CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

qa-plan

QA test plan for a sprint — classifies stories by Logic/Integration/Visual/UI, covers automated tests, manual cases, smoke scope.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/qa-plan/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-5

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

An unusually well-engineered workflow document: fully executable tool calls, explicit validation checkpoints with feedback loops, and mandatory guards against false-clean outcomes. Its weaknesses are token efficiency (rationale blocks and repeated level rules that could be compressed) and file structure (the full plan template belongs in a one-level-deep reference file).

Suggestions

Compress the N=0 rationale blockquote to the rule plus a one-line reason ("an empty plan looks identical to a complete one") and drop the restated MISSING-vs-empty distinction.

Move the Phase 4 plan-document template to references/qa-plan-template.md and keep a short summary of its sections inline, keeping SKILL.md as an overview.

State the qa.level variations (minimal/standard/full) once in a single reference table instead of repeating the per-level rules inside Phase 4 and the Definition of Done.

DimensionReasoningScore

Conciseness

The body is mostly dense, actionable instruction, but contains padded passages: the multi-paragraph N=0 rationale blockquote ("a QA plan for zero stories looks exactly like a completed QA plan", "This is the different case where there is no *several*"), meta-explanation of why full story reads are costly, and qa.level rules restated across Phase 4 and the DoD. Not 4: these are more than minor trimmable instances.

3 / 5

Actionability

Fully executable guidance: copy-paste-ready Grep tool invocations with exact patterns, globs, and -A flags; exact output paths (production/qa/qa-plan-[sprint-slug]-[date].md); verbatim AskUserQuestion prompts and after-write message; and a complete plan-document template with a filled example summary table.

5 / 5

Workflow Clarity

Five phases are explicitly sequenced with mandatory validation checkpoints and feedback loops: the N=0 stop-guard with routing messages, MISSING-and-continue for missing files, "Never treat an absent section as an absent story" (full-read that one story), a classification summary gate before Phase 4, explicit write approval in Phase 5, and defined terminal verdicts (COMPLETE / NOT ASSESSED).

5 / 5

Progressive Disclosure

No bundle files exist, and external docs (.claude/docs/automation-modes.md, workflow-modes.md, etc.) are referenced one level deep with stated purpose — but the ~120-line Phase 4 plan template is inlined in an already-long SKILL.md where a references/ template file would keep the overview lean. Some structure, but inlining the template holds it below anchor 4.

3 / 5

Total

16

/

20

Passed

Description

66%Weight 40%Scale 1-5

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, domain-grounded description with a concrete story-type taxonomy and good natural keywords, but it omits any explicit "when to use" trigger guidance and is not comprehensive about the skill's outputs (playtest requirements, DoD, the written plan file). Adding a Use-when clause and a few synonyms would lift the two weakest dimensions.

Suggestions

Add an explicit trigger clause, e.g., "Use when planning QA for an upcoming sprint, feature, or story, or when the user mentions test plans, test coverage, or QA hand-off."

Include synonyms and natural variations users might say: "quality assurance", "test coverage", "playtest planning".

Mention the concrete output (a written QA plan document at production/qa/) so the "what" covers the deliverable, not just the analysis steps.

DimensionReasoningScore

Specificity

"classifies stories by Logic/Integration/Visual/UI, covers automated tests, manual cases, smoke scope" lists several concrete facets including a specific classification taxonomy, though the repeated verb "covers" is generic and playtest planning and the output artifact are absent. Not 5 because coverage has visible gaps; not 3 because it goes beyond 1-2 actions.

4 / 5

Completeness

The "what" is clear (classifies stories, covers automated/manual/smoke scope) but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Natural terms a user would say are present: "QA test plan", "sprint", "automated tests", "manual cases", "smoke". Missing common variations such as "quality assurance" spelled out, "test coverage", or "playtest", keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (sprint-level QA test planning) with distinct vocabulary; only minor overlap risk with adjacent QA skills (e.g., smoke-check, which shares the "smoke" term).

4 / 5

Total

15

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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/qa-plan/SKILL.md

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.