testing

Skill validation framework PLUS daily test-suite health and regression intelligence. Validates skill conformance (frontmatter, manifest coverage, resolver coverage). Runs the project test suite in tiered phases (unit / evals / integration / system health), classifies failures, and produces a regression-aware report.

Quality

73%

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 ./skills/testing/SKILL.md

Quality

Content

75%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 dense, highly actionable body with concrete commands, classification tables, and a well-sequenced two-mode workflow including escalation feedback loops. Its main weaknesses are conformance-test boilerplate duplicated at the end and version literals that could go stale, which keep conciseness at 3.

Suggestions

Remove or consolidate the trailing '## Contract' and '## Output Format' sections that exist only 'for the conformance test' to trim padding and raise conciseness.

Move version-specific markers ('v0.25.1 extension', '1.0 scope') out of the body or into a deprecated/old-patterns note so they do not go stale.

Add an explicit 're-run the affected tests to confirm green' checkpoint after the auto-fix protocol to close the workflow-clarity gap.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tables, commands, and code blocks, but it carries unnecessary padding: a duplicated '## Contract' and '## Output Format' at the end explicitly labelled as existing 'for the conformance test', plus stale-prone version literals ('v0.25.1 extension', '1.0 scope'). Not a 4 because the boilerplate conformance-test scaffolding is clearly trimmable; not a 2 because the bulk is lean rather than extensively padded.	3 / 5
Actionability	Fully executable guidance throughout — 'bun test test/skills-conformance.test.ts ...', 'git log --oneline --since="24 hours ago"', 'gbrain doctor --fast --json', concrete classification and report-format templates, a state JSON example, and DO/DO-NOT auto-fix rules cover the common cases copy-paste ready.	5 / 5
Workflow Clarity	Both modes are clearly sequenced (Mode 1 phases 1–7; Mode 2 daily protocol steps 1–7) with classification, DO/DO-NOT escalation rules, and a retry-once feedback loop for flakes. Not a 5 because there is no explicit 're-run to confirm green' checkpoint after an auto-fix; not a 3 because validation/escalation checkpoints are clearly present, so the destructive/batch cap does not apply.	4 / 5
Progressive Disclosure	Well-organized into clearly signalled sections (Two modes, Mode 1, Mode 2 subsections, Anti-Patterns) with project-file references (manifest.json, RESOLVER.md, conventions/quality.md) one level deep and no nested reference chains. No bundle files exist to verify. Not a 5 because the trailing duplicate Contract/Output Format scaffolding is a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

71%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, third-person description with strong capability detail and good keyword coverage, but it omits any explicit 'Use when...' trigger guidance, which caps completeness at 3. The dual-mode scope slightly raises conflict risk.

Suggestions

Add an explicit 'Use when ...' clause naming natural trigger phrases (e.g., 'Use when running the test suite, checking daily test health, asking what's broken, or validating skill conformance') to lift completeness above 3.

Include common-synonym trigger terms like 'broken tests' or 'test health' to broaden natural keyword coverage.

Clarify which mode fires for which trigger so the dual-purpose scope does not collide with a dedicated testing or conformance skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across both modes — 'Validates skill conformance (frontmatter, manifest coverage, resolver coverage)', 'Runs the project test suite in tiered phases (unit / evals / integration / system health)', 'classifies failures, and produces a regression-aware report' — comprehensive coverage of what the skill does.	5 / 5
Completeness	The 'what' is clear and detailed, but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 3. Not a 4 because the 'when' is entirely absent rather than merely weak.	3 / 5
Trigger Term Quality	Good keyword coverage including natural terms ('test suite', 'regression', 'failures', 'report') alongside technical ones ('frontmatter', 'manifest coverage', 'resolver coverage'), but leans technical and omits common phrasings like 'broken tests' or 'what's broken'. Not a 5 because synonyms and natural variations are incomplete; not a 3 because coverage is clearly above 'some relevant keywords'.	4 / 5
Distinctiveness Conflict Risk	The combined skill-validation-plus-test-health niche is mostly distinct with specific triggers, but bundling two modes creates minor overlap risk with a pure 'testing' or pure 'conformance' skill. Not a 5 because of that overlap risk; not a 3 because the domain is clearly narrower than generic file/code helpers.	4 / 5
	Total	16 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/testing/SKILL.md
Commit: 055ac6c

Reviewed: about 2 hours 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.