Directives
This skill executes your commands directly, streamlining workflows and automating tasks for rapid action and efficiency.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add directives npx -- -y @trustedskills/directives
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"directives": {
"command": "npx",
"args": [
"-y",
"@trustedskills/directives"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill allows you to provide instructions and constraints to an AI agent, influencing its behavior and output. It enables specifying desired formats, tones, or limitations on responses. Essentially, it's about guiding the AI’s actions through precise commands.
When to use it
- Formatting Output: You need the AI to present information in a specific format like JSON, Markdown tables, or bulleted lists.
- Controlling Tone: You want the AI to respond with a particular tone – formal, informal, humorous, etc.
- Limiting Scope: You wish to restrict the AI's responses to a certain topic or exclude specific information.
- Defining Length Constraints: You need the AI to keep its answers within a defined word count or character limit.
Key capabilities
- Specifying output formats (e.g., JSON, Markdown)
- Controlling response tone and style
- Setting length constraints for responses
- Limiting topic scope
Example prompts
- "Respond in JSON format with the keys 'title' and 'description'."
- "Answer as if you were a friendly chatbot."
- "Summarize this article in under 100 words."
- "Only discuss topics related to astrophysics."
Tips & gotchas
The effectiveness of this skill depends on clear and specific instructions. Vague directives may lead to unpredictable results, so be precise with your requests.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🏢 Official
Published by the company or team that built the technology.