workflow-lite-test-review
Post-execution test review and fix - chain from lite-execute or standalone. Reviews implementation against plan, runs tests, auto-fixes failures.
70
63%
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 ./.claude/skills/workflow-lite-test-review/SKILL.mdQuality
Discovery
50%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 conveys a reasonable sense of what the skill does—reviewing implementations, running tests, and fixing failures—but lacks explicit trigger guidance ('Use when...') and natural user-facing keywords. The internal jargon ('lite-execute', 'chain from') reduces accessibility, and the actions described could overlap with other coding/testing skills.
Suggestions
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to run tests after implementation, debug failing tests, or verify code against a plan.'
Replace or supplement internal jargon like 'lite-execute' and 'chain from' with user-facing language such as 'after code generation', 'test failures', 'fix broken tests', 'test suite'.
List more specific concrete actions, e.g., 'Runs unit/integration tests, parses error output, identifies root causes, and applies targeted code fixes to pass failing tests.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names some actions ('reviews implementation against plan', 'runs tests', 'auto-fixes failures') but they are somewhat generic and not deeply specific about what kinds of tests, what kinds of fixes, or what 'reviewing against plan' entails concretely. | 2 / 3 |
Completeness | The 'what' is partially addressed (reviews implementation, runs tests, auto-fixes failures), but there is no explicit 'Use when...' clause or clear trigger guidance for when Claude should select this skill. The phrase 'chain from lite-execute or standalone' hints at when but doesn't provide explicit user-facing trigger conditions. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'test', 'fix', 'failures', and 'lite-execute', but misses common natural user phrases like 'run my tests', 'debug test failures', 'failing tests', 'test suite', 'unit tests', or 'CI'. The term 'lite-execute' is internal jargon unlikely to be used by users. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'post-execution test review' and 'chain from lite-execute' provides some distinctiveness, but 'runs tests' and 'auto-fixes failures' could easily overlap with general coding, debugging, or test-running skills. The niche is not sharply defined. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
77%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, highly actionable skill for a complex multi-phase test review workflow. The workflow clarity is excellent with explicit phase transitions, skip conditions, validation loops, and error handling. The main weakness is that the document is quite long and could benefit from splitting detailed data structures and CLI invocation patterns into separate reference files to improve progressive disclosure and reduce token cost.
Suggestions
Move the Data Structures section (testReviewContext, testChecklist schemas) to a separate REFERENCE.md file and link to it, reducing the main skill's token footprint.
Consider extracting the CLI convergence review code block into a separate file since it's a conditional path that doesn't always execute.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long and detailed but most content is necessary for the complex multi-phase workflow. Some sections like the data structures and mode explanations could be tightened, and there's mild redundancy in explaining the convergence review tool options. However, it doesn't over-explain basic concepts. | 2 / 3 |
Actionability | The skill provides executable JavaScript code for initialization, agent delegation, CLI invocation, and session sync chaining. Test framework detection has concrete file-to-command mappings. The auto-fix loop includes specific agent prompts and iteration logic. Nearly everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | The 5-phase workflow is clearly sequenced with explicit TodoWrite checkpoints between phases, skip conditions clearly stated, and validation built into the iterative fix loop (max 3 rounds with break-on-pass). Phase 5 is marked as MANDATORY checkpoint. Error handling table covers failure modes with resolutions. | 3 / 3 |
Progressive Disclosure | The skill is a monolithic document with all phases, data structures, and error handling inline. While the phase summary table provides a good overview, the data structures section and detailed CLI convergence review code could be split into referenced files. The reference to `ccw spec load --category test` is a good external reference, but the document itself is quite long. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%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
- 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.