Skip to content
TrustedSkillsbeta
Back to all skills

tool-advisor

Checked
dragon1086·v1.0.0·other·MIT

Discovers your full tool environment and amplifies prompts with capability awareness. Suggests optimal tool compositions as non-binding options.

Install on your platform

Showing OpenClaw.

  1. 1

    Run this in your terminal

    terminal
    $

What we know about this skill

Publisher

dragon1086

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 dragon1086/claude-skills at 1551280ae8.

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

Commit
1551280ae8
Manifest
.agents/skills/tool-advisor/SKILL.md
Scanned
2 files, 297 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 tool-advisor skill analyzes the available tools in an AI agent's environment, identifying their capabilities and limitations. It then suggests potential combinations of these tools to best address a given task or prompt. These suggestions are presented as non-binding recommendations designed to enhance the agent’s efficiency and effectiveness.

When to use it

  • Complex tasks: When facing a multi-step process requiring diverse tool functionalities (e.g., researching market trends, generating a report, and scheduling a meeting).
  • Unfamiliar tools: When an agent is new to the environment or unsure of how different tools interact with each other.
  • Optimization: To explore alternative tool sequences that might improve performance or reduce execution time.
  • Discovery: When you want to understand what tools are available and their potential uses within a given context.

Key capabilities

  • Environment discovery: Identifies all accessible tools.
  • Capability analysis: Determines the functionalities of each tool.
  • Tool composition suggestions: Proposes optimal combinations for specific tasks.
  • Non-binding recommendations: Presents suggestions as options, not directives.

Example prompts

  • "I need to analyze customer sentiment from recent reviews and create a summary report."
  • "What tools can I use to automate social media posting?"
  • “Suggest some tool combinations for researching competitor pricing.”

Tips & gotchas

The effectiveness of tool-advisor depends on the accuracy and completeness of the tool environment definition. It's important to ensure that all available tools are properly registered within the agent’s system for optimal recommendations.