← 返回 Skills 市场
416
总下载
0
收藏
2
当前安装
10
版本数
在 OpenClaw 中安装
/install plan-c
功能描述
于已有规划文件继续对话：智能识别“显式文件加载”意图，优先提供状态总结，支持按需深度迭代。
安全使用建议
This skill appears to do what it says: it will read planning files (plans/.../*.md), summarize them by default, and only scan code or update files if you explicitly request deep analysis and iteration. Before installing or invoking it: 1) confirm where your planning files live and avoid placing sensitive data in the same directories; 2) be aware the skill will write back updates to the original planning file when you ask it to iterate—only grant that permission if you trust the edits; 3) note that the skill is not autonomously invoked (disable-model-invocation=true), which reduces accidental access; and 4) if you want stricter control, provide explicit file paths in your commands every time so the skill only reads the intended file. Overall the skill is internally coherent and proportional to its stated purpose.
功能分析
Type: OpenClaw Skill
Name: plan-c
Version: 1.0.9
The 'plan-c' skill is a planning assistant designed to manage and iterate on project documentation. It provides structured instructions for an AI agent to read planning files and perform read-only codebase analysis to update those plans. The skill includes explicit safety constraints, such as prohibiting code generation and forbidding the execution of specific scripts like 'pl-init.sh', showing no signs of malicious intent or data exfiltration.
能力评估
Purpose & Capability
The name/description promise (continue conversations based on existing planning files; summarize first, deep-iterate on demand) matches the runtime instructions: detect explicit file paths, summarize when asked, and run a deeper 'Plan Mode' only for specific analysis requests.
Instruction Scope
Instructions explicitly direct the agent to read plan files (plans/.../*.md), optionally scan related code directories in deep mode, and write updates back to the original planning file. This is coherent with the skill's purpose, but it does mean the skill will perform file I/O (reads and writes) on project files when invoked for iteration — users should expect and authorize that behavior.
Install Mechanism
Instruction-only skill with no install steps or external downloads; nothing is written to disk by an installer. No install-related red flags.
Credentials
No environment variables, credentials, or config paths are requested. The required inputs (file paths and conversational context) are proportional to the stated functionality.
Persistence & Privilege
The skill does not request permanent/always-on inclusion and has disable-model-invocation=true (it will not be invoked autonomously). It does perform writes to planning files when the user explicitly asks for iteration, which is a normal capability for a document-update skill.
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 plan-c - 安装完成后，直接呼叫该 Skill 的名称或使用
/plan-c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
v1.0.9
plan-c 1.0.9 更新日志
- 优化“模式二”下的规划文件更新，强调根据文件结构和内容灵活增量更新
- 补充约束：新增“安全红线”，再次强调禁止自动生成代码，只有在用户明确指令并规划就绪时才允许编码
- 路由规则增强：路径判定时，支持用户输入或上下文中携带路径皆触发快速加载模式
- 精简“规划迭代”流程，不再强制要求更新 TODO 列表，强调移除已解决关键点
- 文档表述更清晰，流程和约束描述更加准确
v1.0.8
No functional or documentation changes in this version.
- No file or SKILL.md updates detected in this release.
- Behavior and user interaction remain unchanged.
v1.0.7
Version 1.0.7
- No code or file changes detected; content and logic remain unchanged.
- All workflows, constraints, and user interaction strategies are consistent with previous version.
- Continues to require an existing plan file and follows the described routing based on user intent.
v1.0.6
- 优化指令路由，支持“显式文件加载”与“深度迭代”两种核心模式。
- 检测到路径时默认输出文件状态总结，除非用户同句明确要求深入分析。
- 明确禁止列出代码与开发实施步骤，仅聚焦数据结构和规划逻辑。
- 完善输入示例与模式判定规则，提升交互灵活性和智能性。
v1.0.5
- No user-facing changes; SKILL.md remains unchanged in this version.
- No file modifications detected for version 1.0.5.
v1.0.4
- 移除了 _meta.json 文件，简化了技能元数据结构。
- 功能和行为未做更改。
v1.0.3
- 初始发布 meta 信息：新增 _meta.json 文件，完善技能元数据。
- 功能和文档未变。
v1.0.2
No user-facing changes in this version.
- No file changes detected in this release.
- Functionality and documentation remain the same as the previous version.
v1.0.1
- No visible changes; this release does not modify any files.
- All features and behaviors from the previous version remain unchanged.
v1.0.0
plan-c v1.0.0
- 新增：基于已有规划文件进行持续对话与深度迭代，自动识别并加载规划文件。
- 支持用户选择方向或细化需求，智能分析并细化规划条目，保持文档实时更新。
- 严格限制只做规划与文档更新，不生成代码、不初始化项目（禁用pl-init.sh）。
- 自动检测依赖规划文件，不存在时引导先创建（/plan-i）。
- 每轮迭代后智能总结并推荐后续讨论方向，支持用户循环推进规划进程。
元数据
常见问题
Plan C 是什么？
于已有规划文件继续对话：智能识别“显式文件加载”意图，优先提供状态总结，支持按需深度迭代。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 416 次。
如何安装 Plan C？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install plan-c」即可一键安装，无需额外配置。
Plan C 是免费的吗？
是的，Plan C 完全免费（开源免费），可自由下载、安装和使用。
Plan C 支持哪些平台？
Plan C 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 Plan C？
由 Xin Ding（@9talk）开发并维护，当前版本 v1.0.9。
推荐 Skills