testing

Skill: testing

Quality

38%

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/testing/SKILL.md

Quality

Content

77%

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 dense, highly actionable testing playbook with concrete commands, named APIs, explicit thresholds, and a clearly sequenced coverage workflow with validation feedback loops. Its main weakness is conciseness (a redundant Quick Reference) and the absence of progressive disclosure via separate bundle files.

Suggestions

Trim or remove the 'Quick Reference' section, which duplicates Core Rules and pass thresholds already stated above, to lift conciseness.

Move the per-package rules (autoformat, markdown, core, slate, etc.) into a references/ file and link to it from the body, splitting the monolithic 246-line file.

Lead the body with a 3-4 line summary of the three-layer goal and the default inner-loop command before the hard constraints, so the overview reads first.

Dimension	Reasoning	Score
Conciseness	The body is dense, bullet-driven, and assumes Claude's competence with no basic-concept padding, but the closing 'Quick Reference' section re-states many Core Rules and pass thresholds already covered above, so it is mostly efficient yet could be tightened.	2 / 3
Actionability	It gives fully executable commands and concrete thresholds throughout ('bun run test', 'pnpm test:slowest -- --top 25 --rerun-each 3', '60ms/test or 120ms/file', 'tooling/config/test-suites.mjs') plus specific APIs (createEditor -> createSlateEditor -> createPlateEditor), matching the copy-paste-ready anchor.	3 / 3
Workflow Clarity	The Coverage Strategy lays out a clear pass sequence (>=6 pass, rerun coverage, >=5 follow-up, architecture-safety pass) with explicit validation checkpoints (bun run test:profile, pnpm test:slowest hard gate) and a feedback loop that fixes the warning zone before it becomes a CI failure.	3 / 3
Progressive Disclosure	There are no bundle files (references/, scripts/, assets/ are absent) and the 246-line body is a single well-sectioned file; package-specific rules and the Quick Reference are inline content that could be split out, so it is organized but monolithic rather than overview-plus-references.	2 / 3
	Total	10 / 12 Passed

Description

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 a bare two-word label with no capabilities, trigger terms, or use-when guidance, scoring the minimum across every dimension. It would neither help a user recognize the right moment nor distinguish this skill from others.

Suggestions

Add concrete actions, e.g. 'Guides test-suite structure toward unit, contract, and golden tests and ranks coverage hotspots from lcov.'

Append an explicit trigger clause, e.g. 'Use when adding tests, restructuring test coverage, or deciding which seams to test in a Plate/Slate codebase.'

Include natural user keywords like 'test suite', 'coverage', 'flaky tests', 'bun test', and 'slow lane' so the skill triggers on real requests.

Dimension	Reasoning	Score
Specificity	The description is literally 'Skill: testing', which names the domain but lists no concrete actions, matching the vague/no-actions anchor ('Helps with documents') rather than the score-2 anchor that names some actions.	1 / 3
Completeness	It states neither what the skill concretely does nor when to use it, and lacks any 'Use when...' clause; the rubric caps completeness at 2 only when 'when' is implied, which it is not here.	1 / 3
Trigger Term Quality	Only the single generic word 'testing' appears; there are no natural trigger phrases a user would say (e.g., 'test suite', 'coverage', 'flaky tests'), so it falls in the no-natural-keywords tier rather than the some-relevant-keywords tier.	1 / 3
Distinctiveness Conflict Risk	'Skill: testing' is maximally generic and would overlap with countless other skills, matching the 'very generic; would conflict with many skills' anchor; it is not the somewhat-specific score-2 case.	1 / 3
	Total	4 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
description_field	'description' is very short (14 chars), consider making it more detailed	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	13 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/testing/SKILL.md
Commit: 45116fd

Reviewed: about 13 hours 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.