Name: maintainer-review
Rating: 73.6 (1 reviews)
Author: redis

maintainer-review

Review an ioredis issue or pull request as an ioredis maintainer, with a staged assessment of whether the claim is real, practically important, already solvable with supported functionality, correctly scoped, better served by another ioredis design, and worth maintainer and contributor effort. Use when assessing ioredis issue validity or severity, deciding whether an issue should be prioritized or closed, determining whether a requested feature represents an unmet need rather than a discoverability or usage gap, judging whether a PR is worth bringing to mergeable quality, comparing open PRs or alternative designs, separating code quality from repository readiness, or drafting a concise maintainer assessment. When closure, additional evidence, or code changes should be requested, also produce a polite, concise, complete, copy-paste-ready maintainer comment.

Quality

90%

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 an action-dense, well-sequenced maintainer-review process with strong validation checkpoints and a clearly signaled single reference file. Its main weakness is mild verbosity and some overlap between inline guidance and the bundled evaluation-framework reference, which keeps conciseness and progressive disclosure just short of top marks.

Suggestions

Trim restatements of the need-gate rule across steps 2, 4, and 6; state it once and reference it to reduce length and repetition.

Move the full severity rubric and evidence-order list into references/evaluation-framework.md and keep only a one-line pointer inline, since the reference already covers them.

Consolidate the ownership-area file listing in step 4 into the reference so the inline body stays a focused workflow overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and task-specific throughout with no padding about concepts Claude already knows, but at ~209 lines some repeated emphasis and overlapping guidance (e.g., re-stated need-gate rules across steps 2, 4, and 6) could be tightened.	4 / 5
Actionability	For an instruction-only skill it gives highly concrete, executable guidance: named Need-evidence statuses, an explicit two-stage evidence order, mandatory passes with numbered checkpoints, ownership-area file paths, a fixed report field list, and a defined severity rubric.	5 / 5
Workflow Clarity	A clear seven-step sequence is given with explicit validation gates ('If any answer is missing...do not call the issue actionable', 'Only proceed when validation passes'-style rules, user-approval gates before runtime probes) and feedback loops for error recovery, satisfying the destructive/batch validation bar.	5 / 5
Progressive Disclosure	Content is well sectioned and points to a single real one-level-deep reference (references/evaluation-framework.md) with clear scoping, but material that the reference already holds (severity rubric, evidence checks, competing-PR guidance) is partly duplicated inline rather than fully deferred.	4 / 5
	Total	18 / 20 Passed

Description

92%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 strong: it is third-person, concrete, and explicitly pairs a 'what' with a rich 'Use when' trigger clause covering the main maintainer-review scenarios. Trigger-term coverage is good but could add a few everyday synonyms. It clearly distinguishes itself from generic review skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete review actions such as 'assessing ioredis issue validity or severity', 'judging whether a PR is worth bringing to mergeable quality', 'comparing open PRs or alternative designs', and 'drafting a concise maintainer assessment', giving comprehensive coverage of what the skill does.	5 / 5
Completeness	It explicitly answers 'what' ('Review an ioredis issue or pull request as an ioredis maintainer, with a staged assessment...') and 'when' ('Use when assessing ioredis issue validity or severity...') with concrete trigger phrases, plus a conditional output ('also produce a polite, concise...maintainer comment').	5 / 5
Trigger Term Quality	Natural user-facing phrases like 'issue validity or severity', 'whether an issue should be prioritized or closed', 'whether a PR is worth bringing to mergeable quality', and 'comparing open PRs' are present, though a few common variations (e.g., 'triage', 'review a PR', 'close an issue') could be added.	4 / 5
Distinctiveness Conflict Risk	The ioredis maintainer-review niche is specific and the triggers are tied to maintainer judgments (issue validity/severity, PR merge-worthiness, competing PRs), leaving minimal overlap risk with generic code-review or doc skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: redis/ioredis
Path: .agents/skills/maintainer-review/SKILL.md
Commit: c0cd66c

Reviewed: 10 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.