Name: test-fixing
Rating: 68 (1 reviews)
Author: administrakt0r

test-fixing

Systematically identify and fix all failing tests using smart grouping strategies. Use when explicitly asks to fix tests ("fix these tests", "make tests pass"), reports test failures ("tests are failing", "test suite is broken"), or completes implementation and wants tests passing.

Quality

83%

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

The canonical home for this skill is test-fixing in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

75%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 delivers a clear, actionable test-fixing workflow with concrete commands, per-group verification, and a worked example. Main weaknesses are mild redundancy across sections and slightly abstract fix-implementation guidance.

Suggestions

Remove the redundant restatement of the frontmatter triggers in the opening line and "When to Use" section to tighten conciseness.

Add explicit error-recovery guidance in the "Verify fix" step for when a fix does not make the group pass (e.g., re-read the error, re-run git diff, try the next root cause) to reach a workflow feedback loop.

Collapse "Best Practices" into the existing workflow steps to eliminate overlap with the systematic fixing process.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with concrete commands and no over-explanation of concepts Claude knows, but the opening line and "When to Use" section repeat the frontmatter triggers and "Best Practices" restates steps already in the workflow; not a 5 because of this redundancy.	4 / 5
Actionability	Provides executable commands (`make test`, `git diff`, `uv run pytest ... -v`, `uv run pytest -k "pattern" -v`) and a concrete example workflow; the "Implement fix" step stays abstract ("Use Edit tool", "make minimal changes"), so it is mostly executable with minor gaps rather than fully copy-paste ready.	4 / 5
Workflow Clarity	A clear five-step sequence with per-group verification checkpoints ("Ensure group passes before moving on") and a final full-suite regression check; not a 5 because explicit error-recovery guidance when a fix fails is implied rather than spelled out.	4 / 5
Progressive Disclosure	Single well-organized file with clear section headers and no nested references; content is appropriately inline since no bundle files exist. Not a 5 because some sections duplicate material and the >50-line simple-skill exception does not apply.	4 / 5
	Total	16 / 20 Passed

Description

91%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 strong: it states what the skill does and gives multiple concrete, natural-language trigger phrases that a user would actually say. The only soft spot is minor overlap risk with general debugging skills.

Dimension	Reasoning	Score
Specificity	"Systematically identify and fix all failing tests using smart grouping strategies" names the domain plus three concrete actions (identify, fix, group), matching the 'lists several specific actions; minor gaps' anchor; not a 5 because it stops short of enumerating the range of fix categories.	4 / 5
Completeness	Clearly states the 'what' (identify and fix all failing tests via smart grouping) and an explicit 'Use when...' clause with concrete trigger phrases, matching the anchor that requires both with concrete triggers.	5 / 5
Trigger Term Quality	Quotes four natural user phrases — "fix these tests", "make tests pass", "tests are failing", "test suite is broken" — plus a completion case, giving comprehensive coverage of real trigger utterances; not below 5 since synonyms/variations are well covered.	5 / 5
Distinctiveness Conflict Risk	"Identify and fix all failing tests" is a clear niche with distinct test-fixing triggers, but it carries minor overlap risk with general debugging or testing skills; not a 5 because that overlap is not fully eliminated.	4 / 5
	Total	18 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/test-fixing/SKILL.md
Commit: 57c135b

Reviewed: 7 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.