dev-testing

AI DevKit · Testing phase guidance for adding and validating feature test coverage. Use when the user wants to write tests, update testing docs, run coverage, close coverage gaps, or run dev-lifecycle phase 8.

Quality

79%

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 ./skills/dev-testing/SKILL.md

Quality

Content

76%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 concise, well-sequenced instructional skill with concrete commands and clear sectioning. It would reach the top band by tightening the softer procedural steps into executable mechanics and making the test-run validation feedback loop explicit rather than delegating it to the separate verify skill.

Suggestions

Make the test-run validation loop explicit: add an inline step such as 'run coverage, and if gaps or failures remain, add tests and re-run until target is met' rather than only referencing the separate verify skill.

Tighten soft steps like 'Analyze the testing template' and 'Highlight missing branches' into concrete actions (e.g., 'diff the testing template against the feature changes to list untested branches').

For the Write Tests step 1, give the exact fallback-resolution command or code snippet instead of describing path resolution in prose.

Dimension	Reasoning	Score
Conciseness	The body is an efficient numbered workflow of mostly action-oriented steps with little padding, though a few phrasings like 'Highlight missing branches' and 'suggest additional tests if below the target' are slightly soft and could be trimmed or made concrete.	4 / 5
Actionability	Most steps give concrete, executable commands (e.g. 'npx ai-devkit@latest lint --feature <name>', resolve '.ai-devkit.json paths.docs'), but some steps like 'Analyze the testing template' and 'Add unit tests' describe intent rather than give executable mechanics, leaving minor gaps.	4 / 5
Workflow Clarity	Two clear numbered sequences (Phase Contract, Write Tests) with an explicit ordering and a branching next-step ('If tests reveal design flaws, return to dev-design'), plus a 'verify' skill checkpoint; however the cap-related validation loop is only implied via the separate verify skill rather than an inline validate-then-fix-then-retry cycle for the batch test run.	4 / 5
Progressive Disclosure	Well-organized into clearly labeled sections (Phase Contract, Write Tests) at one level with a short next-phase pointer; there are no bundle files so there are no nested references to mis-signal, and the single-file structure is appropriate for this scope.	4 / 5
	Total	16 / 20 Passed

Description

82%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 strong description that explicitly pairs a clear 'what' with an explicit 'Use when' trigger clause and names several concrete actions. Minor gains are available by adding a few more trigger synonyms and confirming it stays distinct from neighboring dev-lifecycle phase skills.

Dimension	Reasoning	Score
Specificity	Names the domain (Testing phase guidance) and several concrete actions — 'adding and validating feature test coverage', 'run coverage', 'close coverage gaps' — with only minor gaps in coverage (e.g., it doesn't list test-run/pass actions explicitly).	4 / 5
Completeness	Clearly answers both 'what' (Testing phase guidance for adding and validating feature test coverage) and 'when' (an explicit 'Use when...' clause enumerating concrete trigger scenarios).	5 / 5
Trigger Term Quality	Good natural trigger coverage — 'write tests', 'update testing docs', 'run coverage', 'close coverage gaps' — phrased as a user would say them, though it lacks synonyms or the exact tool/extension terms beyond 'dev-lifecycle phase 8'.	4 / 5
Distinctiveness Conflict Risk	The 'AI DevKit · Testing phase' framing and 'dev-lifecycle phase 8' carve a fairly distinct niche, but 'write tests' / 'run coverage' phrasing could overlap with other generic testing skills, leaving minor conflict risk.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: codeaholicguy/ai-devkit
Path: skills/dev-testing/SKILL.md
Commit: d56e554

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.