Skip to content
TrustedSkillsbeta
Back to all skills

Decision Critic

Checked
akiselev·vlatest·other·Apache-2.0

The Decision Critic analyzes choices and provides insightful feedback on potential outcomes, aiding users in making more informed decisions.

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 akiselev/qt-llm-template --skill decision-critic -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

akiselev

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 akiselev/qt-llm-template at 6855e82e0c.

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

Commit
6855e82e0c
Manifest
.claude/skills/decision-critic/SKILL.md
Scanned
3 files, 92 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 decision-critic skill provides feedback on the quality of decisions made by an AI agent. It analyzes proposed actions and offers suggestions to improve their reasoning, alignment with goals, and overall effectiveness. This helps refine the agent's decision-making process and leads to better outcomes in complex scenarios.

When to use it

  • Improving task planning: Use it when you want your agent to generate more robust and well-reasoned plans for achieving a goal.
  • Refining conversational agents: Apply it to assess the appropriateness and helpfulness of responses in dialogue, ensuring they are aligned with user intent.
  • Evaluating complex decision chains: Employ it to review sequences of actions where each step builds on the previous one, identifying potential pitfalls or suboptimal choices.
  • Debugging agent behavior: Leverage it when an agent is exhibiting unexpected or undesirable behaviors and you need to understand why it made certain decisions.

Key capabilities

  • Provides feedback on decision quality
  • Suggests improvements to reasoning
  • Evaluates alignment with goals
  • Identifies potential issues in action sequences

Example prompts

  • "Critique the following plan: [agent's plan]"
  • "Evaluate this proposed response: [agent's response] and suggest alternatives."
  • "I want to achieve [goal]. The agent decided to [action]. Is that a good idea? Why or why not?"

Tips & gotchas

The effectiveness of decision-critic depends on the clarity and detail provided in the agent’s initial decision. Ensure the context and reasoning behind the action are well-defined for optimal feedback.