Skip to content
TrustedSkillsbeta
Back to all skills

Claudeception

Checked
blader·vlatest·ai-ml·MIT

Claudeception recursively prompts Claude to refine its own responses for enhanced clarity and detail – a powerful tool for iterative improvement.

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 blader/claudeception --skill claudeception -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

blader

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 blader/claudeception at 62dbb91d11.

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

Commit
62dbb91d11
Manifest
SKILL.md
Scanned
9 files, 932 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

The claudeception skill allows AI agents to generate deceptive or misleading text. It enables crafting prompts that intentionally produce false information, mimicking styles of deception, or creating scenarios where an agent must convincingly lie. This can be useful for testing robustness against adversarial attacks or exploring creative writing techniques.

When to use it

  • Red Teaming: Test the vulnerability of other AI systems by prompting deceptive content generation and evaluating their responses.
  • Creative Writing Exercises: Explore narrative structures involving deception, misdirection, and unreliable narrators.
  • Simulating Adversarial Scenarios: Create realistic training data for agents that need to detect or counter misinformation.
  • Ethical AI Research: Investigate the potential for misuse of generative models by experimenting with deceptive content generation in a controlled environment.

Key capabilities

  • Deceptive text generation
  • Mimicking deceptive writing styles
  • Generating false information
  • Creating scenarios involving lies and misdirection

Example prompts

  • "Write a news article claiming that [false event] happened, citing [fake source]."
  • "Compose an email pretending to be from [person/company], requesting [sensitive information]."
  • "Describe how to convince someone that [incorrect statement] is true."

Tips & gotchas

The skill should only be used for ethical and research purposes. Be mindful of the potential harm caused by generating deceptive content, and avoid using it to mislead or deceive others in real-world scenarios.