Delegate coding tasks to Codex, Claude Code, or Pi agents via background host sessions. Use when: (1) building or creating new features or apps, (2) reviewing PRs or parallel coding with managed worktree isolation when subagents are available, (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, or any work in ~/clawd workspace (never spawn agents here). Requires OpenClaw host tools with exec_command plus write_stdin.
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, CLI/type generation, and MCP-backed skills that need a durable command path.
Create or update AgentSkills, especially when a user wants the agent to learn a reusable capability, workflow, integration, domain rule, team process, or tool usage pattern for future tasks. Use when designing, structuring, reviewing, validating, packaging, or improving skills with SKILL.md, scripts, references, and assets.
Simple operations on user-provided text files including summarization.
Connect to a remote streamable HTTP MCP service that exposes announcements and FAQ tools.
| name | skill-find |
| description | Find a public Agent Skill on GitHub, install it, and load it. |
Overview
Use this skill when the user wants a new public Agent Skill that is not already installed.
Workflow
Search GitHub pages with web_search.
Prefer queries that mention SKILL.md, the requested topic, and
site:github.com.
Pick a result that clearly points to a GitHub skill directory or a
SKILL.md page.
Call skill_install_github with that GitHub URL.
Read the tool result carefully.
It returns the exact skill_name that was installed and may also
include installed_files.
Immediately call skill_load with the returned skill_name.
Only if local execution is explicitly enabled for this demo and the
user asked for a runnable demo, follow the installed skill docs and
use skill_run.
If the docs are brief, use installed_files to avoid guessing.
Prefer obvious entrypoint files such as run.sh or scripts under
scripts/.
Rules
SKILL.md.