team-qa

Orchestrate the QA team through a full testing cycle. Coordinates qa-lead (strategy + test plan) and qa-tester (test case writing + bug reporting) to produce a complete QA package for a sprint or feature. Covers: test plan generation, test case writing, smoke check gate, manual QA execution, and sign-off report.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/team-qa/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-sequenced, highly actionable QA orchestration pipeline with strong validation gates and error-recovery feedback loops. Its main weaknesses are repeated boilerplate that inflates token cost and a monolithic structure with no externalized reference materials.

Suggestions

De-duplicate the smoke-check status logic by defining the PASS/WARNINGS/FAIL/UNKNOWN handling once and referencing it from Phase 4 rather than restating it.

Extract the reusable artifacts (sign-off report template, strategy/classification tables, AskUserQuestion option sets) into reference files under references/ and link to them one level deep.

Tighten the repeated AskUserQuestion option blocks into a shared convention statement to reduce boilerplate tokens.

Dimension	Reasoning	Score
Conciseness	The body is directive and assumes Claude's QA knowledge (no basic-concept explanations), but at ~234 lines it repeats material — the smoke-check status logic is restated across Phase 2 and Phase 4, and AskUserQuestion option blocks and verdict text are boilerplate-duplicated. It is not a 3 because of this redundancy and length, and not a 1 because it does not pad with concepts Claude already knows.	2 / 3
Actionability	Provides concrete, copy-paste-ready guidance: exact Task subagent_type values (qa-lead, qa-tester), precise file paths (production/qa/qa-plan-[sprint]-[date].md), full AskUserQuestion option blocks, the BUG-[NNN]-[short-slug].md naming convention, and complete report markdown templates. Per the scoring note, absence of code in this instruction-only skill is not penalized because the guidance is fully actionable; it is not a 2 because nothing is left as vague pseudocode.	3 / 3
Workflow Clarity	Explicit Phase 0→6 sequence with a validation gate (smoke check FAIL halts the cycle, UNKNOWN surfaces a warning), entry/exit criteria, and an Error Recovery Protocol providing feedback loops (surface BLOCKED, assess dependencies, offer options, always emit a partial report). It is not a 2 because checkpoints and feedback loops are explicit rather than implicit.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the ~234-line skill is monolithic with report templates and classification guidance inlined, so content that could be externalized is not split. It is not a 1 because the body is well-organized into clearly headed sections rather than a wall of text, and not a 3 because there are no one-level-deep references and nothing is appropriately separated into reference files.	2 / 3
	Total	10 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-targeted QA-orchestration description that names concrete actions and natural trigger terms with a clear niche. Its only gap is the absence of an explicit 'Use when...' trigger clause, which leaves the 'when' merely implied.

Suggestions

Append an explicit trigger clause, e.g., 'Use when the user asks to run QA on a sprint or feature, wants a test plan, or requests QA sign-off.'

Add common user phrasings such as 'run tests', 'QA this sprint', or 'write test cases' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Coordinates qa-lead (strategy + test plan) and qa-tester (test case writing + bug reporting)' and an enumerated 'Covers' set (test plan generation, test case writing, smoke check gate, manual QA execution, sign-off report). It is not a 2 because it goes beyond naming a domain and a few actions to a comprehensive, specific action list.	3 / 3
Completeness	'What' is explicit (orchestrate the QA team, coordinate two agents, produce a QA package), but 'when' is only implied via 'for a sprint or feature' with no 'Use when...' clause. Per the rubric guideline, a missing explicit trigger clause caps completeness at 2; it is not a 3 for that reason and not a 1 because 'what' is clearly answered.	2 / 3
Trigger Term Quality	Includes natural terms a user would say for this domain — 'QA team', 'testing cycle', 'test plan', 'test cases', 'smoke check', 'manual QA', 'sign-off', 'sprint or feature'. It is not a 2 because coverage spans the common variations rather than a single keyword.	3 / 3
Distinctiveness Conflict Risk	Targets a clear QA-testing niche with distinct triggers (qa-lead, qa-tester, smoke check gate, sign-off report), unlikely to fire for unrelated skills. It is not a 2 because the niche and triggers are specific rather than broadly overlapping.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/team-qa/SKILL.md
Commit: 984023d

Reviewed: 3 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.