Skip to content
TrustedSkillsbeta
Back to all skills

Agent Prompt

Official
getsentry·vlatest·agents

Crafts detailed, context-aware prompts for other agents to maximize task completion accuracy and efficiency.

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 getsentry/warden --skill agent-prompt -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

getsentry

Matched to the vendor's own GitHub organisation.

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 getsentry/warden at 06b388607f.

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

Commit
06b388607f
Manifest
.agents/skills/agent-prompt/SKILL.md
Scanned
9 files, 823 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

The agent-prompt skill enables AI agents to interpret and execute natural language instructions directly. It bridges the gap between user intent and automated action by parsing requests into executable commands within the Warden framework.

When to use it

  • Task delegation: Assign complex multi-step workflows like data analysis or report generation without writing code.
  • Dynamic interaction: Allow users to converse with the agent about specific goals, letting the AI determine the necessary steps.
  • Rapid prototyping: Test new agent behaviors by describing desired outcomes in plain English rather than configuring logic manually.
  • Contextual queries: Ask the agent to retrieve or summarize information based on a specific scenario or constraint.

Key capabilities

  • Parses natural language inputs into structured agent actions.
  • Integrates seamlessly with the getsentry/warden environment.
  • Supports dynamic instruction interpretation for varied user needs.
  • Facilitates direct command execution from conversational prompts.

Example prompts

  • "Analyze the latest sales data and summarize the top three trends."
  • "Create a deployment plan for the new feature branch based on current system status."
  • "Draft an email to the team explaining the outage and outlining the recovery steps."

Tips & gotchas

Ensure your agent has the necessary permissions and tool access before issuing complex commands. While natural language is powerful, providing specific context about data sources or constraints can significantly improve the accuracy of the generated actions.