review-cycle

Unified multi-dimensional code review with automated fix orchestration. Routes to session-based (git changes), module-based (path patterns), or fix mode. Triggers on "workflow:review-cycle", "workflow:review-session-cycle", "workflow:review-module-cycle", "workflow:review-cycle-fix".

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/review-cycle/SKILL.md

Quality

Content

85%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured orchestrator skill that clearly defines mode detection, routing logic, and delegation to phase documents. Its strengths are strong actionability with executable code examples, clear workflow sequencing, and good progressive disclosure. Minor weakness is some redundancy in explaining mode detection across multiple formats (code, table, prose), which slightly impacts conciseness.

Dimension	Reasoning	Score
Conciseness	The architecture diagram and mode detection logic are useful, but there's some redundancy—the mode detection is explained three times (code, table, and execution flow). The ASCII diagram, while helpful, adds tokens for something that could be conveyed more concisely. Overall mostly efficient but could be tightened.	2 / 3
Actionability	Provides concrete mode detection logic in executable JavaScript, a clear input-to-mode mapping table, specific usage examples with exact invocation syntax, and explicit flag documentation. Claude can directly follow these instructions to route and execute.	3 / 3
Workflow Clarity	The execution flow is clearly sequenced (parse → detect → read phase doc → execute), with explicit error handling for each failure mode. The delegation model is unambiguous: mode detection first, then full delegation to phase docs. The core rules reinforce the workflow with clear constraints like 'DO NOT STOP' and 'Progressive Loading'.	3 / 3
Progressive Disclosure	Excellent progressive disclosure structure: SKILL.md serves as a concise orchestrator overview that delegates to three clearly-referenced phase documents (review-session.md, review-module.md, review-fix.md) with one-level-deep references. The 'read on-demand based on detected mode' instruction is well-signaled. However, no bundle files were provided to verify the referenced paths exist.	3 / 3
	Total	11 / 12 Passed

Description

42%Scale 1-3

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 identifies a clear niche in code review orchestration with distinct routing modes, making it unlikely to conflict with other skills. However, it relies entirely on internal workflow command triggers rather than natural language terms users would actually say, and the capabilities described are somewhat abstract rather than listing concrete review actions.

Suggestions

Replace or supplement the 'workflow:' trigger identifiers with natural language trigger terms like 'code review', 'review my changes', 'review git diff', 'fix code issues', 'review module'.

Add a 'Use when...' clause describing user-facing scenarios, e.g., 'Use when the user wants to review code changes, scan modules for issues, or automatically fix identified problems.'

List more specific concrete actions such as 'analyzes git diffs for issues, scans code modules by path pattern, applies automated fixes for detected problems' instead of abstract phrases like 'multi-dimensional code review'.

Dimension	Reasoning	Score
Specificity	It names the domain (code review) and mentions some modes (session-based, module-based, fix mode), but the actual concrete actions are vague—'multi-dimensional code review' and 'automated fix orchestration' are somewhat abstract and don't list specific actions like 'lint checking, security scanning, style enforcement'.	2 / 3
Completeness	It partially answers 'what' (code review with routing to different modes) and provides trigger information, but the triggers are machine-readable workflow commands rather than natural 'Use when...' guidance. The 'when' is technically present but not in a useful human-readable form.	2 / 3
Trigger Term Quality	The trigger terms are all internal workflow identifiers ('workflow:review-cycle', 'workflow:review-session-cycle', etc.) rather than natural language terms a user would say. No user would naturally say 'workflow:review-cycle'; terms like 'code review', 'review my changes', 'fix lint errors', or 'review PR' are absent.	1 / 3
Distinctiveness Conflict Risk	The highly specific workflow trigger identifiers and the distinct routing modes (session-based, module-based, fix mode) make this skill clearly distinguishable from other skills and unlikely to conflict, even if the triggers are not user-friendly.	3 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	10 / 11 Passed

Repository: catlog22/Claude-Code-Workflow
Path: .claude/skills/review-cycle/SKILL.md
Commit: 07491b0

Reviewed: 5 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.