/skill-creator
Create new AI agent skills for Claude Code, Codex, and Cursor. Use when asked to create a skill, add a new agent capability, or set up a slash command.
$ npx -y skills add stacklok/toolhive-studio --skill skill-creator --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/skill-creator
Context preview
The summary Claude sees to decide when to auto-load this skill.
Create new AI agent skills for Claude Code, Codex, and Cursor. Use when asked to create a skill, add a new agent capability, or set up a slash command.
SKILL.md
skill-creator.SKILL.mdname: skill-creator
description: Create new AI agent skills for Claude Code, Codex, and Cursor. Use when asked to create a skill, add a new agent capability, or set up a slash command.
Skill Creator
Create AI agent skills that work across Claude Code, Codex, and Cursor.
Workflow
1. **Claude is canonical** - Always create/edit in `.claude/skills/<name>/` first 2. **Replicate with CLI** - Copy to `.codex/skills/` and `.cursor/skills/` using `cp -r` 3. **Format differences** - Use `sed` only if agent-specific tweaks are needed (rare)
Directory Structure
.claude/skills/<skill-name>/
├── SKILL.md # Required - instructions + metadata
├── references/ # Optional - supporting documentation
├── scripts/ # Optional - executable helpers
└── assets/ # Optional - templates, resources
.codex/skills/<skill-name>/ # Copy of Claude's
.cursor/skills/<skill-name>/ # Copy of Claude's
SKILL.md Format
---
name: skill-name # Required: lowercase, hyphens, max 64 chars
description: What it does... # Required: triggers auto-selection by agent
allowed-tools: Read, Grep, Bash # Optional: Claude-specific (ignored by others)
model: claude-opus-4-5-20251101 # Optional: Claude-specific (ignored by others)
---
# Skill Title
Instructions in markdown...
Required Fields
- **`name`**: Lowercase with hyphens, must match directory name
- **`description`**: Explains what the skill does and when to use it. Include keywords users would say to help the agent auto-select this skill.
Optional Fields (Claude-specific, ignored by other agents)
- **`allowed-tools`**: Tools the agent can use without asking permission
- **`model`**: Override the model for this skill
- **`context: fork`**: Run in isolated subagent context
Creating a New Skill
1. Ask the user what the skill should do 2. Choose a descriptive name (lowercase, hyphens) 3. Create the Claude skill:
mkdir -p .claude/skills/<name>
4. Write `.claude/skills/<name>/SKILL.md` with proper frontmatter 5. Replicate to other agents:
cp -r .claude/skills/<name> .codex/skills/
cp -r .claude/skills/<name> .cursor/skills/
Modifying an Existing Skill
1. Edit `.claude/skills/<name>/SKILL.md` (canonical source) 2. Replicate changes:
cp .claude/skills/<name>/SKILL.md .codex/skills/<name>/
cp .claude/skills/<name>/SKILL.md .cursor/skills/<name>/
Best Practices
- Keep skills focused on a single capability
- Write clear descriptions with keywords for auto-discovery
- Use `references/` for lengthy documentation to keep SKILL.md concise
- Test the skill by asking the agent to perform the task
Read more
name: skill-creator description: Create new AI agent skills for Claude Code, Codex, and Cursor. Use when asked to create a skill, add a new agent capability, or set up a slash command.
Skill Creator
Create AI agent skills that work across Claude Code, Codex, and Cursor.
Workflow
1. **Claude is canonical** - Always create/edit in `.claude/skills/<name>/` first 2. **Replicate with CLI** - Copy to `.codex/skills/` and `.cursor/skills/` using `cp -r` 3. **Format differences** - Use `sed` only if agent-specific tweaks are needed (rare)
Directory Structure
.claude/skills/<skill-name>/ ├── SKILL.md # Required - instructions + metadata ├── references/ # Optional - supporting documentation ├── scripts/ # Optional - executable helpers └── assets/ # Optional - templates, resources .codex/skills/<skill-name>/ # Copy of Claude's .cursor/skills/<skill-name>/ # Copy of Claude's
SKILL.md Format
--- name: skill-name # Required: lowercase, hyphens, max 64 chars description: What it does... # Required: triggers auto-selection by agent allowed-tools: Read, Grep, Bash # Optional: Claude-specific (ignored by others) model: claude-opus-4-5-20251101 # Optional: Claude-specific (ignored by others) --- # Skill Title Instructions in markdown...
Required Fields
- **`name`**: Lowercase with hyphens, must match directory name
- **`description`**: Explains what the skill does and when to use it. Include keywords users would say to help the agent auto-select this skill.
Optional Fields (Claude-specific, ignored by other agents)
- **`allowed-tools`**: Tools the agent can use without asking permission
- **`model`**: Override the model for this skill
- **`context: fork`**: Run in isolated subagent context
Creating a New Skill
1. Ask the user what the skill should do 2. Choose a descriptive name (lowercase, hyphens) 3. Create the Claude skill:
mkdir -p .claude/skills/<name>
4. Write `.claude/skills/<name>/SKILL.md` with proper frontmatter 5. Replicate to other agents:
cp -r .claude/skills/<name> .codex/skills/ cp -r .claude/skills/<name> .cursor/skills/
Modifying an Existing Skill
1. Edit `.claude/skills/<name>/SKILL.md` (canonical source) 2. Replicate changes:
cp .claude/skills/<name>/SKILL.md .codex/skills/<name>/ cp .claude/skills/<name>/SKILL.md .cursor/skills/<name>/
Best Practices
- Keep skills focused on a single capability
- Write clear descriptions with keywords for auto-discovery
- Use `references/` for lengthy documentation to keep SKILL.md concise
- Test the skill by asking the agent to perform the task
Run any Model Context Protocol (MCP) server — securely, instantly, anywhere. ToolHive is the easiest way to discover, deploy, and manage MCP servers. Launch any MCP server in a locked-down container with just a few clicks.
Repo: stacklok/toolhive-studio
Other skills on toolhive-studio.
- /bug-fix-tdd
Reproduce and fix bugs using TDD. Use when analyzing a bug report, writing a regression test, or applying a minimal fix. Covers test placement, mock patterns, and the red-green-refactor workflow for automated bug fixing.
Open skill - /deep-links
Deep links in ToolHive Studio. Use when implementing, debugging, or asking about deep link features (toolhive-gui:// protocol), adding new deep link intents, understanding the deep link architecture, IPC model, or platform/packaging support.
Open skill - /devcontainer-dev
Spin up and interact with ToolHive Studio's containerized dev environment (Xvfb + noVNC + DinD). Use when running, testing, or debugging the app in isolation — locally, in a git worktree, or in GitHub Codespaces; when touching `.devcontainer/*`, `scripts/devcontainer-*.sh`, or
Open skill - /security-vuln-remediation
Remediate security vulnerabilities found by Grype or pnpm audit. Use when a security scan fails, a CVE needs fixing, or you need to analyze, upgrade, override, or ignore a vulnerable dependency.
Open skill - /skill-editor
REQUIRED for editing any skill file. Ensures changes sync to Claude, Codex, and Cursor. Never edit .claude/skills/ files directly - always use this skill.
Open skill - /testing-api-assertions
Verify API requests in tests. Use when testing that correct API calls are made for create, update, or delete operations. Use when testing mutations, form submissions, or actions with backend side effects.
Open skill

