Skip to content
TrustedSkillsbeta
Back to all skills

Reading Withholding

Checked
kazukinagata·vlatest·other·MIT

This skill analyzes text for subtle withheld information or implied meanings, revealing deeper layers of intent and potential subtext.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add kazukinagata/shinkoku --skill reading-withholding -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

kazukinagata

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned kazukinagata/shinkoku at 607574d5e5.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
607574d5e5
Manifest
skills/reading-withholding/SKILL.md
Scanned
2 files, 138 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

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.