recipe-review

Design Doc compliance and security validation with optional auto-fixes

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/recipe-review/SKILL.md

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.

The content is a highly executable, well-sequenced orchestration workflow with strong validation and feedback loops. Its main weakness is monolithic structure with no progressive disclosure into bundle files.

Suggestions

Move the report-format templates and the Auto-fixable/Non-fixable/Design-Side-Update-Triggers tables into references/ files, keeping SKILL.md as an overview with one-level-deep pointers.

Create a references/review-resolution-gate.md within this skill's own bundle rather than relying solely on the external subagents-orchestration-guide skill's file.

Tighten repeated 'Apply the Review Resolution Gate ...' phrasing into a single defined shorthand used across steps.

Dimension	Reasoning	Score
Conciseness	The body is dense and directive with no concept padding Claude would already know, though some compound sentences and repeated 'Apply the Review Resolution Gate' phrasing could be trimmed.	4 / 5
Actionability	Every step supplies concrete subagent_type values, exact structured-JSON prompt templates, and explicit field mappings, giving copy-paste-ready executable guidance for an instruction-only skill.	5 / 5
Workflow Clarity	Steps 1-10 are strictly ordered with explicit validation gates, convergence conditions, and feedback loops (Steps 6-7 retry, Steps 8-9 re-validation, one retry of retained limitations).	5 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets are absent) and all content is inlined in one ~200-line SKILL.md; the report templates, auto-fixable/non-fixable lists, and trigger tables could be split into referenced files.	3 / 5
	Total	17 / 20 Passed

Description

53%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 and distinct but terse, stating the what without any explicit when/trigger guidance. Adding a 'Use when...' clause with natural trigger phrases would lift the completeness and trigger dimensions.

Suggestions

Append a 'Use when...' clause with natural triggers, e.g. 'Use when validating a Design Doc against its implementation, running a security review, or fixing compliance findings.'

Add common user-facing synonyms like 'review', 'QA', and 'compliance check' to improve trigger term quality.

Expand the action list slightly (e.g. 'route design-side updates, re-validate after fixes') to move specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Design Doc compliance', 'security validation') and two concrete actions ('validation', 'optional auto-fixes'), but coverage is terse and not comprehensive.	3 / 5
Completeness	It clearly states what the skill does but provides no 'Use when...' trigger clause, so per the guideline a missing explicit 'when' caps completeness at 3.	3 / 5
Trigger Term Quality	Terms like 'Design Doc compliance', 'security validation', and 'auto-fixes' are relevant but jargony, missing common natural variations users would say such as 'review' or 'QA'.	3 / 5
Distinctiveness Conflict Risk	'Design Doc compliance and security validation with optional auto-fixes' carves a fairly specific QA niche with only minor overlap risk against related review skills.	4 / 5
	Total	13 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: shinpr/claude-code-workflows
Path: skills/recipe-review/SKILL.md
Commit: 83cf695

Reviewed: about 22 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.