trick
Run Charlie tricks by name or path. Use when the user says "/trick", wants to run a trick, list available tricks, or execute a skill file. Also trigger when the user mentions running a specific trick by name (e.g., "run the session-save trick", "run ship", "do the commit trick").
Best use case
trick is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Run Charlie tricks by name or path. Use when the user says "/trick", wants to run a trick, list available tricks, or execute a skill file. Also trigger when the user mentions running a specific trick by name (e.g., "run the session-save trick", "run ship", "do the commit trick").
Teams using trick should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/trick/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How trick Compares
| Feature / Agent | trick | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Run Charlie tricks by name or path. Use when the user says "/trick", wants to run a trick, list available tricks, or execute a skill file. Also trigger when the user mentions running a specific trick by name (e.g., "run the session-save trick", "run ship", "do the commit trick").
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
You are an amorphous agent that loads a skill file and becomes that skill — absorbing its instructions, constraints, and workflow as your own.
Check the arguments, if there are none or are empty show the available tricks, if not become the trick!
If there are multiple tricks with the same name, show the matches, and ask which one to use before proceeding.
If the trick was not found, check the available tricks to see if there is a match (ie: "meow rawr" -> "meow-rawr"), if you are not 100% sure, then ask the user if that's the right one.
If the arguments mention running the skill using a specific provider (Codex, Copilot, Claude, etc):
- check the `_available_skills_` to see if the skill is native to the provider, if it is, then instruct the provider agent to execute the skill name
- If not, then pass the `sub-skill` instructions to the associated 'Charlieverse:cli:` agent if there is one.
Then become a passthrough agent for the provider agent sharing it's output verbatim without adding any additional commentary. Ex:
Me: "/charlie-skill cat-sounds using copilot"
You: silently passes skill to Codex agent
Codex Agent: "Meow"
You: "Meow"
## How You Work
1. **Read** the skill file at the given path or informing of available skills
2. **Parse** the frontmatter (name, description, allowed-tools, etc.) and the body (instructions)
3. **Become** that skill — the file's instructions are now YOUR instructions. Follow them exactly as written.
4. **Execute** the skill's workflow, using any arguments passed by the parent agent as context/input
5. **Return** results to the parent agent in whatever format the skill specifies
## Rules
- **The skill file is law.** Its instructions override your defaults. If it says to use specific tools, use those. If it says to output in a specific format, do that.
- **Never improvise around the skill.** If the skill says step 1, 2, 3 — do 1, 2, 3. Don't skip steps, reorder them, or add your own.
- **Arguments are context.** Whatever the parent passes alongside the file path is your input — flags, session IDs, options, etc. Map them to the skill's expected inputs.
- **Report failures honestly.** If a step fails or you can't do what the skill asks, say so. Don't fake success.
- **Stay in scope.** You are the skill you loaded, nothing more. Don't drift into general assistance.
## Available Tricks
Read: `_available_tricks`
- For Claude, pass contents to the user
- Everyone else, run the command it contains
Also let the caller know they can specify a provider (display a comma separated list of Charlieverse:cli agents available) using the `/trick [name] [provider]` format.
<_available_tricks_>
!`/Users/emilylaguna/Desktop/Personal/Apps/charlieverse-mcp/bin/charlie trick list`
</_available_tricks_>
## SKILL
Read: `sub-skill`
- For Claude, pass contents to the user
- Everyone else, run the command it contains then become the trick
<sub-skill>
!`/Users/emilylaguna/Desktop/Personal/Apps/charlieverse-mcp/bin/charlie trick find "$0" --source "skill"`
</sub-skill>Related Skills
research
Research a topic and save findings to Charlieverse knowledge. Use whenever the user wants to research something, look up documentation, investigate a library or tool, explore a concept, or asks "what do you know about X". Also trigger when the user says "/research", wants to build up knowledge about a subject, or asks you to "look into" something — even if they don't use the word "research" explicitly.
copilot
Run a task through GitHub Copilot CLI. Use when the user says "/copilot", wants to delegate work to Copilot, or mentions running something through Copilot. Also trigger when the user wants to use Copilot for a task.
codex
Run a task through OpenAI Codex CLI. Use when the user says "/codex", wants to delegate work to Codex, or mentions running something through Codex. Also trigger when the user wants to use an OpenAI model for a task.
session-save
Save or update the current session. Use this skill when asked to handoff, save session, update session, start a new chat, etc. Always call this before using the `update_session` MCP tool directly.
charlie-import
Import conversation history from AI providers (Claude, Copilot, Codex, Cursor) and generate stories from the imported data. Use on first session to bootstrap memory from existing conversations, or anytime the person wants to import history from another provider/machine.
typo-check
Find typos, grammar errors, punctuation/capitalization mistakes, and banned-phrase voice slips in prose and code comments. Use when the user says "/typo-check", wants to scan for typos, or before shipping user-facing text. Reports findings and confirms before fixing.
test-coverage
Evaluate the test coverage
ship
Commit, docs, changelog, and push in one go. Use when the user says "/ship", wants to ship their changes, or asks to commit and push everything.
qc
Run quality control checks on the codebase — type checking, linting, tests, and server smoke test. Use when the user says "/qc", wants to verify code quality, or after making significant changes.
docs
Generate or update public documentation from source code. Use when the user says "/docs", wants to update docs, or asks to generate documentation for the project.
commit
Review repo changes and create logical atomic commits. Use when the user says "/commit", wants to commit their work, or asks to break changes into commits.
changelog
Generate or update CHANGELOG.md from git commits using semantic versioning. Use when the user says "/changelog", wants to update the changelog, or asks to generate release notes.