fix-tests

Systematically fix all failing tests after business logic changes or refactoring

Quality

56%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./plugins/tdd/skills/fix-tests/SKILL.md

Quality

Content

62%

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

This is a reasonably well-structured orchestration skill with a clear workflow and good feedback loops for iterating on test fixes. Its main weaknesses are the lack of concrete, executable commands (relying on placeholders and discovery steps) and some unnecessary contextual explanation. The agent instructions template is a useful inclusion but the overall actionability suffers from the generic nature of the guidance.

Suggestions

Replace vague discovery steps with concrete examples for common project types (e.g., 'For Node.js: `npx jest --testPathPattern={FILE}`, for Python: `pytest {FILE}`') to improve actionability.

Remove the 'Context' section as it explains concepts Claude already understands; the 'Goal' section alone is sufficient.

Define 'complex logic' more precisely in the constraints section (e.g., based on lines changed, number of functions modified) to make the decision criteria for self-writing vs. orchestrating agents more actionable.

Dimension	Reasoning	Score
Conciseness	The skill includes some unnecessary context (e.g., explaining why tests fail after business logic changes, which Claude already knows) and the 'Context' section is somewhat redundant with the goal. However, it's not excessively verbose and most content serves a purpose.	2 / 3
Actionability	The workflow provides a structured process and includes an agent instructions template, but lacks concrete executable commands (test commands are placeholders like {TEST_COMMAND}), and the guidance for discovering test infrastructure is vague ('Read README.md and package.json'). The decision logic for when to write tests vs. orchestrate agents is useful but the threshold ('complex logic') is subjective.	2 / 3
Workflow Clarity	The workflow is clearly sequenced with numbered steps, includes explicit validation checkpoints (step 7: verify all fixes), and has a feedback loop (step 8: iterate if needed, return to step 5). The preparation → analysis → fixing → verification flow is logical and well-structured with clear error recovery.	3 / 3
Progressive Disclosure	The skill references external skills (sadd skill, TDD skill) but these are conditional ('if available') rather than clearly signaled references. There are no bundle files to support the content, and the agent instructions template could potentially be in a separate file to keep the main skill leaner. The structure is reasonable but not optimally organized.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 communicates a clear purpose—fixing failing tests after code changes—but lacks the specificity and explicit trigger guidance needed for reliable skill selection. It would benefit from listing concrete actions and adding an explicit 'Use when...' clause with natural trigger terms users would employ.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when tests are failing after refactoring, business logic changes, or code modifications and the user needs to update or fix the test suite.'

Include more natural trigger terms users would say, such as 'broken tests', 'test failures', 'CI failing', 'red tests', 'test suite broken'.

List specific concrete actions, e.g., 'Updates assertions, adjusts mocks and stubs, refactors test fixtures, and aligns test expectations with new behavior.'

Dimension	Reasoning	Score
Specificity	Names the domain (fixing failing tests) and a general action (systematically fix), but doesn't list specific concrete actions like 'update assertions', 'refactor test fixtures', 'adjust mocks', etc.	2 / 3
Completeness	Answers 'what' (fix all failing tests) and partially implies 'when' (after business logic changes or refactoring), but lacks an explicit 'Use when...' clause with clear trigger guidance.	2 / 3
Trigger Term Quality	Includes relevant terms like 'failing tests', 'refactoring', and 'business logic changes' which users might naturally say, but misses common variations like 'broken tests', 'test failures', 'test suite', 'red tests', or 'CI failures'.	2 / 3
Distinctiveness Conflict Risk	Somewhat specific to the niche of fixing tests after code changes, but could overlap with general test-writing skills, debugging skills, or refactoring skills without clearer boundaries.	2 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

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

	Total	10 / 11 Passed

Repository: NeoLabHQ/context-engineering-kit
Commit: 3711edf

Reviewed: 20 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.