review-cycle
Unified multi-dimensional code review with automated fix orchestration. Supports session-based (git changes) and module-based (path patterns) review modes with 7-dimension parallel analysis, iterative deep-dive, and automated fix pipeline. Triggers on "workflow:review-cycle", "workflow:review-session-cycle", "workflow:review-module-cycle", "workflow:review-cycle-fix".
73
66%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.codex/skills/review-cycle/SKILL.mdQuality
Discovery
85%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 in specificity and completeness, clearly articulating what the skill does and when it should be triggered. Its main weakness is that the trigger terms are structured workflow commands rather than natural language terms users would actually say, which could make it harder for Claude to match against natural user requests. The description is well-structured and distinctive but optimized for programmatic invocation rather than conversational discovery.
Suggestions
Add natural language trigger terms alongside the workflow commands, e.g., 'Use when the user asks for code review, wants to review git changes, needs code quality analysis, or asks to fix code issues'
Include common user phrasings like 'review my code', 'check for bugs', 'analyze code quality', 'fix issues in my changes' to improve discoverability from natural language requests
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: session-based and module-based review modes, 7-dimension parallel analysis, iterative deep-dive, automated fix pipeline, and fix orchestration. These are concrete, specific capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (multi-dimensional code review with automated fix orchestration, session-based and module-based modes, 7-dimension analysis) and 'when' (explicit triggers listed with 'Triggers on' clause specifying the exact workflow commands). | 3 / 3 |
Trigger Term Quality | The trigger terms are explicit workflow commands ('workflow:review-cycle', etc.) rather than natural language a user would say. A user would more likely say 'review my code', 'check git changes', or 'fix code issues' rather than these structured workflow identifiers. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with very specific workflow trigger commands and a unique combination of features (7-dimension parallel analysis, session vs module modes, fix orchestration). Unlikely to conflict with other skills due to the precise trigger terms. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill demonstrates excellent workflow design with clear phase sequencing, conditional logic, and error handling, but suffers significantly from verbosity. The main SKILL.md tries to be both an orchestration overview and a comprehensive reference document, resulting in a massive file that contradicts its own 'progressive phase loading' principle. The architecture diagrams, data flow sections, and execution flow sections contain substantial redundancy.
Suggestions
Move the Subagent API Reference, Error Handling tables, and Output File Structure sections to separate reference files (e.g., api-reference.md, error-handling.md) and link to them from the main SKILL.md, reducing the main file by ~40%.
Consolidate the Architecture Overview diagram, Execution Flow section, and Data Flow section into a single concise flow description—currently these three sections describe the same pipeline three different ways.
Remove the mode detection JavaScript function and replace with just the detection table, since Claude can implement the logic from the table alone.
Move the Phase 7.5 inline implementation code to its own phase document (phases/07.5-export-task-json.md) consistent with how all other phases are handled.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines. It includes extensive ASCII architecture diagrams, redundant data flow descriptions (the execution flow and data flow sections largely duplicate each other), detailed error handling tables, and a full subagent API reference that could be in a separate file. Much of this is reference material that doesn't need to be in the main SKILL.md. | 1 / 3 |
Actionability | The skill provides concrete usage examples, mode detection logic in JavaScript, and specific CLI commands. However, the actual phase execution details are deferred to external phase documents, and the inline code (like mode detection, Phase 7.5 export) is illustrative rather than truly executable—it's embedded in explanation rather than being copy-paste ready operational code. | 2 / 3 |
Workflow Clarity | The multi-step workflow is exceptionally well-sequenced with clear phase progression, explicit conditional branching (Phase 4 criteria, fix pipeline trigger), validation checkpoints (test pass rate requirements, severity thresholds for deep-dive), error handling with blocking/non-blocking classification, and feedback loops (Phase 3↔4 iteration loop with exit criteria). | 3 / 3 |
Progressive Disclosure | The skill correctly references external phase documents via a clear table with one-level-deep links, which is good. However, the main SKILL.md itself is a monolithic wall of text containing extensive inline content (full API reference, detailed error tables, complete output file structure, Phase 7.5 implementation) that should be split into separate reference files, undermining the progressive disclosure principle it claims to follow. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- catlog22/Claude-Code-Workflow
- Commit
0f8e801
- 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.