test-quality

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

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

Quality

Content

85%

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

A lean, well-organized checklist with concrete named APIs and explicit validation gates. The one real gap is actionability: it references flags and functions in isolation without a copy-paste-ready example.

Suggestions

Add one copy-paste-ready example, e.g. a minimal Cataclysm-BN test using 'restore_on_out_of_scope' with a 'TEST_DATA' fixture, or the exact CI shard command, so guidance is fully executable rather than references in isolation.

Show the assembled '--rng-seed' reproduction command (the full test invocation with the failing seed) so the reproduce-flake workflow can be run verbatim.

Dimension	Reasoning	Score
Conciseness	The body is a lean bullet checklist with no concept explanations or filler — it assumes Claude's competence and every line is actionable. It is not a 2 because there is no unnecessary explanation like the 'good library that handles most formats' filler in the 2-anchor.	3 / 3
Actionability	It names concrete real mechanisms — 'restore_on_out_of_scope', 'clear_map()', 'data/mods/TEST_DATA', '--rng-seed' — but never assembles them into a copy-paste-ready command or example test, so key execution details are missing. It is above the pseudocode 2-anchor example yet short of the fully-executable 3-anchor.	2 / 3
Workflow Clarity	Multi-step processes carry explicit validation gates and feedback loops — 'reproduce with the failing --rng-seed before accepting the fix', 'run that same shard command... before declaring the fix validated', 'run both... before pushing'. Checkpoints are explicit, not implicit, so it clears the 2-anchor.	3 / 3
Progressive Disclosure	The skill is under 50 lines, single-purpose, and needs no external references, with well-organized 'Gates' and 'Cleanup' sections. Per the simple-skills note this scores 3 on structure alone; it is not a 2 because content is appropriately inline rather than poorly signaled.	3 / 3
	Total	11 / 12 Passed

Description

82%

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, distinctive description that names several concrete actions and uses natural domain keywords. Its main weakness is the missing explicit 'Use when...' trigger, which caps completeness at 2.

Suggestions

Add an explicit trigger clause, e.g. 'Use when adding, fixing, or reviewing Cataclysm-BN automated tests — especially flaky or state-dependent ones.' to satisfy the 'when' half of completeness.

Broaden natural keyword coverage with common variations users might say, such as 'flaky tests', 'test fixtures', and 'CI test failures'.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'Write or review Cataclysm-BN tests', 'use deterministic fixtures', and 'clean up global state' — matching the 'lists multiple specific concrete actions' anchor. It is not a 2 because it goes beyond naming a domain to enumerate several distinct actions.	3 / 3
Completeness	It clearly answers 'what' (write/review tests, avoid flakes, deterministic fixtures, clean up state) but has no explicit 'Use when...' trigger clause, so 'when' is only implied. The rubric guideline caps completeness at 2 for a missing trigger; it is not 1 because the 'what' is strong and not 3 because 'when' is not explicit.	2 / 3
Trigger Term Quality	It uses natural domain terms a user of this codebase would actually say — 'Cataclysm-BN tests', 'flakes', 'fixtures', 'global state' — giving good coverage. It clears the 2-anchor because these are the keywords a user would naturally invoke, not jargon.	3 / 3
Distinctiveness Conflict Risk	It is pinned to the specific 'Cataclysm-BN' testing niche with distinct, domain-bound triggers, making it unlikely to fire for unrelated skills. It is above the 2-anchor ('somewhat specific but could overlap') because the domain is narrowly scoped.	3 / 3
	Total	11 / 12 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: 584939c

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.