skill-creator
The skill-creator provides a structured workflow for developing, testing, and refining AI agent skills. It guides users through intent capture, skill drafting, iterative evaluation using subagents, and performance benchmarking.
Is skill-creator safe to install?
Review the source first: our audit of skill-creator's source files found 2 shell commands, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes shell commands to run benchmarks and launch local servers for evaluation viewers. It also performs file system operations to create directories, save test outputs, and manage skill snapshots.
How we audit skills: our security review methodology.
Who is this skill for?
Users who want to create, edit, or optimize AI agent skills, ranging from those new to coding to experienced developers.
What can you do with it?
- Drafting new skill definitions and instructions
- Iteratively improving existing skills based on performance data
- Running comparative evaluations between skill versions
- Generating quantitative benchmarks and qualitative reviews for skill performance
- Optimizing skill descriptions to improve triggering accuracy
How good is this skill?
Quality score: 5/10. The skill provides a comprehensive, well-documented workflow for the entire lifecycle of AI agent skill development. It includes specific instructions for directory structure, evaluation methodology, and data handling.
What does the skill file contain?
# Skill Creator A skill for creating new skills and iteratively improving them. At a high level, the process of creating a skill goes like this: - Decide what you want the skill to do and roughly how it should do it - Write a draft of the skill - Create a few test prompts and run claude-with-access-to-the-skill on them - Help the user evaluate the results both qualitatively and quantitatively - While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). ...
Frequently asked questions
Does this skill automatically write the code for my new skill?
No. The skill assists in drafting the SKILL.md file and structure based on your intent, but it requires your input and iteration to finalize the content.
How does the skill evaluate performance?
It runs comparative tests using subagents (with and without the skill), captures timing data, grades assertions, and aggregates results into a benchmark report for review.
Can I use this to test skills that involve subjective outputs?
Yes. The workflow supports qualitative evaluation alongside quantitative benchmarks for skills where objective assertions are not applicable.
Related skills
find-skills
2.3MUsers seeking to extend agent capabilities with specialized tools, workflows, or knowledge packages
The find-skills skill enables agents to search for, discover, and install modular packages from the open agent skills ecosystem using the Skills CLI.
agent-browser
506.7KAI agents and developers requiring programmatic web interaction, exploratory testing, or automation of Electron desktop applications
The agent-browser CLI provides browser automation for AI agents using Chrome or Chromium via CDP. It supports page navigation, form interaction, data extraction, and testing. The tool utilizes accessibility-tree snapshots and element references for interaction.
image-to-video
355.0KDevelopers and users who need to automate video generation from images using the RunComfy platform
The image-to-video skill routes user requests to specific RunComfy animation models based on intent. It selects HappyHorse 1.0 I2V for general animation, Wan 2.7 for custom-voiceover lip-sync, or Seedance 2.0 Pro for multi-modal composition. The skill executes the RunComfy CLI to process inputs and download generated video files.
video-edit
338.7KUsers of the RunComfy CLI who need to automate video editing tasks like restyling, background swapping, or motion transfer
The video-edit skill acts as a router for the RunComfy CLI, selecting between Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, and Lucy Edit Restyle models based on user intent to perform video transformations.