📦 Peer Review — 多模型复核
v1.0.0通过 Ollama 调用 2-3 个本地 LLM，对云端模型输出进行扇出式评审、聚合标记并合成共识，为高风险的 Claude 结果提供质量把关与错误捕捉。
0· 933·15 当前·18 累计
by @staybased下载技能包
最后更新
2026/4/22
安全扫描
OpenClaw
可疑
medium confidenceNULL
评估建议
Key things to check before installing or using this skill:
- Local model & resource requirements: It expects Ollama running locally with specific models (mistral:7b, tinyllama:1.1b, llama3.1:8b). Those models consume disk, memory, and will increase latency — confirm you have hardware and are comfortable hosting them locally.
- Missing scripts and automation: The SKILL.md refers to bash scripts in workspace/scripts/, but no scripts are bundled. Ask the publisher for the scripts or inspect the i...详细分析 ▾
⚠ 用途与能力
The described purpose (fan-out critiques to local Ollama models) matches the listed dependencies (Ollama, local models, jq, curl). However the SKILL.md also describes posting to Discord channels (#the-deep, #swarm-lab, #reef-logs) and packaging a ‘Reef API’ endpoint for agent calls; those capabilities imply network access and service credentials but the skill declares no required environment variables, credentials, or config paths. That omission is an incoherence between stated capabilities/workflows and declared requirements.
⚠ 指令范围
The runtime instructions focus on running local model fan-out and aggregating critiques, which is in-scope. But they also instruct posting to specific Discord channels and packaging an API endpoint / logging with TPR tracking. The skill references bash scripts under workspace/scripts/ for review and seeding tests, yet no scripts are bundled or install steps provided. The instructions do not specify how to authenticate to Discord or how agents should call the Reef API, leaving ambiguous what data would be sent where and under what credentials.
✓ 安装机制
This is an instruction-only skill with no install spec and no code files, which minimizes install-time risk. Dependencies are declared in prose (Ollama and specific local models, jq, curl), which is appropriate for this kind of local workflow. No external downloads or archive extraction are specified.
⚠ 凭证需求
The skill declares no required environment variables or credentials, yet the SKILL.md explicitly references posting to Discord channels and exposing a POST /review API endpoint and logging to '#reef-logs'. Those behaviors normally require tokens/URLs and configuration. The absence of any declared credential requirements is disproportionate to the external-communication behaviors described and creates ambiguity about where sensitive cloud model outputs or reviews would be sent/stored.
✓ 持久化与权限
The skill does not request persistent always:true privileges, does not modify other skills, and has no install-time persistence. It appears to run on-demand and use local Ollama instances, so privilege/persistence concerns are low on their face.
安全有层次，运行前请审查代码。
运行时依赖
无特殊依赖
版本
latestv1.0.02026/2/13
NULL
● 可疑
安装命令
点击复制官方npx clawhub@latest install peer-review
镜像加速npx clawhub@latest install peer-review --registry https://cn.longxiaskill.com