Path-grounded multi-agent orchestration using the Liku directory hierarchy (skills.xml inheritance, todo.md + LikuErrors.md audit trail, SQLite memory). Use when you need to initialize Liku, generate an agent bundle for a specific Liku/* residence path, or expose Liku as an MCP server for Gemini-CLI, Claude Code, Copilot-CLI, or ChatGPT Codex.
Scanned 9/12/2026
Install to Claude Code
Skills Directorynpx -y skills add aibot88/sec_skill_store --skill liku-orchestrator --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Liku Orchestrator?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/aibot88-liku-orchestrator)More formats (shields.io, HTML) on the badges page.
---
name: liku-orchestrator
description: Path-grounded multi-agent orchestration using the Liku directory hierarchy (skills.xml inheritance, todo.md + LikuErrors.md audit trail, SQLite memory). Use when you need to initialize Liku, generate an agent bundle for a specific Liku/* residence path, or expose Liku as an MCP server for Gemini-CLI, Claude Code, Copilot-CLI, or ChatGPT Codex.
---
# Liku Orchestrator
## What to do
- Treat `Liku/` as the canonical source of truth for agent identity, scope, and state.
- Load skills by inheriting `skills.xml` from the agent residence directory up to `Liku/`.
- Mirror progress to `todo.md`; mirror failures to `LikuErrors.md`.
## Quick start (repo-local)
- Initialize: run `liku init`
- Start MCP server (stdio): run `liku-mcp`
- Generate a bundle for a residence path:
- Call MCP tool `liku.invoke` with `agentResidence` like `Liku/specialist/ts` and a JSON `task`.
## Notes
- If an action would require root-only privilege, return an escalation request as structured output; do not assume interactive consent unless the client supports it.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
