test-prompt

Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

62%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.

Highly actionable and well-sequenced with strong validation feedback loops, but the single-file monolith is verbose and repeats content, hurting token efficiency and progressive disclosure. Splitting examples and reference tables into separate files and trimming redundant walkthroughs would lift both weak dimensions.

Suggestions

Split the long worked Example ('Testing a Command') and the Quick Reference table into separate reference files linked from SKILL.md to improve progressive_disclosure.

Remove the duplicate Prompt Types / Quick Reference table and tighten the repeated RED/GREEN/REFACTOR prose to reduce token bloat for conciseness.

Condense explanatory preamble that restates TDD concepts Claude already knows, keeping only the prompt-testing-specific framing.

Dimension	Reasoning	Score
Conciseness	At ~715 lines the body is noticeably verbose, with repeated coverage (the Prompt Types table is restated in the Quick Reference table) and padded example walkthroughs that assume little of Claude's intelligence.	2 / 5
Actionability	Fully executable guidance throughout: concrete Task-tool invocation snippets, copy-paste-ready scenario prompts, and worked commit-command examples covering the common cases.	5 / 5
Workflow Clarity	Clear RED-GREEN-REFACTOR sequence with explicit validation checkpoints, re-test feedback loops ('If new failures appear: revert'), and per-phase checklists for complex processes.	5 / 5
Progressive Disclosure	A single monolithic SKILL.md with no bundle files and no external references; large blocks (worked examples, quick-reference tables) that could live in separate files are inlined and buried.	2 / 5
	Total	14 / 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 description that clearly states the trigger ('Use when creating or editing any prompt'), enumerates concrete target types, and ties the method to RED-GREEN-REFACTOR. Minor room to add more natural synonyms and sharpen the niche boundary.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('creating or editing any prompt', enumerates commands, hooks, skills, subagent instructions) and a concrete method ('RED-GREEN-REFACTOR cycle' via subagents), with only minor gaps in coverage.	4 / 5
Completeness	Explicitly answers both what ('verify it produces desired behavior') and when ('Use when creating or editing any prompt...') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('creating or editing any prompt', 'commands, hooks, skills, subagent instructions', 'testing') though a few lay synonyms are absent and the TDD jargon is somewhat specialized.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (testing prompts via subagents) mostly distinct from prompt-writing skills, with only minor overlap risk against the related test-skill.	4 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (715 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: NeoLabHQ/context-engineering-kit
Path: plugins/customaize-agent/skills/test-prompt/SKILL.md
Commit: c346eee

Reviewed: 5 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.