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

88%

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.

The body is a well-sequenced, highly actionable triage workflow with strong validation and error-recovery guidance. It stays domain-specific without generic padding. The main gap is that substantial inline detail could be moved to reference files for cleaner progressive disclosure.

Suggestions

Consider moving the detailed gate mechanics (the 'How the gate works' section) and the MRE-vs-contract philosophy into a reference file, keeping SKILL.md as a lean overview that links one level deep.

Tighten a few prose passages in Step 2 and Step 3 (e.g. the contract discussion) to trim tokens without losing the non-obvious domain insight.

Add a brief explicit checklist at the end of Step 3 summarizing the severity-separation rule, so the review verdict logic is scannable rather than narrative.

Dimension	Reasoning	Score
Conciseness	Dense and domain-specific throughout (gate mechanics, CONTRIBUTING categories, the MRE-vs-bug trap) with no generic concept padding, but a few prose passages could be tightened, keeping it below the lean anchor 5.	4 / 5
Actionability	Provides copy-paste-ready gh commands for every key action (gh issue view, gh pr list --search, gh issue edit --add-assignee, gh issue comment --body-file) covering the common cases, matching the anchor 5 example.	5 / 5
Workflow Clarity	Sequences a clear Step 1-5 flow with explicit validation checkpoints and error-recovery feedback loops ('Verify that the assignment workflow clears the check', 'If it does not, inspect the run', deleted-branch handling); destructive ops carry validation, so no cap applies.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and a coherent single workflow, but it is over 50 lines with inline detail (gate mechanics, contract philosophy) that could be offloaded to reference files, leaving it just below the clean anchor 5 split.	4 / 5
	Total	18 / 20 Passed

Description

87%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.

The description is specific, well-triggered, complete, and clearly disambiguated from the related review-pr skill. It reads naturally and tells Claude exactly when to engage. Minor room for slightly broader trigger synonym coverage.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('Review an incoming external issue', 'decide whether to assign the contributor or decline', 'Assigning the author auto-reopens their PR'), but the action set is narrower than a fully comprehensive multi-feature skill, so it sits below the anchor 5 example.	4 / 5
Completeness	Explicitly answers both what (review issue, decide assign/decline, reopen PR) and when (concrete 'Use when...' trigger phrases), matching the anchor 5 example.	5 / 5
Trigger Term Quality	Quotes natural maintainer phrasings ('look at this issue', 'review issue #N', 'should we take this', 'asks whether to assign someone') that a user would genuinely say, but coverage of synonyms and variations is good rather than exhaustive.	4 / 5
Distinctiveness Conflict Risk	Explicitly disambiguates from a sibling skill ('distinct from review-pr, which responds to bot reviews on your own open PR'), carving a clear niche with minimal conflict risk.	5 / 5
	Total	18 / 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: 0796584

Reviewed: 12 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.