Skip to content
TrustedSkillsbeta
Back to all skills

Context Health Monitor

Checked
toonight·vlatest·other·MIT

Continuously assesses conversation context quality, proactively alerting users to potential misunderstandings or derailments.

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 toonight/get-shit-done-for-antigravity --skill context-health-monitor -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

toonight

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 toonight/get-shit-done-for-antigravity at 5b7762fd6f.

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

Commit
5b7762fd6f
Manifest
.agents/skills/context-health-monitor/SKILL.md
Scanned
1 file, 104 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 context-health-monitor skill assesses the quality and relevance of information provided within a conversation or task. It identifies potential issues like outdated data, contradictory statements, or hallucinations. This allows the AI agent to flag concerns and request clarification, improving overall accuracy and reliability.

When to use it

  • Long conversations: Monitor context drift and ensure consistency over extended interactions.
  • Fact-checking tasks: Verify information before presenting it as truth.
  • Complex problem solving: Identify conflicting data points that could lead to incorrect conclusions.
  • Research projects: Evaluate the trustworthiness of sources and identify potential biases.

Key capabilities

  • Contextual analysis
  • Data consistency checks
  • Hallucination detection
  • Outdated information identification

Example prompts

  • "Analyze the context of our conversation so far and flag any inconsistencies."
  • "Evaluate the reliability of this document snippet: [paste text here]."
  • "Check if the information I'm about to present contradicts anything we’ve already discussed."

Tips & gotchas

The skill requires access to the full conversation history or relevant data sources. Performance may vary depending on the complexity and volume of context being analyzed.