技能详情（站内镜像，无评论）
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v1.0.0
统计：⭐ 1 · 34 · 0 current installs · 0 all-time installs
⭐ 1
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：可疑
Package：aowind/long-running-harness
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：可疑
OpenClaw 评估
The skill's instructions are coherent with a long-running project harness, but the SKILL.md expects shell tools and running arbitrary project init scripts (which may install software or run network operations) while the skill declares no required binaries or environment access—this mismatch and the ability to execute repo-provided scripts merit caution.
目的
The name/description (long-running project harness) matches the actions in SKILL.md: creating project folders, reading/writing features.json and progress.md, selecting tasks, committing git changes, spawning child sessions, and optionally scheduling cron checks. However the instructions assume availability of system tools (git, bash, curl, npm, pip, python, pytest) and the ability to run project-provided init.sh and tests, yet the skill metada…
说明范围
Instructions remain within the declared purpose (manage project state, run one feature per session, enforce tests, update files, git commit). But they explicitly direct the agent to run shell commands and any project-provided init.sh, which can execute arbitrary code, perform package installs, start services, and make network requests. That behavior is expected for a harness but expands the runtime authority significantly and should only be ap…
安装机制
There is no install spec (instruction-only), which is low risk from the skill distribution perspective. However the provided init.sh templates instruct package installation (npm, pip) and starting services — these actions would download and run third-party code at runtime. The lack of an install step in the skill itself is consistent, but users should note that the skill will routinely execute repository scripts that may install software.
证书
The skill declares no required environment variables or credentials, which aligns with its general purpose. But practical execution often relies on system credentials (git remotes requiring git credentials, DB access, package registry/network access). The skill does not request or document these, so users must be aware the agent may attempt operations that implicitly depend on external credentials or network access.
持久
always:false and normal autonomous invocation settings are used. The skill writes/commits to project directories (its intended scope) but does not request persistent system-wide privileges. The scheduling/cron example can make the agent run periodically, so users should control whether and how those schedules are created.
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「long-running-harness」。简介：长时程 Agent 项目工作流框架（基于 Anthropic "Effective Harnesses for Long-Running Agents"）。 …。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/aowind/long-running-harness/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
暂无本地缓存内容，可在后台执行详情同步。