Skip to content
TrustedSkillsbeta
Back to all skills

Coding Agent

Checked
openclaw·v2026.3.2·agents·MIT

Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Requires a bash tool that supports pty:true.

Repository

Install on your platform

Showing OpenClaw.

  1. 1

    Run this in your terminal

    terminal
    $ openclaw skills install coding-agent

What we know about this skill

Publisher

openclaw

Taken from the source listing. We haven't verified who controls this account.

Install target

Pinned to 7b5e64ef

Installs fetch a stored snapshot of that commit, so the code can't change after the fact.

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 openclaw/openclaw at f12a8dee23.

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

Commit
f12a8dee23
Manifest
skills/coding-agent/SKILL.md
Scanned
1 file, 188 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

OpenClaw is a personal AI assistant designed to operate locally on user devices. It provides responses across various messaging platforms like WhatsApp, Telegram, and Slack, and offers voice interaction capabilities on macOS/iOS/Android. A key feature is its "Canvas" which allows for interactive control by the user.

When to use it

  • Personal Productivity: Use OpenClaw to manage tasks, set reminders, or quickly access information without relying on cloud-based services.
  • Cross-Platform Communication: Receive and respond to messages across multiple platforms (Slack, Discord, Telegram) from a single interface.
  • Local Data Privacy: Ideal for users who prioritize keeping their data and interactions private by running an AI assistant locally.
  • Interactive Control: Utilize the Canvas feature for visual interaction and control of the AI agent's functions.

Key capabilities

  • Cross-platform messaging support (WhatsApp, Telegram, Slack, Discord, etc.)
  • Voice interaction on macOS/iOS/Android
  • Local operation – data stays on user devices
  • Interactive "Canvas" for visual control
  • Onboarding wizard for easy setup (openclaw onboard)

Example prompts

  • “OpenClaw, remind me to call John at 2 PM.”
  • “Show me the latest news headlines on the Canvas.”
  • "Can you summarize my messages from Slack?"
  • "What's the weather like today?”

Tips & gotchas

  • The preferred setup method is running openclaw onboard in your terminal to guide initial configuration.
  • OpenClaw functions as a personal assistant, designed for single-user operation.