test-quality

Write or review Cataclysm-BN tests that avoid flakes, use deterministic fixtures, and clean up global state.

Quality

78%

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 ./.agents/skills/test-quality/SKILL.md

Quality

Content

86%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 tight, concrete, instruction-only skill with strong actionability and clear validation checkpoints for destructive/batch test changes. Minor gains possible from consolidating the CI-debugging workflow into a numbered sequence with an explicit feedback loop.

Suggestions

Convert the CI failure and pre-push validation bullets into a short numbered workflow with an explicit 'validate -> fix -> re-run' feedback loop.

Add one minimal copy-paste example of restore_on_out_of_scope and clear_map() usage to lift actionability to fully executable.

Dimension	Reasoning	Score
Conciseness	Lean and dense with no conceptual padding; every bullet is a concrete rule and assumes Claude's competence, with specific flags, paths, and API names earning their place.	5 / 5
Actionability	Guidance is highly actionable with concrete references (--rng-seed, restore_on_out_of_scope, clear_map(), data/mods/TEST_DATA), but as an instruction-only skill it lacks complete copy-paste code blocks, leaving minor gaps.	4 / 5
Workflow Clarity	Explicit validation checkpoints are present (reproduce flakes with --rng-seed before accepting a fix; run focused plus CI-equivalent shard before pushing), but the steps are scattered as gates rather than a crisp numbered sequence with feedback loops.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, no external references needed, and well-organized into Gates and Cleanup sections, qualifying for the top score per the simple-skills guidance.	5 / 5
	Total	18 / 20 Passed

Description

70%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 specific, domain-scoped description that clearly states what the skill does, but it lacks an explicit 'Use when...' trigger clause which caps its completeness. Trigger-term coverage is good but could add common synonyms like 'flaky tests'.

Suggestions

Add an explicit trigger clause, e.g. 'Use when adding, reviewing, or debugging Cataclysm-BN tests, or when fixing flaky tests.'

Include common synonyms such as 'flaky tests', 'unit tests', or 'test suite' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the Cataclysm-BN test domain and lists several specific concerns (write/review tests, avoid flakes, deterministic fixtures, clean up global state), with only minor coverage gaps.	4 / 5
Completeness	The 'what' is clear and concrete, but there is no explicit 'Use when...' trigger clause, so completeness is capped at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	Natural terms like 'tests', 'write', 'review', 'flakes', 'fixtures', and 'Cataclysm-BN' are present, though a few common variations (e.g. 'flaky tests', 'unit tests') are missing.	4 / 5
Distinctiveness Conflict Risk	The Cataclysm-BN test niche is highly specific with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	16 / 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: cataclysmbn/Cataclysm-BN
Path: .agents/skills/test-quality/SKILL.md
Commit: b782646

Reviewed: 1 day 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.