mirror of
https://github.com/alirezarezvani/claude-skills.git
synced 2026-10-09 03:17:54 +00:00
abd9c9d8de
generate-docs.py learns the agent-launcher domain (5 hardcoded maps extended); regenerated docs tree: 343 skill pages / 96 agent pages / 122 command pages (561 total). mkdocs.yml nav gains the Agent Launcher skill section (7 pages), 4 cs-agent-* agent entries, and 8 /cs:* command entries; all nav targets verified to exist. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012FwXG6TqCXKZQvF4iD69cv
1.6 KiB
1.6 KiB
| title | description |
|---|---|
| Agent Launcher Skills — Agent Skills & Codex Plugins | 6 agent launcher skills — Claude Managed Agent launcher agent skill and Claude Code plugin for session-goal-driven interview, BYOK launch, bounded grade-iterate loops, and cron scheduled deployments. Works with Claude Code, Codex CLI, Gemini CLI, and OpenClaw. |
:material-rocket-launch-outline: Agent Launcher
6 skills in this domain
Install all:
claude /plugin install agent-launcher-skills
-
agent-launcher — Domain Orchestrator
Every session starts with a goal — one sentence for one CMA. This orchestrator
-
Phase 3 — Grade → Iterate (the bounded loop)
This is the plugin's loop: CMA's outcome primitive self-grades the agent's
-
Open warmly with one or two examples from
-
Phase 4 — Run Without You (the recurring loop)
A scheduled deployment fires a fresh session on a cron cadence — the agent
-
Turn the build sheet into runnable artifacts, then let the founder launch with
-
The explicit close-out. Confirm what's live, regenerate the shareable overview,