📦 ollama-task-orchestrator — 远程Ollama任务编排
v1.0.0通过SSH在远程Worker上管理和执行Ollama任务，提供队列状态、独占任务锁与代码生成命令，实现分布式AI模型调用与自动化编排。
0· 58·0 当前·0 累计
by 下载技能包
最后更新
2026/4/9
安全扫描
OpenClaw
安全
high confidenceThe skill's code, scripts, and runtime instructions are consistent with its stated purpose (orchestrating Ollama tasks over SSH); it requires SSH access and direct file/command privileges on the worker, which is expected but high‑privilege.
评估建议
This skill appears to do what it says: let an agent run Ollama tasks on a remote worker via SSH. Before installing, verify the worker is fully trusted and configured for this use: 1) review runner/run_task.sh and runner/queue_status.sh (they can kill/restart Ollama, eval arbitrary commands, and write files inside PROJECTS_DIR); 2) ensure SSH keys in ~/.ssh/config grant access only to the intended, isolated worker account (prefer a least‑privilege account or VM); 3) set DEFAULT_PROJECT carefully ...详细分析 ▾
✓ 用途与能力
Name/description match the code and runtime instructions: skill.py SSHs to a worker to run runner scripts that check Ollama, invoke model generation, write files, run tests, and execute shell commands. No unrelated cloud credentials, external services, or unexpected binaries are requested.
ℹ 指令范围
SKILL.md and the included runner scripts stay within the described domain (queue status, codegen, write, test, exec). However, run_task.sh exposes high‑impact capabilities: it can write files into the project directory, run arbitrary shell commands (eval "$cmd"), kill/restart the Ollama server, and its NL interpreter maps natural language to actions (write/test/exec). These are coherent with the skill's purpose but are powerful and should be used only on a trusted worker.
✓ 安装机制
There is no remote download/extract. The repo includes an install.sh that copies local runner scripts to the target runner directory and marks them executable. No external installers, URL downloads, or obfuscated installers are used.
ℹ 凭证需求
The registry metadata doesn't require env vars, but the skill and README document several worker and host environment variables (SSH host, runner path, DEFAULT_PROJECT, OLLAMA_MODEL, OLLAMA_URL, etc.). These variables are directly relevant to the skill. The notable privilege is the implicit requirement of SSH key access to the worker and the scripts' ability to read/write project files and run commands — appropriate for the purpose but high in practical privilege.
✓ 持久化与权限
always is false and the skill does not modify other skills or global agent configurations. It runs commands over SSH and installs scripts only into the designated runner path via install.sh. Autonomous invocation (model invocation enabled) is default platform behavior; combined with the skill's exec/write capabilities this is powerful, but that combination is explained by the skill's purpose.
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
latestv1.0.02026/4/9
Ollama Task Orchestrator 1.0.0 – Initial Release - Manage remote Ollama task queues and trigger code generation via SSH. - Health check and queue management commands, including stale lock cleanup and server restarts. - Execute various tasks on the worker: codegen, write to file, test, shell command execution, and project listing. - Exclusivity locking ensures tasks do not overlap. - Easy configuration using environment variables for hosts, directories, and model selection.
● 可疑
安装命令
点击复制官方npx clawhub@latest install ollama-task-orchestrator
镜像加速npx clawhub@latest install ollama-task-orchestrator --registry https://cn.longxiaskill.com