factory-review

Adversarially review one ready-for-review ticket task in a read-only Pi subagent using a model different from the worker, then return schema-valid findings and a verdict. Use only for the review stage; it never edits code or applies its own findings.

Quality

86%

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

85%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, instruction-only review skill with a clear sequenced workflow, explicit validation checkpoints, and clean progressive disclosure into real reference files. It assumes Claude's competence and stays lean.

Dimension	Reasoning	Score
Conciseness	Lean and directive, assuming Claude's competence without explaining basic review concepts; minor padding in the stacked 'Do not…' boundary list could be tightened.	4 / 5
Actionability	Provides a concrete ordered checklist (1–6), an explicit required-packet specification, and a named output schema 'factory.review.v3'; the detailed finding/verdict rules are delegated to references rather than inlined, leaving a small gap.	4 / 5
Workflow Clarity	Clear sequence from boundaries to required packet to ordered review checks to output, with explicit validation checkpoints (blocked verdict conditions) and feedback loops for later rounds (verify claimed fixes and regressions first).	5 / 5
Progressive Disclosure	Body is an overview that points to well-signaled, one-level-deep references — review-contract.md for findings/verdict rules and code-quality.md for the structural lens — both real bundle files, enabling easy navigation.	5 / 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.

A specific, well-scoped description that conveys both capability and trigger conditions in third-person imperative voice. It is concise, distinct, and explicitly answers what and when.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'adversarially review one ready-for-review ticket task', 'return schema-valid findings and a verdict', 'never edits code or applies its own findings' — but does not enumerate what the review itself entails, leaving a minor coverage gap.	4 / 5
Completeness	Clearly answers 'what' (review a ticket task and return schema-valid findings and a verdict) and explicitly answers 'when' with the concrete trigger 'Use only for the review stage'.	5 / 5
Trigger Term Quality	Includes natural terms a user would say — 'review', 'ticket task', 'findings', 'verdict', 'review stage' — with good coverage, though a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — read-only, model-independent ticket review — with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	18 / 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: geut/factory-skills
Path: skills/factory-review/SKILL.md
Commit: c0e9a42

Reviewed: 10 hours 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.