testing

Skill: testing

1.53x

Quality

53%

Does it follow best practices?

Impact

92%

1.53x

Average score across 3 eval scenarios

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

82%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 body is a highly actionable, well-structured testing policy skill: concrete commands, explicit thresholds and file paths, a sequenced coverage-pass workflow with feedback loops, and a useful Quick Reference. Its main weaknesses are mild internal redundancy and per-package sections that slightly overstay a single overview file.

Suggestions

De-duplicate the seam hierarchy and the >=6/>=5 pass strategy so each appears once in its primary section, with Quick Reference pointing back rather than restating.

Consider moving the lengthy per-package rules (autoformat, markdown, ai, core, selection, docx, slate) into a referenced PACKAGE_RULES.md to keep SKILL.md a lean overview.

Tighten the duplicated createSlateEditor usage lists in 'Seam Selection' and the 'core' package section so the canonical list lives in one place.

Dimension	Reasoning	Score
Conciseness	The body is dense, imperative, and assumes competence (naming Plate/Slate/Bun APIs without explaining them); it earns a 4 rather than 5 because of mild redundancy, e.g. the seam hierarchy and the >=6/>=5 pass strategy each recur in both their section and Quick Reference.	4 / 5
Actionability	It provides exact copy-paste commands and thresholds ('bun run test', 'pnpm test:slowest -- --top 25 --rerun-each 3', '60ms/test or 120ms/file', '*.spec.ts[x]') plus specific file paths, fully actionable and covering the common cases.	5 / 5
Workflow Clarity	The coverage process is clearly sequenced into passes with feedback loops ('rerun coverage', 'fresh lcov after each pass', 'use coverage after each phase to choose the next hotspot') and a stop criterion; it is a 4 not 5 because the checkpoints are strategy-level rather than a strict validate->fix->retry gate.	4 / 5
Progressive Disclosure	The body is well-organized into clearly headed sections (Testing Goal, Coverage Strategy, Core Rules, Seam Selection, Package Rules, Reviewed Exceptions, Quick Reference) with no nested references; it is a 4 rather than 5 because the long per-package rule sections could plausibly be split into reference files and no bundle files exist to leverage one-level-deep disclosure.	4 / 5
	Total	17 / 20 Passed

Description

25%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 'Skill: testing' is far too minimal: it names a domain but provides no concrete actions, no natural trigger phrases, and no 'Use when' guidance, giving it low specificity, trigger quality, and completeness. It also has high conflict risk because 'testing' is generic.

Suggestions

Rewrite the description to list concrete actions, e.g. 'Writes and maintains Plate/Slate test suites across fast and slow lanes, ranks coverage hotspots, and selects the smallest proving seam.'

Add an explicit 'Use when...' clause with natural trigger phrases such as 'adding tests', 'improving coverage', 'fixing flaky slow specs', or 'choosing a test seam'.

Narrow the niche with specific terms (Bun, Plate/Slate, lcov hotspot ranking) to reduce overlap with other testing skills.

Dimension	Reasoning	Score
Specificity	The description is just 'Skill: testing', which names the domain but states no concrete actions or verbs, fitting the 'names the domain but actions are minimal or generic' anchor rather than score 1 because a concrete domain is at least identified.	2 / 5
Completeness	It offers only a vague 'what' (the bare word 'testing') and no 'when'/Use-when guidance at all, matching the 'has a vague what and no when' anchor; it is not a 1 because a domain is named.	2 / 5
Trigger Term Quality	It contains a single generic keyword ('testing') and lacks the natural phrases a user would actually say, matching the 'one or two generic keywords; missing the natural phrases users say' anchor.	2 / 5
Distinctiveness Conflict Risk	'testing' is extremely broad and would overlap with many other testing-related skills, matching the 'very broad; high overlap risk with many similar skills' anchor rather than 1 because it is a single coherent domain rather than two unrelated ones.	2 / 5
	Total	8 / 20 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: d76efae

Reviewed: 3 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.