review-issue

Review an incoming external issue (and any gated-closed PR behind it) and decide whether to assign the contributor or decline. Use when the maintainer says "look at this issue", "review issue

Quality

91%

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

88%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 well-structured, highly actionable triage workflow with concrete commands, explicit decision checkpoints, and genuinely non-obvious domain guidance on the MRE/contract distinction. The only meaningful weakness is mild verbosity in the philosophical sections and a monolithic structure that doesn't lean on progressive disclosure.

Suggestions

Tighten the 'A reproducible MRE is not the same as a bug' section (lines 67-81) into a sharper rule with one short example — the contract-vs-behavior point is valuable but currently runs long.

Consider extracting the gate-mechanics reference (labels, exemptions, sibling bots) into a references/ file so SKILL.md stays a lean decision overview.

The 'How the gate works' section could be condensed to the single lever (assign → reopen) plus a pointer, since Step 1 onward re-covers the operational details.

Dimension	Reasoning	Score
Conciseness	Mostly dense and earned — repo-specific gate mechanics and concrete commands assume Claude's competence — but the MRE-vs-contract philosophy section (lines 67-81) is somewhat expansive and could be trimmed, fitting the 'efficient with minor over-explanation' anchor.	4 / 5
Actionability	Provides copy-paste-ready gh commands with appropriate placeholders — 'gh issue view N --repo ...', 'gh issue edit N --add-assignee <login>', 'gh issue comment N --body-file ...' — covering the common assign/decline cases.	5 / 5
Workflow Clarity	Clear five-step sequence (Orient → Classify → Investigate → Decide → Act) with explicit validation checkpoints ('stop here and decline', 'Wait for confirmation') and feedback loops ('If it fails... investigate the run, don't re-assign').	5 / 5
Progressive Disclosure	Well-organized into clear sections with a 'What this skill does NOT do' navigation aid and no bundle files needing references, but it is a ~165-line monolithic doc where a subsection (e.g. the contract/MRE reasoning) could plausibly live in a reference.	4 / 5
	Total	18 / 20 Passed

Description

95%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.

A strong, opinionated description that clearly states the skill's action, gives concrete trigger phrases a maintainer would naturally say, and explicitly differentiates it from the sibling review-pr skill. Minor specificity gap only in that the actions sit at a decision level rather than enumerated operations.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'Review an incoming external issue', 'decide whether to assign the contributor or decline', 'auto-reopens their PR' — matching the anchor that lists several specific actions with minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what (review issue and decide assign/decline) and when (concrete 'Use when the maintainer says...' triggers), matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural maintainer phrasing — 'look at this issue', 'review issue #N', 'should we take this', 'whether to assign someone' — comprehensive coverage of terms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Carves a clear niche and explicitly distinguishes it — 'distinct from review-pr, which responds to bot reviews on your own open PR' — minimizing wrong-skill triggering.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: PrefectHQ/fastmcp
Path: .claude/skills/review-issue/SKILL.md
Commit: c9cf237

Reviewed: 2 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.