writing-skills

Creates, edits, and tests Claude skill files (SKILL.md) using TDD methodology with baseline pressure testing and rationalization defense. Use when writing a new skill, modifying an existing skill, optimizing a skill description for discovery (CSO), testing whether a skill triggers correctly, or structuring skill documentation. Enforces RED-GREEN-REFACTOR for process documentation.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

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 skill is highly actionable with clear sequenced workflows and concrete templates, but it is verbose through repetition and references several bundle files that are not present, weakening navigation.

Suggestions

Remove or merge the redundant TDD-framing sections ("The Iron Law", "The Bottom Line", and the repeated "skills ARE TDD" statements) into a single concise statement to tighten conciseness.

Fix broken references: either add the missing @graphviz-conventions.dot, render-graphs.js, @testing-skills-with-subagents.md, and anthropic-best-practices.md, or remove the citations to them so navigation is not dead-ended.

Consider moving the per-skill-type testing details and the full checklist into a reference file, leaving SKILL.md as a leaner overview that points one level deep.

Dimension	Reasoning	Score
Conciseness	The body restates the "skills ARE TDD" thesis repeatedly ("Writing skills IS Test-Driven Development", "The Iron Law", "The Bottom Line", "If you follow TDD for code, follow it for skills"), so it is mostly efficient but padded with redundant framing that could be tightened.	2 / 3
Actionability	Concrete templates (frontmatter, directory structures, the SKILL.md skeleton), a TodoWrite checklist with specific checkboxes, and per-skill-type testing approaches give executable, specific guidance rather than abstract direction.	3 / 3
Workflow Clarity	The RED-GREEN-REFACTOR cycle is explicitly sequenced with validation feedback loops ("Run same scenarios WITH skill", "Re-test until bulletproof") plus a checkpoint checklist, matching the top anchor.	3 / 3
Progressive Disclosure	Two references (cso-guide.md, rationalization-defense.md) are real and clearly signaled one level deep, but four referenced files (@graphviz-conventions.dot, render-graphs.js, @testing-skills-with-subagents.md, anthropic-best-practices.md) do not exist, and the ~430-line body is closer to monolithic than a lean overview.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 strong across all dimensions: concrete capabilities, natural trigger terms, an explicit Use-when clause covering what and when, and a distinct niche. No changes needed.

Dimension	Reasoning	Score
Specificity	"Creates, edits, and tests Claude skill files (SKILL.md)" lists multiple specific concrete actions, matching the top anchor rather than the vague mid-level domain-only example.	3 / 3
Completeness	It explicitly answers both what ("Creates, edits, and tests Claude skill files...") and when via an explicit "Use when..." clause enumerating triggers, so it is not the level-below where 'when' is only implied.	3 / 3
Trigger Term Quality	"writing a new skill", "modifying an existing skill", "optimizing a skill description for discovery (CSO)", "testing whether a skill triggers correctly" are natural phrases a user would actually say, with good coverage and no jargon-only filler.	3 / 3
Distinctiveness Conflict Risk	The niche — TDD-based skill authoring with "baseline pressure testing" and "rationalization defense" — has distinct triggers unlikely to collide with unrelated skills.	3 / 3
	Total	12 / 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: shousper/claude-kit
Path: skills/writing-skills/SKILL.md
Commit: ae181ef

Reviewed: about 3 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.