Skip to content
TrustedSkillsbeta
Back to all skills

Context Audit

Checked
hjewkes·vlatest·ai-ml·MIT

Analyzes conversation history to identify missing context & suggests prompts for improved AI responses.

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 hjewkes/agent-skills --skill context-audit -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

hjewkes

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 hjewkes/agent-skills at f3c9318438.

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

Commit
f3c9318438
Manifest
skills/context-audit/SKILL.md
Scanned
2 files, 244 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 hjewkes-context-audit skill provides a mechanism to analyze and evaluate the context being used by an AI agent. It helps identify potential issues like excessive length, irrelevant information, or outdated data impacting performance. This allows for optimization of prompts and improved agent accuracy.

When to use it

  • Debugging unexpected behavior: If an agent is producing inconsistent or incorrect results, audit its context to see if extraneous information is interfering.
  • Optimizing prompt efficiency: Determine if the current context length is unnecessarily long, impacting speed and cost.
  • Maintaining data freshness: Regularly check the context for outdated information that could lead to inaccurate responses.
  • Improving agent reliability: Ensure the context consistently provides relevant information for better decision-making.

Key capabilities

  • Context analysis
  • Identification of irrelevant information
  • Evaluation of context length
  • Detection of outdated data

Example prompts

  • "Audit the current context being used by the agent."
  • "Show me the longest sections in the agent's context."
  • "Identify any data points older than one week within the agent’s context."

Tips & gotchas

The skill requires access to the agent's active context. Ensure appropriate permissions are granted for accurate analysis and reporting.