skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Quality

46%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./claude/skills/skill-creator/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 provides a reasonable framework for creating skills with a clear 6-step process and useful concrete commands, but it is significantly too verbose—spending many tokens explaining concepts Claude already understands (what PDFs are, what scripts do, what progressive disclosure means). The skill would benefit greatly from practicing its own advice: moving detailed reference material to separate files and keeping SKILL.md lean with only essential procedural instructions.

Suggestions

Cut the 'About Skills' section dramatically—move the anatomy/resource-type details to a references/skill-anatomy.md file and keep only a brief summary in SKILL.md, practicing the progressive disclosure the skill itself advocates.

Add a concrete example of a complete, well-written SKILL.md (even a short one) so Claude has a tangible template to follow, rather than just abstract questions to answer in Step 4.

Remove explanatory text that Claude already knows (e.g., what scripts/references/assets are conceptually) and replace with terse, imperative instructions focused on what's non-obvious.

Add explicit validation checkpoints between editing (Step 4) and packaging (Step 5), such as a checklist of common issues to verify before running the packaging script.

Dimension	Reasoning	Score
Conciseness	The skill is highly verbose, explaining concepts Claude already knows (what skills are, what scripts/references/assets are, the concept of progressive disclosure). Sections like 'What Skills Provide' and 'About Skills' are largely unnecessary background. The entire document could be cut by 50%+ while preserving all actionable content.	1 / 3
Actionability	There are concrete commands (init_skill.py, package_skill.py) and a clear directory structure, but much of the guidance is abstract advice rather than executable instructions. The 'Edit the Skill' section is particularly vague—it asks questions rather than providing concrete templates or examples of good SKILL.md content. No example of actual SKILL.md output is provided.	2 / 3
Workflow Clarity	The 6-step process is clearly sequenced and logically ordered, with some validation via the packaging script in Step 5. However, there's no explicit validation checkpoint between Steps 3-4 (editing) and Step 5 (packaging), and the iteration step (Step 6) lacks concrete guidance on what to check or how to evaluate skill quality. The feedback loop is mentioned but not structured with specific checkpoints.	2 / 3
Progressive Disclosure	The skill references scripts (init_skill.py, package_skill.py) but no bundle files are provided, so we can't verify those references. The SKILL.md itself is monolithic—all content is inline rather than split into reference files. The detailed anatomy section and resource type descriptions could be moved to a references file, keeping SKILL.md leaner, which would better practice what the skill preaches.	2 / 3
	Total	7 / 12 Passed

Description

57%

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 adequately communicates when to use the skill with explicit trigger guidance, but falls short on specificity—it reads more like a category label than a concrete capability list. The 'what' portion is too abstract ('guide for creating effective skills') without detailing the actual actions performed (e.g., generating templates, structuring YAML frontmatter, validating skill format).

Suggestions

Replace the vague 'Guide for creating effective skills' with specific actions like 'Generates skill markdown files with proper YAML frontmatter, description fields, and structured instructions'.

Add more natural trigger term variations such as 'SKILL.md', 'skill file', 'skill template', 'write a skill', 'custom workflow' to improve keyword coverage.

Clarify what concrete outputs or artifacts this skill produces to distinguish it from general documentation or instruction-writing skills.

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'creating effective skills' and 'extends Claude's capabilities with specialized knowledge, workflows, or tool integrations' without listing any concrete actions. It doesn't specify what the skill actually does (e.g., generates YAML frontmatter, writes markdown templates, validates skill structure).	1 / 3
Completeness	It explicitly answers both 'what' ('Guide for creating effective skills') and 'when' ('when users want to create a new skill or update an existing skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations'). The 'Use when' equivalent is clearly stated.	3 / 3
Trigger Term Quality	It includes some relevant trigger terms like 'create a new skill', 'update an existing skill', and 'skill' itself, which users might naturally say. However, it misses variations like 'SKILL.md', 'skill file', 'skill template', 'write a skill', or 'custom instruction'.	2 / 3
Distinctiveness Conflict Risk	The term 'skill' is fairly specific to this domain, reducing conflict risk. However, the vague mention of 'specialized knowledge, workflows, or tool integrations' could overlap with other meta-skills or documentation skills. It's somewhat distinguishable but not sharply defined.	2 / 3
	Total	8 / 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: einverne/dotfiles
Commit: b1b2fe0

Reviewed: 4 months 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.