create-skill

Create a new Claude Code agent skill with proper folder structure and SKILL.md format. Use when the user wants to add a model-invoked skill that Claude uses autonomously based on context. Handles skill folder creation with SKILL.md and optional reference files.

Quality

75%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/claude-code-dev/skills/create-skill/SKILL.md

Quality

Discovery

85%

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 articulates what the skill does and when to use it. It uses third person voice correctly and provides specific, concrete actions. The main weakness is that trigger terms could include more natural variations of how users might request skill creation.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Create a new Claude Code agent skill', 'proper folder structure', 'SKILL.md format', 'skill folder creation with SKILL.md and optional reference files'. These are concrete, actionable capabilities.	3 / 3
Completeness	Clearly answers both what ('Create a new Claude Code agent skill with proper folder structure and SKILL.md format') and when ('Use when the user wants to add a model-invoked skill that Claude uses autonomously based on context').	3 / 3
Trigger Term Quality	Includes relevant terms like 'skill', 'SKILL.md', 'agent skill', 'Claude Code', but misses common variations users might say such as 'new skill', 'add skill', 'skill template', or 'skill file'.	2 / 3
Distinctiveness Conflict Risk	Very specific niche targeting Claude Code skill creation with distinct triggers like 'SKILL.md', 'agent skill', 'model-invoked skill'. Unlikely to conflict with general file creation or documentation skills.	3 / 3
	Total	11 / 12 Passed

Implementation

64%

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

This skill provides excellent actionable guidance with concrete examples and clear formatting requirements. However, it could benefit from a clearer step-by-step creation workflow with validation checkpoints, and the lengthy inline example could be moved to a reference file to improve conciseness and progressive disclosure.

Suggestions

Add an explicit numbered workflow: 1. Create skill folder, 2. Create SKILL.md with frontmatter, 3. Validate frontmatter fields, 4. Add body content, 5. Test skill invocation

Move the full 'conventional-commits' example to a separate file (e.g., examples/conventional-commits.md) and reference it instead of embedding inline

Add a validation checklist: 'Before committing: verify name is kebab-case, description includes trigger conditions, frontmatter parses correctly'

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some redundant explanations. The 'Bad Description Examples' section explains obvious concepts, and the full conventional-commits example skill could be shortened or referenced externally rather than embedded inline.	2 / 3
Actionability	Provides fully concrete, copy-paste ready examples including complete folder structures, YAML frontmatter, markdown templates, and a full working example skill. The format tables and code blocks are immediately executable.	3 / 3
Workflow Clarity	The skill describes what to create but lacks explicit sequencing for the creation process. There's no step-by-step workflow like '1. Create folder, 2. Create SKILL.md, 3. Validate frontmatter' and no validation checkpoints to verify the skill was created correctly.	2 / 3
Progressive Disclosure	Content is reasonably organized with clear sections, but the full example skill embedded inline (conventional-commits) bloats the main file. This could be referenced as a separate file. The skill mentions subfolders but doesn't link to actual reference materials.	2 / 3
	Total	9 / 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: jpoutrin/product-forge
Commit: 0ebe7ae

Reviewed: 29 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.