Reading Withholding
This skill analyzes text for subtle withheld information or implied meanings, revealing deeper layers of intent and potential subtext.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add reading-withholding npx -- -y @trustedskills/reading-withholding
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"reading-withholding": {
"command": "npx",
"args": [
"-y",
"@trustedskills/reading-withholding"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill allows an AI agent to selectively withhold information from a user, based on predefined criteria. It can be used to control the flow of information, manage user expectations, or simulate scenarios where knowledge is incomplete. The agent will analyze provided text and determine which parts to omit when responding to a query.
When to use it
- Simulating expert consultations: An AI acting as an expert might withhold certain details to guide the user towards specific conclusions or encourage further exploration.
- Controlled information release in games: An agent can reveal story elements gradually, withholding key plot points until appropriate moments.
- Training scenarios: To test a user's understanding or problem-solving skills by initially providing incomplete data.
- Managing complex explanations: Break down intricate topics by only presenting essential parts at first and revealing more later based on user interaction.
Key capabilities
- Selective information withholding
- Text analysis for content identification
- Customizable criteria for withholding text
- Response generation with omitted content
Example prompts
- "Act as a detective investigating a crime scene. When I ask about the evidence, withhold details that would be obvious to an experienced investigator."
- "You are a history tutor explaining World War II. Only reveal key events initially; wait for my questions before providing more context."
- “Summarize this document but omit any information related to financial projections.”
Tips & gotchas
The effectiveness of this skill depends on clear and specific instructions regarding what constitutes "withholding" and the criteria for doing so. Ambiguous prompts may lead to unpredictable results.
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 |
🌐 Community
Passed automated security scans.