Skill Create
CheckedSourman's skill-create generates custom AI agent skills based on user prompts, defining purpose, inputs, and outputs.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add sourman/skills --skill skill-create -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
sourman
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned sourman/skills at 5f81b5e23f.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 5f81b5e23f
- Manifest
- skill-create/SKILL.md
- Scanned
- 1 file, 199 lines
About this skill
skill-create
What it does
This foundational agent capability enables the creation of new skills, allowing users to define custom functionalities and extend an AI agent's operational scope. It serves as the primary mechanism for building reusable logic blocks that agents can execute to perform specific tasks.
When to use it
- You need to add a specialized function to your agent that isn't covered by default capabilities.
- You want to standardize a recurring task across multiple different AI workflows.
- You are developing a custom toolset for an enterprise environment with unique compliance or data handling requirements.
- You wish to modularize complex logic into smaller, testable units for better maintainability.
Key capabilities
- Defining new functional blocks for AI agents
- Extending standard agent behavior with custom logic
- Creating reusable components for workflow automation
- Establishing the foundation for specialized task execution
Example prompts
- "Create a skill that summarizes long documents into bullet points while preserving key dates and names."
- "Define a new capability to automatically format raw JSON data into readable Markdown tables."
- "Build a custom tool that cross-references user input against a specific internal knowledge base and returns relevant citations."
Tips & gotchas
Ensure you clearly define the input parameters and expected output format for any skill you create to prevent ambiguity during execution. Test new skills in a sandbox environment first to verify they integrate correctly with your agent's existing workflow before deploying them broadly.