Skill Builder
CheckedSkill Builder by jwynia allows you to easily create and customize AI agent skills for streamlined workflows and automated tasks.
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 jwynia/agent-skills --skill skill-builder -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
jwynia
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 jwynia/agent-skills at e02ec7e226.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- e02ec7e226
- Scanned
- 6 files, 2,965 lines
About this skill
The skill-builder allows AI agents to dynamically discover, install, and manage additional capabilities from a registry. It enables agents to expand their functionality on-demand by integrating new tools or logic modules without requiring manual code updates.
When to use it
- Deploying an agent that needs to adapt to changing task requirements over time.
- Creating modular systems where core logic remains stable while specific features are swapped out.
- Building agents that must access specialized libraries or APIs not included in the base environment.
- Automating the setup of complex workflows by chaining together multiple distinct skills.
Key capabilities
- Dynamic Discovery: Automatically locates available skills within a configured registry.
- On-Demand Installation: Fetches and installs new skill modules directly into the agent's runtime.
- Modular Architecture: Supports swapping individual components to alter agent behavior without redeploying the whole system.
Example prompts
- "Install the 'data-analyzer' skill so I can process CSV files."
- "Discover all available skills for web scraping and install the most efficient one."
- "Update my current configuration by adding a new translation module from the registry."
Tips & gotchas
Ensure your agent has network access to the skill registry URL, as installation requires fetching external resources. Be mindful of version compatibility; installing a skill that conflicts with existing dependencies may cause runtime errors.