agent-swarm
agent-swarm is an Agent task delegation & fan-out skill for AI agents, published by lidpeng in the openclaw_swarm repository on GitHub. Skillspace rates agent-swarm F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
创建和编排多智能体集群完成复杂任务。当用户需要将复杂任务拆解给多个专业智能体并行或串行执行时使用此技能。适用场景：(1) 复杂项目需要多角色协作（规划、调研、编码、写作、设计、分析、审核）(2) 需要并行执行多个独立子任务以提高效率 (3) 需要专业分工以优化成本和质量。关键词：多智能体、Agent集群、任务编排、并行执行、智能体团队。
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 52
Unproven: rated by static analysis only, not yet compared head-to-head.
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 65 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- High-risk patterns
- License
- Not declared. Check the repository before reusing it.
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- executes shell/subprocess
- dynamic code execution (eval/exec)
- hidden/zero-width/bidi unicode chars
- mentions secrets in text
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.