test-discipline

Update tests when changing APIs — no exceptions

Quality

72%

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 ./.copilot/skills/test-discipline/SKILL.md

Quality

Content

87%Weight 40%Scale 1-3

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

A tight, well-structured instruction-only skill with concrete examples and good sectioning. Its main gap is the absence of an explicit validation/feedback loop for the batch test-update operations it describes.

Suggestions

Add an explicit validate-fix-retry checkpoint (e.g., "After updating tests, run them; if CI fails on assertion mismatches, re-sync EXPECTED_* arrays and re-run before committing").

Turn the API-change pattern into a short numbered sequence (update signature -> update tests -> run suite -> commit) so the workflow sequence is explicit rather than implied by bullets.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept-explanation padding; every line (e.g., "When APIs or public interfaces change, tests must be updated in the same commit") earns its place.	3 / 3
Actionability	Guidance is concrete and instruction-actionable: named assertion arrays (EXPECTED_FEATURES, EXPECTED_SCENARIOS) and specific worked examples (auth API -> auth.test.ts); absence of code is fine for an instruction-only skill.	3 / 3
Workflow Clarity	Patterns are clear bullets and "CI failures -> check assertions first" gives a debugging order, but there is no explicit validate-fix-retry checkpoint loop for batch test operations.	2 / 3
Progressive Disclosure	Under 50 lines with well-organized sections (Context, Patterns, Examples, Anti-Patterns) and no need for external references, fitting the simple-skill allowance.	3 / 3
	Total	11 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 concise and distinct but terse: it names one concrete action and implies its trigger rather than giving explicit "Use when" guidance. It would benefit from explicit trigger terms and broader keyword coverage.

Suggestions

Add an explicit "Use when..." clause (e.g., "Use when changing function signatures, public interfaces, or exported APIs, or when test assertions reference file counts").

Broaden trigger terms to include natural variations users say: "test files", "CI", "assertions", "expected arrays", "commit".

Name the concrete sub-actions (update test files, sync EXPECTED_* assertion arrays) to lift specificity from a single action to multiple specific actions.

Dimension	Reasoning	Score
Specificity	It names a concrete action ("Update tests") tied to a trigger ("changing APIs"), but lists only a single action rather than multiple specific ones.	2 / 3
Completeness	It states what to do ("Update tests when changing APIs") but provides no explicit "Use when..." trigger clause, so the "when" is only implied.	2 / 3
Trigger Term Quality	"tests" and "APIs" are natural terms a user might say, but coverage is thin and omits common variations like test files, CI, assertions, or commits.	2 / 3
Distinctiveness Conflict Risk	The test/API-sync discipline is a clear niche with distinct triggers, unlikely to fire for unrelated skills.	3 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: microsoft/waza
Path: .copilot/skills/test-discipline/SKILL.md
Commit: f466c4f

Reviewed: 13 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.