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

68%

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

77%

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

The body is highly actionable with clearly sequenced workflows and concrete commands, but it carries redundant conformance-test placeholder sections and keeps most detail inline rather than splitting it across reference files.

Suggestions

Remove or fold the trailing 'Contract' and 'Output Format' sections that exist only for the conformance test, since they duplicate content already documented inline in the body.

Move the verbose daily-run protocol, output-format templates, and regression-state JSON into a separate reference file referenced one level deep from the overview to improve progressive disclosure.

Add an explicit re-run/retest step after auto-fix in the daily protocol to close the validate→fix→retry loop concretely.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — tables, concrete commands, and no over-explanation of concepts Claude knows — but the trailing 'Contract' and 'Output Format' sections explicitly state they exist only to satisfy the conformance test, which is redundant padding that keeps it below the lean level-3 anchor.	2 / 3
Actionability	It provides fully executable commands ('bun test test/skills-conformance.test.ts …', 'git log --oneline --since="24 hours ago"', 'gbrain doctor --fast --json'), concrete output-format templates, a classification table, and a JSON state example — copy-paste ready, matching the level-3 anchor.	3 / 3
Workflow Clarity	Mode 1 lists numbered phases (1–7) and Mode 2 gives a 7-step daily protocol with a failure-classification checkpoint and explicit DO/DO NOT auto-fix guardrails, matching the clear-sequence-with-checkpoints level-3 anchor.	3 / 3
Progressive Disclosure	No bundle files exist and sections are well-organized with one clearly signaled one-level reference (conventions/quality.md), but ~230 lines of largely inline content (full daily-run protocol, output templates, state JSON) that could be split keeps it at 'some structure but content that should be separate is inline'.	2 / 3
	Total	10 / 12 Passed

Description

60%

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

The description is specific and action-oriented about what the skill does, but it is jargon-heavy, omits explicit 'Use when…' trigger guidance, and blends two scopes in a way that weakens distinctiveness.

Suggestions

Add an explicit 'Use when…' clause naming natural triggers such as 'run the tests', 'how are the tests', or 'what's broken' to lift completeness and trigger-term quality.

Replace jargon-heavy phrases ('manifest coverage', 'resolver coverage', 'regression intelligence') with plainer user-facing language so the description reads as natural keywords.

Tighten the dual-mode framing so the skill's distinct niche (skill conformance + test-suite regression) is unambiguous and less likely to overlap with a generic testing skill.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Validates skill conformance (frontmatter, manifest coverage, resolver coverage)', 'Runs the project test suite in tiered phases', 'classifies failures', and 'produces a regression-aware report' — matching the level-3 anchor of several specific concrete actions rather than the partial level-2.	3 / 3
Completeness	It clearly answers 'what' but contains no 'Use when…' clause or equivalent explicit trigger guidance, which the rubric guidelines cap at 2; it cannot reach level 3 without an explicit when.	2 / 3
Trigger Term Quality	It includes some natural terms ('test suite', 'failures', 'daily test-suite health') but leans heavily on jargon ('conformance', 'manifest coverage', 'resolver coverage', 'regression intelligence') and omits common phrasings a user would actually say like 'run the tests' or 'what's broken', so it is not the full-coverage level 3.	2 / 3
Distinctiveness Conflict Risk	The skill-conformance validation niche is distinctive, but the dual-mode scope plus the generic 'daily test-suite health' framing could overlap with a general testing skill, fitting 'somewhat specific but could still overlap' rather than the clear-niche level 3.	2 / 3
	Total	9 / 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
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: 3fafb69

Reviewed: about 20 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.