Agent skill
load-skill
Load, activate, and optionally install an AI skill from a .skill file. Use this skill when the user wants to load, activate, or use a skill file. The user can invoke this skill with slash command `/load-skill [ --install | -i ] SKILLFILE`, where SKILLFILE is the path to a .skill file.
Install this agent skill to your Project
npx add-skill https://github.com/fpl9000/ai-skills/tree/main/load-skill
SKILL.md
Load Skill
This skill loads, activates, and optionally installs another skill from a .skill file. Here's a screenshot of it being used in Claude Code, but it will work similarly in other AI agents.
Usage
/load-skill [ --install | -i ] SKILLFILE
Where:
SKILLFILEis the path to a.skillfile (a ZIP archive containing skill content).--installor-i(optional) installs the skill permanently without prompting the user.
How to Process This Skill
When this skill is invoked, you (the AI agent) should:
-
Parse the arguments: Extract the skill file path and any switches from the arguments provided. If
--installor-iis present, note that the skill should be installed without prompting. If no path is provided, ask the user for the path to the skill file. -
Validate the file: Verify the file exists and has a
.skillextension. -
Extract the skill: Use
unzipto extract the skill to a temporary directory. Use a command like:bashunzip -o "SKILLFILE" -d "TEMPDIR" -
Locate SKILL.md: Find the
SKILL.mdfile in the extracted contents. It may be at the root level or inside a subdirectory (depending on how the skill was packaged). -
Read the skill: Read the entire
SKILL.mdfile to understand the skill's capabilities and instructions. -
Install the skill (if requested): If the
--installor-iswitch was provided and your AI system has a designated skills folder where skills can be permanently installed, copy the extracted skill folder there. This makes the skill available in future sessions without needing to reload it. Do not prompt the user; proceed with installation automatically. -
Activate the skill: Follow the instructions in the loaded skill's
SKILL.mdas if it had been invoked directly. The loaded skill is now active for the remainder of the conversation. -
Clean up: After activating the skill, you may delete the temporary extraction directory.
Examples
User: /load-skill ./my-custom.skill
Agent: [Extracts skill, reads SKILL.md, activates skill]
User: /load-skill --install ./my-custom.skill
Agent: [Extracts skill, reads SKILL.md, installs skill, activates skill]
Notes
-
The
.skillfile format is a ZIP archive as defined by the Agent Skills specification at https://agentskills.io. -
If the skill file contains scripts in a
scripts/directory, those scripts become available for use per the loaded skill's instructions. -
If the skill file contains references in a
references/directory, read those files as needed for additional context. -
If the skill requires environment variables or prerequisites, inform the user before proceeding.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
bluesky
Read from and post to Bluesky social network using the AT Protocol. Use this skill when the user wants to interact with Bluesky including posting text/images/links, replying to posts, reading their timeline, searching posts, viewing profiles, following/unfollowing users, checking notifications, or viewing reply threads. All scripts use PEP 723 inline metadata for dependencies and run via `uv run`. Requires BLUESKY_HANDLE and BLUESKY_PASSWORD environment variables.
ai-messaging
Communicate with the local stateful agent system via the GitHub relay. Use this skill when the user wants to interact with their local machine remotely — reading memory files, running shell commands, or delegating tasks to the local Claude Desktop agent. Triggers include phrases like: "on my local machine", "check my local files", "run this on my home computer", "ask my local Claude", "read my memory files", "what's in my core memory", "what's on my home machine", "run this locally". Requires the github skill for relay transport scripts.
github
Access GitHub repositories via the GitHub REST API. Use this skill when the user wants to interact with GitHub including reading files, creating/updating files, listing repos, managing branches, viewing commits, working with issues, or managing pull requests. All scripts use PEP 723 inline metadata for dependencies and run via `uv run`. Requires GITHUB_TOKEN environment variable (a Personal Access Token with appropriate scopes).
drawio
Generate draw.io diagrams programmatically using Python. Creates flowcharts, architecture diagrams, tree structures, network diagrams, and more. Use when the user requests a .drawio file, diagram, flowchart, or visual documentation.
transcript-saver
Save and export the current Claude Code session as a shareable HTML transcript. Use this skill when the user asks to save, export, archive, or publish their current Claude Code conversation or session. Triggers on phrases like "save this transcript", "export this session", "create a transcript", "archive this conversation", "publish to gist", or "share this session". Wraps Simon Willison's claude-code-transcripts tool for in-session use.
edit-article
Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
Didn't find tool you were looking for?