pr

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".

Quality

98%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

96%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tightly written, highly actionable workflow skill with excellent command-level guidance, explicit gates, and thorough error/fallback handling. The only weakness is that its progressive-disclosure references point to sibling skills/files that are not present in this skill's own bundle.

Suggestions

Co-locate or vendor the critical sibling references this skill depends on at runtime (../audit/references/security.md, ../audit/references/review-levels.md, ../hyperflow/DOCTRINE.md, ../hyperflow/git-workflow.md) so the skill is navigable as a standalone unit, or add a one-line 'Requirements' note stating these must be present in the plugin tree.

For the merge-method inference rule, inline the brief decision logic (linear history → --rebase, merge commits present → --merge, squash-dominant → --squash) as a tiny checklist rather than only prose, so the gate's status line can be generated deterministically.

Dimension	Reasoning	Score
Conciseness	Lean and command-dense throughout — it assumes Claude knows what a PR, gh, and git are, and devotes prose only to substantive rules (the untrusted-code boundary, gate etiquette) rather than concept explanations.	5 / 5
Actionability	Fully executable guidance with real commands and exact argument shapes — 'gh pr view <n> --json title,body,…', 'git fetch origin pull/<n>/head:pr-<n>', 'gh api repos/{owner}/{repo}/pulls/<n>/reviews', 'git push origin pr-<n>:<headRefName>' — covering the common cases copy-paste ready modulo parameter substitution.	5 / 5
Workflow Clarity	Steps 0–5 are explicitly sequenced with validation checkpoints (preflight auth check, SECURITY_VIOLATION halt, posting gate, fix gate, merge gate) and a feedback table covering fetch-failure fallback, unauthenticated mode, and headless behavior — exactly the validate→fix→retry structure the rubric rewards for destructive/batched operations.	5 / 5
Progressive Disclosure	The body is a clear overview with well-signaled, one-level-deep references to sibling materials, but every cross-skill link (../audit/SKILL.md, ../audit/references/security.md, ../audit/references/review-levels.md, ../dispatch/SKILL.md, ../hyperflow/DOCTRINE.md, ../hyperflow/git-workflow.md, ../issue/SKILL.md) was verified missing from the skill's bundle, leaving minor navigation gaps.	4 / 5
	Total	19 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exemplary description: concrete actions, explicit 'Use when' trigger guidance with natural phrasing, third-person/infinitive voice, and a clear niche that distinguishes it from sibling skills. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'runs the multi-level (L1-L5) audit', 'posts findings as one batched review (inline, summary, or local-only)', 'offers the standard fix chain on NEEDS_FIX', 'optionally merges' — giving comprehensive coverage rather than a single generic verb.	5 / 5
Completeness	Explicitly answers both: what ('runs the multi-level audit… posts findings… offers the fix chain… optionally merges') and when ('Use when reviewing an incoming GitHub pull request' plus a dedicated 'Trigger with…' line of concrete trigger phrases).	5 / 5
Trigger Term Quality	Supplies natural phrases a user would actually say — 'review PR #N', 'review this pull request <url>', 'audit the PR', 'check this contribution' — with strong synonym coverage (PR/pull request, review/audit/check/contribution).	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — 'inbound' GitHub PR review framed as 'The maintainer-side counterpart to /hyperflow:issue' and distinct from the outbound audit — minimizing overlap with sibling skills.	5 / 5
	Total	20 / 20 Passed

Validation

81%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 7 suspicious	Warning

	Total	13 / 16 Passed

Repository: jeremylongshore/tons-of-skills-marketplace
Path: plugins/ai-agency/hyperflow/skills/pr/SKILL.md
Commit: 88dcf65

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

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.