team-quality-assurance
Unified team skill for quality assurance. Full closed-loop QA combining issue discovery and software testing. Triggers on "team quality-assurance", "team qa".
69
62%
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/team-quality-assurance/SKILL.mdQuality
Discovery
40%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 too abstract and relies on domain buzzwords ('closed-loop QA', 'issue discovery') without specifying concrete actions the skill performs. While it includes explicit trigger commands, it lacks natural language trigger terms users would actually say and doesn't clearly describe the range of specific capabilities.
Suggestions
Replace abstract phrases like 'full closed-loop QA combining issue discovery and software testing' with specific actions such as 'writes unit/integration tests, identifies bugs through code review, generates test plans, tracks defects'.
Add a 'Use when...' clause with natural trigger scenarios like 'Use when the user asks to write tests, review code for bugs, create a test plan, improve test coverage, or set up QA workflows'.
Include natural keyword variations users might say: 'tests', 'bugs', 'test coverage', 'regression', 'test suite', 'defects', 'code review'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'quality assurance', 'issue discovery', and 'software testing' but these are abstract domain terms rather than concrete actions. It doesn't list specific things the skill does (e.g., 'write unit tests', 'run test suites', 'file bug reports'). | 1 / 3 |
Completeness | It partially answers 'what' (closed-loop QA combining issue discovery and software testing) and has trigger terms, but the 'when' guidance is limited to specific command-like triggers ('team quality-assurance', 'team qa') rather than describing natural scenarios when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | It includes 'team quality-assurance' and 'team qa' as explicit triggers, and mentions 'software testing' and 'issue discovery'. However, these are somewhat formulaic and miss natural user phrases like 'write tests', 'find bugs', 'test coverage', 'regression testing', etc. | 2 / 3 |
Distinctiveness Conflict Risk | The 'team qa' and 'team quality-assurance' triggers are fairly distinct command-style triggers, but the broader description ('quality assurance', 'software testing', 'issue discovery') could overlap with individual testing or debugging skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
85%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 orchestration skill that clearly defines the multi-agent QA pipeline architecture, delegation rules, and worker spawn patterns. Its strengths are the highly actionable delegation lock, concrete spawn templates, and excellent progressive disclosure to role-specific files. Minor verbosity in some tables and the model selection guide could be tightened, but overall this is a strong skill document.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is fairly dense and information-rich, but includes some sections that could be tightened—like the model selection guide with '(default)' repeated for every role, and the verbose spawn template. Some tables add clarity but others feel redundant. Overall mostly efficient but not maximally lean. | 2 / 3 |
Actionability | Provides concrete spawn_agent templates with exact parameter structures, specific tool call allowlists/blocklists, exact file paths, CLI commands, and copy-paste ready code blocks for agent spawning, health checks, and completion actions. The delegation lock table is highly specific and executable. | 3 / 3 |
Workflow Clarity | The pipeline is clearly sequenced (scout -> strategist -> generator -> executor -> analyst) with explicit validation via agent health checks, GC loops for coverage gaps (max 3 rounds), error handling table, and the delegation lock acts as a checkpoint preventing coordinator from doing worker tasks. The architecture diagram and pipeline pattern are well-defined. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure: the SKILL.md serves as a router/overview, with each role's details in separate files (roles/<name>/role.md), specs in dedicated files (specs/pipelines.md, specs/team-config.json), and clear one-level-deep references via the Role Registry table with direct links. Content is appropriately split between overview and detail files. | 3 / 3 |
Total | 11 / 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.