test-skill

Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

1.92x

Quality

76%

Does it follow best practices?

Impact

100%

1.92x

Average score across 1 eval scenario

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/customaize-agent/skills/test-skill/SKILL.md

Quality

Content

70%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 well-sequenced, actionable testing workflow with strong validation checkpoints, undermined by length and redundancy. The single monolithic file and missing referenced bundle files leave navigation and progressive disclosure as the weakest areas.

Suggestions

Remove the duplicated TDD-mapping table and fold the 'Bottom Line'/'Real-World Impact' sections into existing content to cut roughly 30-40 lines of repetition.

Move the full worked example (the 'Example: TDD Skill Bulletproofing' section) and the extended rationalization/pressure-type catalogs into separate referenced files so SKILL.md stays an overview.

Create the referenced bundle files (e.g. references/CLAUDE_MD_TESTING_EXAMPLE.md and references/persuasion-principles.md) or remove the dangling references so signaled links resolve.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded: the TDD-mapping table is duplicated (lines 39-47 and 384-391), and the 'Bottom Line' and 'Real-World Impact' sections restate the overview rather than adding new guidance.	3 / 5
Actionability	Provides concrete, copy-paste-ready pressure-scenario templates plus explicit formats for rationalization tables, red flags, and meta-testing prompts, with only minor gaps around how many scenarios to run or how to select target skills.	4 / 5
Workflow Clarity	The RED -> Verify RED -> GREEN -> Verify GREEN -> REFACTOR -> Re-verify sequence is explicit, with feedback loops (re-test on failure, continue REFACTOR on new rationalizations) and a consolidated Testing Checklist.	5 / 5
Progressive Disclosure	Two one-level references are signaled ('examples/CLAUDE_MD_TESTING.md', 'persuasion-principles.md'), but no bundle files exist and the ~400-line body keeps worked examples, pressure-type catalogs, and rationalization lists inline rather than split out.	3 / 5
	Total	15 / 20 Passed

Description

83%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 strong, mostly concrete description that clearly states both purpose and trigger conditions with a recognizable meta-testing niche. Its main weakness is the broad 'creating or editing skills' trigger, which could fire for plain skill authoring rather than testing.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('running baseline without skill', 'writing to address failures', 'iterating to close loopholes', 'applies RED-GREEN-REFACTOR cycle'), with only minor coverage gaps such as capturing rationalizations or designing pressure scenarios.	4 / 5
Completeness	Explicitly answers both 'when' ('Use when creating or editing skills, before deployment') and 'what' ('verify they work under pressure and resist rationalization ... applies RED-GREEN-REFACTOR cycle') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ('creating or editing skills', 'before deployment', 'verify they work under pressure'), but misses common synonyms like 'testing skills', 'validating skills', or 'bulletproofing'.	4 / 5
Distinctiveness Conflict Risk	The verification/pressure-testing niche is fairly distinct, but the 'creating or editing skills' trigger overlaps with general skill-authoring skills, leaving minor conflict risk.	4 / 5
	Total	17 / 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: NeoLabHQ/context-engineering-kit
Path: plugins/customaize-agent/skills/test-skill/SKILL.md
Commit: 23e2428

Reviewed: 10 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.