test-discipline

Update tests when changing APIs — no exceptions

Quality

66%

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

71%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.

The content is a well-organized, actionable discipline skill with a clear section structure and an implicit verification checkpoint, but it carries redundant restating of the same rules across Patterns, Examples, and Anti-Patterns that could be tightened.

Suggestions

Merge overlapping points between Patterns, Examples, and Anti-Patterns to remove redundancy and lift conciseness.

Add an explicit pre-commit validation step (e.g., 'Run the affected test suite locally before committing') to strengthen workflow_clarity toward 5.

Collapse the Anti-Patterns that merely restate Incorrect examples into a single section to reduce token cost.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude knows what tests/APIs/CI are, but the Patterns, Examples, and Anti-Patterns sections repeat the same ideas (e.g., committing API changes without test updates appears in both), so it could be tightened; this fits score 3 rather than 4.	3 / 5
Actionability	Directives are concrete and specific ('update the corresponding tests before committing', 'verify test assertion arrays match filesystem state') and the Correct/Incorrect examples cover common cases, matching score 4; not 5 because guidance is policy-level rather than copy-paste-ready commands.	4 / 5
Workflow Clarity	An implicit sequence exists (change API -> update tests same commit) with a verification checkpoint ('CI failures -> check assertions first'), fitting score 4; not 5 because there is no explicit 'run tests/CI before committing' validation step in the sequence.	4 / 5
Progressive Disclosure	The skill is under 50 lines, single-purpose, needs no external references, and is organized into clearly headed sections (Context, Patterns, Examples, Anti-Patterns), matching the simple-skill exception that allows score 5 for well-organized sections with no bundle files.	5 / 5
	Total	16 / 20 Passed

Description

62%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.

The description is concise and states a clear what-and-when trigger, but it offers only one concrete action and a narrow trigger set with no synonyms, capping specificity and trigger-term quality at the midpoint.

Suggestions

Add 1-2 more concrete actions (e.g., 'sync expected-count assertions to disk, update test fixtures') to lift specificity toward 4-5.

Broaden trigger terms with synonyms users actually say (e.g., 'test failures', 'CI breakage', 'stale assertions', 'API signature changes') to improve trigger-term coverage.

Consider an explicit 'Use when...' clause enumerating triggers to push completeness toward 5.

Dimension	Reasoning	Score
Specificity	The phrase 'Update tests when changing APIs' names the domain and one concrete action, matching the score-3 anchor of naming the domain with 1-2 concrete actions; it is not score 4 because only a single action is given and coverage is not comprehensive.	3 / 5
Completeness	It states both what ('Update tests') and when ('when changing APIs') in one clause, so the missing-'Use when' cap at 3 does not apply; it stays at 4 rather than 5 because the single trigger is narrow and lacks the richer concrete trigger phrases of the score-5 example.	4 / 5
Trigger Term Quality	Natural terms 'tests', 'APIs', and 'update' are present but coverage is thin with no synonyms or variations, fitting the score-3 anchor of some relevant keywords missing common variations.	3 / 5
Distinctiveness Conflict Risk	The test-discipline-around-API-changes niche is mostly distinct with only minor overlap risk against general testing or CI skills, matching score 4 rather than 5 because some overlap with broad testing skills remains.	4 / 5
	Total	14 / 20 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: 611250c

Reviewed: 17 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.