEDS_FIX plus graded findings. A
SECURITY_VIOLATION halts everything — nothing posts, the halt surfaces locally per
../audit/references/security.md.
One AskUserQuestion, four options (comment=never skips straight to local-only). Multi-option gate →
mark a recommended choice (DOCTRINE): Inline review (Recommended) on NEEDS_FIX with line-anchored findings,
Summary only (Recommended) on PASS or when findings have no stable anchors.
gh api repos/{owner}/{repo}/pulls/<n>/reviews call: every finding as a
file/line-anchored comment plus a short summary body. Verdict maps PASS → APPROVE,
NEEDS_FIX → REQUEST_CHANGES..hyperflow/audits/; print the path.Comment etiquette: constructive, specific, file:line citations, no AI attribution, and one review round = one
batched call — never a stream of separate comments.
The standard audit fix-gate applies (fix all / criticals / no). When fixes are approved, delivery is auto-detected:
maintainerCanModify: true → chain fixes via /hyperflow:plan →
/hyperflow:dispatch on the pr-<n> ref and push to the contributor's branch
(git push origin pr-<n>:<headRefName>). Never force-push a contributor's branch.After PASS (or fixes verified green): if merge=never, stop. Otherwise gate:
Merge PR #<n>? (<method>) Yes / No — binary, no marker. Method inferred from repo history — linear history →
--rebase, merge commits present → --merge, squash-dominant → --squash; say which and why in the gate's
status line. There is deliberately no merge=auto. On merge: honor Closes # links, offer branch cleanup
(--delete-branch).
| Failure | Behavior |
|---|---|
gh missing / unauthenticated | Local-only mode — full review, manual posting commands printed |
| PR not found / no access | Stop: PR #<n> not found in <repo> — check the number and gh auth scope. |
Fetch of pull/<n>/head fails | Fall back to gh pr diff <n> text review at ≤L2 with an explicit "context-limited review" caveat in any posted summary |
SECURITY_VIOLATION from audit | Halt. Nothing posts. Surface locally only |
| Headless | Requires comment= and merge= pre-elected; contributor code never runs |
Hyperflow Question chat blocks per the
dispatch fallback pattern.Shared rules in ../hyperflow/DOCTRINE.md. Review levels in
../audit/references/review-levels.md. Git rules in
../hyperflow/git-workflow.md.
88dcf65
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.