workflow-test-fix
Unified test-fix pipeline combining test generation (session, context, analysis, task gen) with iterative test-cycle execution (adaptive strategy, progressive testing, CLI fallback). Triggers on "workflow-test-fix", "test fix workflow".
55
44%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/workflow-test-fix/SKILL.mdQuality
Discovery
35%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 attempts to convey a complex multi-stage testing workflow but relies heavily on internal jargon and parenthetical feature lists that don't clearly communicate concrete actions to either Claude or users. The trigger terms are artificial command strings rather than natural language, and the 'when to use' guidance is essentially just those command strings rather than real usage scenarios.
Suggestions
Replace jargon-heavy parenthetical lists with plain-language concrete actions, e.g., 'Generates test cases, runs them iteratively, identifies failures, and applies fixes automatically.'
Add a 'Use when...' clause with natural trigger scenarios, e.g., 'Use when the user asks to fix failing tests, generate and run tests, debug test suite errors, or iteratively resolve test failures.'
Include natural keywords users would actually say, such as 'failing tests', 'test errors', 'run tests', 'fix broken tests', 'test suite', 'test coverage'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain (test generation and execution) and mentions some actions like 'session, context, analysis, task gen' and 'adaptive strategy, progressive testing, CLI fallback', but these read more like internal jargon/feature labels than concrete user-facing actions. It doesn't clearly list what specific things it does in plain language. | 2 / 3 |
Completeness | It describes what it does (unified test-fix pipeline combining generation and execution) and has explicit trigger terms, but the 'when' guidance is limited to artificial trigger phrases rather than describing real scenarios when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | The trigger terms 'workflow-test-fix' and 'test fix workflow' are artificial command-like phrases, not natural language a user would say. Missing natural terms like 'fix failing tests', 'run tests', 'debug test failures', 'test suite', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The description is somewhat specific to a test-fix pipeline workflow, but the heavy jargon and vague sub-components (e.g., 'adaptive strategy', 'progressive testing') could overlap with other testing-related skills. The artificial trigger terms help reduce conflict but don't clearly carve out a distinct niche. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
54%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at workflow clarity and progressive disclosure, with a well-structured multi-phase pipeline, explicit validation checkpoints, and clean delegation to phase-specific documents. However, it is severely over-engineered in terms of token efficiency — the same pipeline is described in at least 3 different representations (architecture diagram, execution flow, data flow), quality thresholds are repeated, and the TodoWrite pattern examples are excessively detailed. The actionability is moderate since the skill is primarily an orchestration document that delegates real execution to external phase files.
Suggestions
Consolidate the redundant pipeline representations (sections 1, 6, and 9 all describe the same flow) into a single clear representation, removing at least two of the three.
Remove duplicated information like quality thresholds (listed in both sections 10 and 11) and compact rules (sections 5 and 6) — state each fact once.
Trim the TodoWrite pattern section (section 14) significantly — the three full JSON examples could be replaced with one example and a brief note about state transitions.
Remove the ASCII architecture diagram or the textual execution flow — having both is redundant and consumes significant tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines with massive ASCII diagrams, redundant data flow representations (sections 1, 6, 9 all describe the same pipeline), repeated information across sections (quality thresholds listed in sections 10 and 11, compact rules in sections 5 and 6), and extensive JSON examples for TodoWrite patterns. Much of this could be compressed to 1/3 the size without losing information. | 1 / 3 |
Actionability | Provides concrete phase references, file paths, and structured task definitions, but the actual executable guidance is delegated to external phase files. The JavaScript code snippet for preference collection is helpful but the skill itself is more of an architectural document than executable instructions. Key execution details are in the referenced phase files, not here. | 2 / 3 |
Workflow Clarity | The multi-step workflow is exceptionally well-sequenced with clear phase progression (1→2→3→4→Summary→5), explicit validation checkpoints (quality gates at IMPL-001.3, IMPL-001.5, 95% pass rate gate), error handling tables for each phase, regression detection with rollback, and a detailed coordinator checklist. Feedback loops are explicitly defined in the fix cycle. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure pattern with phase documents loaded on-demand via Read() calls to separate files (phases/01-session-start.md through phases/05-test-cycle-execute.md). The main SKILL.md serves as a clear coordinator/overview with well-signaled one-level-deep references to phase documents, and a clear table mapping phases to their documents. | 3 / 3 |
Total | 9 / 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.