📄 skillActiveCuratedmedium

agentscope-ai/HiClaw

by agentscope-ai

An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.

Supported Platforms

🤖 Claude Code🧠 Codex

Stars

4.8k

Skill Type

⚙️ Infrastructure Operations

Quality Score

144/200

License

Apache-2.0

Forks

572

Last Updated

Jun 11, 2026

Discovered

Apr 26, 2026

Validation

Passed

github.com/agentscope-ai/HiClaw

Quality Breakdown

144/ 200

Content Signals

Gotchas/Edge Cases+40
Progressive Disclosure+30
Trigger Description+20
Verification/Safety+20
Code Examples+15
Composability+15

Repo Health

Recent Activity+15
Scripts/Automation+10
Real Usage (Issues)+10
Single Responsibility+10
Config/Persistence+10
Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Risk Assessment

  • Repository contains Docker and Kubernetes manifests that could execute arbitrary code during build/deployment
  • Multiple GitHub Actions workflows (.github/workflows) with potential for automated execution without explicit approval gates
  • Shell scripts in copaw/scripts/ directory (copaw-worker-entrypoint.sh, patch_*.py) that execute code during container initialization
  • Python package installation and bootstrap logic in pyproject.toml and setup configurations
  • Multi-agent orchestration platform designed to spawn and manage multiple agent instances autonomously
  • Declarative resource management and Kubernetes CRD integrations allow dynamic agent spawning