End-to-end test-fix workflow generate test sessions with progressive layers (L0-L3), then execute iterative fix cycles until pass rate >= 95%. Combines test-fix-gen and test-cycle-execute into a unified pipeline. Triggers on "workflow:test-fix-cycle".
62
73%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.codex/skills/workflow-test-fix-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.
This 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 internal/technical identifiers ('workflow:test-fix-cycle') rather than natural language phrases a user would typically use, which could limit discoverability in natural conversation. The description is concise and well-structured without unnecessary fluff.
Suggestions
Add natural language trigger terms alongside the command trigger, e.g., 'Use when the user asks to run a full test-fix cycle, fix failing tests automatically, or wants end-to-end test generation and repair.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generate test sessions with progressive layers (L0-L3), execute iterative fix cycles, specifies a pass rate threshold (>= 95%), and names the sub-skills it combines (test-fix-gen and test-cycle-execute). | 3 / 3 |
Completeness | Clearly answers both 'what' (generate test sessions with progressive layers, execute iterative fix cycles until 95% pass rate, combines two sub-skills) and 'when' (explicitly states 'Triggers on workflow:test-fix-cycle'). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'test-fix workflow', 'test sessions', 'fix cycles', and the explicit trigger 'workflow:test-fix-cycle', but these are mostly technical/internal identifiers rather than natural language terms a user would say. Missing common variations like 'run tests', 'fix failing tests', 'test pipeline', etc. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: it's a unified pipeline combining specific sub-skills (test-fix-gen and test-cycle-execute) with a specific trigger command. The L0-L3 layer system and 95% pass rate threshold further distinguish it from generic testing skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has excellent workflow clarity with well-defined phases, validation gates, error recovery, and a clear coordinator checklist. Actionability is strong with concrete code examples and specific parameters. However, the content is severely bloated — information is repeated across multiple sections (agents listed 3-4 times, execution flow described twice), and substantial content that belongs in the referenced phase docs is inlined, undermining the progressive disclosure structure.
Suggestions
Move the Subagent API Reference section to a separate reference file (e.g., SUBAGENT_API.md) and link to it — Claude doesn't need the full spawn/wait/close API inline when phase docs already guide usage.
Consolidate agent listings to a single location; currently agents are enumerated in Architecture Overview, Phase Execution, and Related Skills sections redundantly.
Move the detailed Output Artifacts directory structure and Error Handling table to the respective phase docs (phases/01-*.md and phases/02-*.md) since they are phase-specific details.
Remove the ASCII architecture diagram or significantly simplify it — the Execution Flow section already conveys the same information more clearly.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines. The ASCII architecture diagram, repeated agent listings (agents are listed in Architecture Overview, Phase Execution, Related Skills, and Coordinator Checklist), redundant execution flow descriptions (shown as both ASCII diagram and markdown list), and extensive boilerplate all waste tokens. Much of this (subagent API reference, error handling tables, progress tracking code) could be in referenced phase docs rather than the main SKILL.md. | 1 / 3 |
Actionability | Provides concrete, executable code examples for spawn_agent/wait_agent/close_agent lifecycle, progress tracking initialization, error handling patterns, and specific CLI usage examples with multiple modes. The task pipeline, strategy engine parameters, and quality gate thresholds are all specific and actionable. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing across both phases, explicit validation checkpoints (MANDATORY CONFIRMATION GATE between phases, quality gates at IMPL-001.3 and IMPL-001.5), feedback loops (fix → re-test → decision), error recovery strategies (rollback on regression, CLI fallback chain), and a comprehensive coordinator checklist. The strategy engine progression (conservative → aggressive → surgical) is well-defined. | 3 / 3 |
Progressive Disclosure | References phase docs (phases/01-test-fix-gen.md, phases/02-test-cycle-execute.md) appropriately, but the SKILL.md itself contains far too much inline detail that belongs in those phase docs — the full subagent API reference, detailed error handling table, complete directory structure, and repeated agent listings should be delegated. No bundle files were provided to verify the referenced paths exist. | 2 / 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 | |
5ff5e86
Table of Contents
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.