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

67%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/writing-skills/SKILL.md

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is comprehensive in scope but suffers significantly from verbosity and redundancy—the core TDD principle is restated at least 5 times, and sections like 'What is a Skill?' explain things Claude already knows. The actionability is moderate: good structural templates and checklists exist, but the actual testing methodology is deferred to missing bundle files. The workflow is present but lacks concrete validation criteria.

Suggestions

Cut the content by 40-50%: remove the 'What is a Skill?' section, the TDD mapping table (Claude knows TDD), repeated statements of the Iron Law, and the 'Bottom Line' section which just restates the overview.

Add a concrete, complete example of writing a skill end-to-end: show an actual pressure scenario prompt, an actual baseline failure output, the resulting skill content, and the passing test—not just abstract descriptions.

Include the referenced bundle files (cso-guide.md, rationalization-defense.md, testing-skills-with-subagents.md) or inline their critical content, since the skill defers key actionable details to files that don't exist in the bundle.

Define concrete validation criteria for the GREEN phase: what does 'agent complies' look like? Provide a scoring rubric or specific pass/fail conditions rather than the vague 'verify agents now comply.'

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~400+ lines. It explains concepts Claude already knows (what TDD is, what RED-GREEN-REFACTOR means, what a skill is), includes extensive tables mapping TDD concepts that are self-evident, and repeats the 'Iron Law' and core principle multiple times. The 'What is a Skill?' section and much of the TDD mapping table are unnecessary padding.	1 / 3
Actionability	The skill provides structural templates (YAML frontmatter format, directory structure) and a detailed checklist, which are concrete. However, it lacks executable code examples for the core task (actually writing/testing a skill), relies on pseudocode-level descriptions for pressure testing, and defers critical details to referenced files (rationalization-defense.md, cso-guide.md, testing-skills-with-subagents.md) that aren't provided in the bundle.	2 / 3
Workflow Clarity	The RED-GREEN-REFACTOR workflow is clearly sequenced and the checklist at the end provides good structure. However, validation checkpoints are vague ('run scenarios WITH skill - verify agents now comply') without specifying what compliance looks like or how to measure it. The skill also mentions the official skill-creator plugin for eval running but doesn't show how to use it, creating a gap in the verification workflow.	2 / 3
Progressive Disclosure	The skill references several supporting files (references/cso-guide.md, references/rationalization-defense.md, testing-skills-with-subagents.md, graphviz-conventions.dot, anthropic-best-practices.md) which suggests good intent for progressive disclosure. However, none of these files are provided in the bundle, making it impossible to verify they exist or contain useful content. The main file itself is monolithic with content that could be split out (anti-patterns, testing all skill types, flowchart usage).	2 / 3
	Total	7 / 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.

This is a strong skill description that clearly defines its niche around Claude skill file creation and testing. It excels in all dimensions: specific concrete actions, natural trigger terms, explicit 'Use when' guidance with multiple scenarios, and a distinctive domain that won't conflict with other skills. The description is concise yet comprehensive, using proper third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Creates, edits, and tests Claude skill files', 'baseline pressure testing', 'rationalization defense', 'optimizing a skill description for discovery (CSO)', 'testing whether a skill triggers correctly', 'structuring skill documentation', and 'RED-GREEN-REFACTOR for process documentation'.	3 / 3
Completeness	Clearly answers both 'what' (creates, edits, tests skill files using TDD with pressure testing and rationalization defense) and 'when' (explicit 'Use when...' clause listing five specific trigger scenarios: writing new skills, modifying existing ones, optimizing for discovery, testing triggers, and structuring documentation).	3 / 3
Trigger Term Quality	Includes strong natural trigger terms users would say: 'skill', 'SKILL.md', 'new skill', 'modifying an existing skill', 'skill description', 'discovery', 'CSO', 'triggers correctly', 'skill documentation', 'TDD'. These cover a good range of how users would phrase requests about skill file creation and testing.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche focused specifically on Claude skill files (SKILL.md) with TDD methodology. The combination of skill file management, CSO, pressure testing, and rationalization defense creates a very clear and unique domain unlikely to conflict with other 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: shousper/claude-kit
Commit: 08bc600

Reviewed: 14 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.