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".

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/team-quality-assurance/SKILL.md

Quality

Content

72%Scale 1-3

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 effectively serves as a routing hub for a multi-agent QA pipeline. Its strengths are strong actionability with concrete spawn templates and clear progressive disclosure to role-specific files. The main weakness is the lack of explicit validation checkpoints between pipeline stages, which is important for a complex multi-step orchestration workflow.

Suggestions

Add explicit validation/checkpoint steps between pipeline stages (e.g., 'Coordinator verifies scout output exists before spawning strategist') to improve workflow clarity.

Document the GC (generate-check) loop mechanism more concretely — what triggers it, what validation occurs, and what the exit criteria are.

Dimension	Reasoning	Score
Conciseness	The content is reasonably efficient for a complex multi-agent orchestration skill, but includes some structural elements (like the ASCII architecture diagram) that could be tightened. The worker spawn template and completion action blocks are verbose but arguably necessary for copy-paste usage.	2 / 3
Actionability	Provides concrete, executable templates including the Agent spawn template with exact parameters, the AskUserQuestion completion block, specific CLI commands, exact file paths, and a clear role router decision logic. These are copy-paste ready for Claude to use.	3 / 3
Workflow Clarity	The pipeline flow (scout -> strategist -> generator -> executor -> analyst) is clearly sequenced, and error handling is documented in a table. However, there are no explicit validation checkpoints between pipeline stages, and the feedback/GC loop mechanism is mentioned but not detailed with concrete validation steps.	2 / 3
Progressive Disclosure	Excellent progressive disclosure structure: SKILL.md serves as a clear router/overview with well-signaled one-level-deep references to role files (roles/<name>/role.md) and spec files (specs/pipelines.md, specs/team-config.json). The role registry table provides a clean navigation index.	3 / 3
	Total	10 / 12 Passed

Description

40%Scale 1-3

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 buzzwords ('full closed-loop QA') rather than concrete actions. While it provides command-style trigger terms, it lacks natural user language and specific capability details that would help Claude distinguish this skill from other testing or debugging skills. The description would benefit significantly from listing concrete actions and broadening trigger term coverage.

Suggestions

Replace vague phrases like 'full closed-loop QA combining issue discovery and software testing' with specific actions such as 'Discovers bugs through static analysis, generates and runs test suites, tracks issues to resolution'.

Add a 'Use when...' clause with natural trigger terms like 'find bugs', 'write tests', 'test coverage', 'regression testing', 'run QA', 'check for defects'.

Clarify what makes this a 'unified team skill' versus an individual QA skill — specify if it coordinates multiple agents, runs parallel test suites, or combines distinct QA workflows.

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'quality assurance', 'issue discovery', and 'software testing' without listing concrete actions. 'Full closed-loop QA' is a buzzword phrase that doesn't describe specific capabilities like 'run unit tests', 'generate test cases', or 'file bug reports'.	1 / 3
Completeness	The 'what' is present but vague ('issue discovery and software testing'). The 'when' is partially addressed with trigger phrases ('Triggers on "team quality-assurance", "team qa"'), but these are command triggers rather than explicit guidance on when Claude should select this skill based on user intent or context.	2 / 3
Trigger Term Quality	It includes some relevant keywords like 'quality assurance', 'qa', 'issue discovery', and 'software testing', but the explicit triggers ('team quality-assurance', 'team qa') are command-like rather than natural user language. Missing common variations like 'bug', 'test coverage', 'regression', 'defect'.	2 / 3
Distinctiveness Conflict Risk	The 'team quality-assurance' and 'team qa' trigger terms provide some distinctiveness as command-style triggers, but the broader description of 'issue discovery and software testing' could overlap with individual testing or debugging skills. The 'team' prefix helps somewhat but the scope remains unclear.	2 / 3
	Total	7 / 12 Passed

Validation

90%

Warnings & errors only

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
Path: .claude/skills/team-quality-assurance/SKILL.md
Commit: 07491b0

Reviewed: 1 month ago

Table of Contents

Discovery Implementation Validation

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.