CtrlK
BlogDocsLog inGet started
Tessl Logo

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

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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 triage workflow with executable commands, explicit validation checkpoints, and non-obvious domain judgment. It is slightly long for a single self-contained file, which is the main improvement lever.

Suggestions

Move the detailed gate mechanics ('How the gate works' section) into a references/ file, leaving SKILL.md as an overview that points to it — this would tighten conciseness and lift progressive_disclosure.

Trim the emphatic restatements in Step 3 ('That is a cursory review and it produces wrong verdicts... You cannot assess a PR without reading the code it changes in context') to a single crisp statement of the anti-pattern.

DimensionReasoningScore

Conciseness

Largely efficient and assumes GitHub/git competence, focusing on non-obvious domain judgment (the MRE-vs-contract distinction, gate mechanics) rather than concepts Claude already knows; minor emphatic repetition ('a cursory review... it produces wrong verdicts') could be trimmed.

4 / 5

Actionability

Copy-paste-ready gh commands with placeholders throughout — gh issue view/list, gh pr view/comments, gh api users, gh search prs, gh issue edit --add-assignee, gh issue comment --body-file — covering the common triage cases.

5 / 5

Workflow Clarity

Steps 1–5 are clearly sequenced with explicit validation and feedback loops: verify the assignment check clears and reopens the PR (inspect the run if not), a stop-and-decline checkpoint at Step 2, and authorization gating before destructive public actions.

5 / 5

Progressive Disclosure

Well-organized with clear section headers and a one-level reference to require-issue-link.yml, but the ~195-line single-file body has no bundle files to offload detail into, and some gate mechanics could be split into a reference file.

4 / 5

Total

18

/

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.

A strong description: concrete actions, natural trigger phrases, explicit what-and-when, and an explicit disambiguation from the related review-pr skill. No vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — review an incoming issue and any gated-closed PR, decide assign-or-decline, and (assigning the author) auto-reopen their PR — which is comprehensive coverage for the triage niche.

5 / 5

Completeness

Explicitly answers both what (review issue + PR, assign or decline) and when (concrete maintainer trigger phrases), satisfying the top anchor.

5 / 5

Trigger Term Quality

The 'Use when' clause surfaces natural maintainer phrases with synonyms — 'look at this issue', 'review issue #N', 'should we take this', 'asks whether to assign someone' — exactly what a user would say.

5 / 5

Distinctiveness Conflict Risk

Explicitly carves out a clear niche — 'distinct from review-pr, which responds to bot reviews on your own open PR' — minimizing overlap with the sibling skill.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
PrefectHQ/fastmcp
Reviewed

Table of Contents

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.