team-testing

Unified team skill for testing team. Progressive test coverage through Generator-Critic loops, shared memory, and dynamic layer selection. Triggers on "team testing".

Quality

48%

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-testing/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 serves effectively as a router/overview for a multi-agent testing pipeline. Its strengths are strong actionability with concrete spawn templates and clear progressive disclosure to role-specific files. Its main weaknesses are the lack of explicit validation checkpoints between pipeline stages and some verbosity in the spawn template and completion action blocks that could be tightened.

Suggestions

Add explicit validation/checkpoint steps between pipeline stages (e.g., verify strategist output before spawning generator) to improve workflow clarity.

Detail the Generator-Critic loop convergence criteria and feedback mechanism, since this is mentioned as a core feature but lacks concrete workflow steps.

Dimension	Reasoning	Score
Conciseness	The content is reasonably efficient and avoids explaining basic concepts, but includes some verbose sections like the full ASCII architecture diagram and the completion action AskUserQuestion block that could be more compact. The worker spawn template is quite lengthy.	2 / 3
Actionability	Provides concrete, executable guidance: specific Agent spawn templates with exact parameters, precise file paths, CLI commands (ccw cli --mode analysis/write), team_msg function signatures, and a clear role routing mechanism. The worker spawn template is copy-paste ready.	3 / 3
Workflow Clarity	The pipeline sequence (strategist -> generator -> executor -> analyst) is clear, and the role router logic is well-defined. However, there are no explicit validation checkpoints between pipeline stages, and the Generator-Critic loop mentioned in the description lacks detail on convergence criteria or feedback loops for error recovery within the workflow.	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), specs (specs/pipelines.md, specs/team-config.json), and a clear session directory layout. Navigation is straightforward via the Role Registry table.	3 / 3
	Total	10 / 12 Passed

Description

25%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.

This description relies heavily on internal jargon and abstract concepts rather than concrete, user-facing actions. It fails to describe what specific testing tasks it performs and uses an artificial trigger phrase ('team testing') that users would rarely say naturally. The description would benefit significantly from listing concrete capabilities and including natural trigger terms.

Suggestions

Replace jargon like 'Generator-Critic loops' and 'dynamic layer selection' with concrete actions such as 'generate unit tests', 'identify untested code paths', 'validate test coverage metrics'.

Replace the artificial trigger 'team testing' with natural user phrases like 'write tests', 'improve test coverage', 'unit tests', 'integration tests', 'test suite'.

Add a clear 'Use when...' clause with realistic scenarios, e.g., 'Use when the user asks to write tests, increase test coverage, or generate test cases for their code.'

Dimension	Reasoning	Score
Specificity	The description uses abstract, jargon-heavy language like 'Generator-Critic loops', 'shared memory', and 'dynamic layer selection' without describing concrete actions. It does not list specific tasks the skill performs (e.g., 'generate unit tests', 'run test suites', 'measure coverage').	1 / 3
Completeness	It attempts to answer both 'what' (progressive test coverage through Generator-Critic loops) and 'when' (triggers on 'team testing'), but the 'what' is vague/jargon-laden and the 'when' trigger is artificially narrow and not a natural user phrase. The trigger clause exists but is weak.	2 / 3
Trigger Term Quality	The only explicit trigger is 'team testing', which is not a natural phrase users would say. It lacks common terms like 'unit tests', 'test coverage', 'write tests', 'integration tests', or 'test suite' that users would naturally use.	1 / 3
Distinctiveness Conflict Risk	The specific jargon ('Generator-Critic loops', 'shared memory', 'dynamic layer selection') and the narrow trigger phrase 'team testing' make it unlikely to conflict with other skills, but the domain of 'testing' is broad enough that it could overlap with other test-related skills.	2 / 3
	Total	6 / 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-testing/SKILL.md
Commit: 07491b0

Reviewed: 23 days 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.