← 返回 Skills 市场
Openclaw Godmode Skill Repo
作者
TonyNoScope
· GitHub ↗
· v5.11.3
5483
总下载
12
收藏
25
当前安装
3
版本数
在 OpenClaw 中安装
/install cc-godmode
功能描述
Self-orchestrating multi-agent development workflows. You say WHAT, the AI decides HOW.
安全使用建议
Install only if you intentionally want a highly autonomous development orchestrator. Use it in trusted repositories, scope GitHub and MCP credentials narrowly, avoid live customer or secret-bearing pages during screenshot testing, and require explicit approval before file writes, shell commands, PR merges, issue closure, releases, tags, CI/CD actions, or any production-like operation.
功能分析
Type: OpenClaw Skill
Name: cc-godmode
Version: 5.11.3
The skill is classified as suspicious due to its extensive use of high-risk capabilities, including broad `Bash` execution, file system modification (`Read`, `Write`, `Edit`, `mkdir`), and network access (`WebSearch`, `WebFetch`, `GitHub MCP`, `Playwright MCP`). While these capabilities are explicitly declared in `SKILL.md` and `clawdis.yaml` and are plausibly necessary for an 'autonomous multi-agent development workflow,' they inherently present a significant attack surface. The `SKILL.md` and other documentation files also serve as a prompt injection surface for the AI agent, even though the current instructions do not contain explicit malicious commands. The transparency about runtime requirements and the explicit instruction 'NEVER git push without permission' mitigate against a 'malicious' classification, but the inherent power granted to the agent warrants a 'suspicious' label.
能力评估
Purpose & Capability
The declared purpose is multi-agent development orchestration, and the documented capabilities fit that purpose: file edits, Bash, web research, Playwright testing, GitHub operations, optional credentials, and network use are disclosed.
Instruction Scope
The skill uses broad triggers such as ordinary development requests and a start rule of 'When the user makes a request,' while workflows can create reports, edit files, run commands, create releases, merge PRs, close issues, and trigger CI/CD; only git push has a clear permission boundary.
Install Mechanism
The package contains markdown and YAML documentation only, no executable files, and the install examples are user-directed copy or ClawHub install commands.
Credentials
Runtime access to local binaries, network, GitHub/MCP credentials, messaging/cron-triggered OpenClaw contexts, and production/server-administration-adjacent workflows is powerful and not tightly scoped by the artifacts.
Persistence & Privilege
The skill directs agents to save reports and Playwright screenshots, and optionally use memory MCP; this is disclosed, but screenshot and memory retention lacks clear privacy controls for secrets, PII, or authenticated pages.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install cc-godmode - 安装完成后，直接呼叫该 Skill 的名称或使用
/cc-godmode触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v5.11.3
v5.11.3 – Security Declaration Alignment
This release fixes security-scan findings caused by inconsistent runtime declarations in v5.11.2.
What changed
• Updated runtime declarations to match actual workflow behavior:
• requires_binaries: true
• requires_credentials: true
• requires_network: true
• Clarified package behavior:
• The package itself remains documentation-only (no install-time executable payload).
• Agent workflows may execute shell/network actions at runtime when invoked by the user.
• Added explicit runtime transparency:
• Required/optional runtime binaries
• Optional credentials/environment expectations (e.g. GH_TOKEN, Claude auth, MCP configuration)
• Refined security semantics to distinguish:
• install-time safety
• runtime agent capabilities
Why this release
v5.11.2 could create a misleading security impression by claiming no network/credentials/code-execution requirements while documenting workflows that use shell, GitHub, Playwright, and web tools.
v5.11.3 resolves that mismatch for clearer trust and more accurate scanner interpretation.
Compatibility
• No breaking workflow changes
• Backward-compatible behavior
• Metadata/security declaration update only
v5.11.2
v5.11.2 - Converts skill to documentation-only, updates ownership/metadata
- Fully converted cc-godmode to a documentation-only skill: skill now provides workflow/instructions but does not execute code.
- Updated skill metadata: new author (`cubetribe`), repository, tags, and clarified type as `orchestration-docs`.
- Added `clawdis.yaml` and `.DS_Store` files; removed legacy `scripts/build-skill.js`.
- Explicit note added highlighting that the skill requires no binaries or credentials and does not perform orchestration itself.
- Tool and model references clarified as examples; actual implementations depend on OpenClaw setup.
v5.11.1
cc-godmode 5.11.1
- Updated SKILL.md with clearer descriptions of workflows, agent roles, and orchestration best practices.
- Improved documentation of standard workflows, including diagrams for agent handoffs and quality gates.
- Added detailed agent specifications and output formats for all subagents.
- Clarified file structure and requirements for build reports and versioning.
- Included pre-push and release validation checklist to enforce project integrity.
元数据
常见问题
Openclaw Godmode Skill Repo 是什么？
Self-orchestrating multi-agent development workflows. You say WHAT, the AI decides HOW. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 5483 次。
如何安装 Openclaw Godmode Skill Repo？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install cc-godmode」即可一键安装，无需额外配置。
Openclaw Godmode Skill Repo 是免费的吗？
是的，Openclaw Godmode Skill Repo 完全免费（开源免费），可自由下载、安装和使用。
Openclaw Godmode Skill Repo 支持哪些平台？
Openclaw Godmode Skill Repo 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Openclaw Godmode Skill Repo？
由 TonyNoScope（@cubetribe）开发并维护，当前版本 v5.11.3。
推荐 Skills