regression-suite

Map test coverage to GDD critical paths, find fixed bugs lacking regression tests, flag drift from new features.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/regression-suite/SKILL.md

Quality

Content

81%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.

A strong, highly actionable instruction-only skill with concrete globs, statuses, templates, guards, and an explicit verdict system — its workflows are among the clearest in structure. The main costs are repetition of the qa.level-minimal guard and the long self-justifying denominator blockquote, plus inline templates that could be split into a reference file.

Suggestions

State the qa.level: minimal guard once (Section 1) and have Step 2c and Section 7 reference it instead of re-explaining the distinction.

Trim the denominator blockquote to its operative rule (empty denominator → NOT ASSESSED with reason and producing skill named); the 0%/100% rationale and cross-skill citations can go.

Move the full manifest/report templates to a reference file (e.g. references/manifest-template.md) and keep a one-line pointer in SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — tables, status enums, and globs earn their tokens — but the qa.level-minimal guard is re-explained in Section 1, Step 2c, and the Section 7 verdict list, and the "denominator" blockquote spends many lines justifying itself ("0% reads as 'measured and terrible'..."). Not 4 because this repetition is more than a minor trim; not 2 because there is no padded concept explanation.	3 / 5
Actionability	Fully executable guidance: exact glob patterns ("tests/unit/*/_test.*"), concrete statuses (COVERED/PARTIAL/MISSING/EXEMPT), literal AskUserQuestion prompts with option text, complete report and manifest templates, and exact suggested test paths. Placeholders like [ext] and "[Engine-specific command]" are appropriately parameterized for a template skill, not gaps.	5 / 5
Workflow Clarity	Clearly sequenced Sections 1-7 with explicit validation checkpoints: an early qa.level guard before any scan, ask-before-write confirmation for manifest writes, a first-match verdict ordering, and error-recovery paths (no smoke report → stop and name /smoke-check; empty denominator → NOT ASSESSED with the producing skill named). Write operations are gated, satisfying the destructive/batch feedback-loop requirement.	5 / 5
Progressive Disclosure	There are no bundle files (no references/, scripts/, or assets/), so this is a single-file skill with well-organized, clearly headed sections. Not 5 because at ~330 lines the full report and manifest templates inline are borderline content that could live in a reference file; not 3 because structure and navigation are otherwise good and references to project docs (.claude/docs/*) are explicit.	4 / 5
	Total	17 / 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 concise, third-person, action-oriented description with good domain keywords, but it lacks any "when to use" trigger clause, capping its completeness. Adding explicit usage triggers and a couple of natural synonyms (e.g. "regression suite") would round it out.

Suggestions

Append a trigger clause, e.g. ". Use when fixing bugs, closing a sprint, running a phase gate, or auditing regression test coverage against GDD critical paths."

Include natural synonyms users would say — "regression suite", "coverage audit", "bug fixes without tests" — to broaden trigger matching.

Mention the deliverable (maintains tests/regression-suite.md) so the description states what the skill produces, not just what it checks.

Dimension	Reasoning	Score
Specificity	"Map test coverage to GDD critical paths", "find fixed bugs lacking regression tests", and "flag drift from new features" name three concrete, distinct actions. Not 5 because coverage has minor gaps — the suite manifest output and the update/audit/report modes are unmentioned; not 3 because it clearly exceeds the 1-2 action level.	4 / 5
Completeness	The "what" is clear (map coverage, find bugs lacking tests, flag drift) but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because "when" is entirely absent rather than just weakly implied; not 2 because the "what" is concrete, not vague.	3 / 5
Trigger Term Quality	Natural domain terms like "test coverage", "regression tests", "fixed bugs", and "drift" are present and would be said by a user managing QA on this project. Not 5 because common variations and synonyms (e.g. "regression suite", "coverage report", "QA") are missing; not 3 because the keywords are natural and relevant rather than sparse or jargon-only.	4 / 5
Distinctiveness Conflict Risk	"GDD critical paths" and "regression tests" pin a clear niche (regression coverage tied to game design docs), distinct from generic test-writing skills. Not 5 because "test coverage" and "flag drift" could pull in general testing/QA skills in a broader environment; not 3 because overlap risk is limited to closely related skills.	4 / 5
	Total	15 / 20 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/regression-suite/SKILL.md
Commit: b21fa0f

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.