← 返回 Skills 市场
jisang1000

Writing Plans

作者 jisang1000 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ 安全检测通过
251
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install jisang1000-writing-plans
功能描述
Break work into clear, ordered plans before execution. Use when a task is multi-step, long-running, easy to derail, or needs coordination across tools, files...
使用说明 (SKILL.md)

Writing Plans

Write plans that are concrete enough to execute, review, and verify.

Core Rule

Do not jump into a long task with only a vague idea. Break it into explicit steps with outcomes.

When to Use

Use for:

  • multi-step setup work
  • migrations
  • skill installation and validation passes
  • browser automation workflows
  • refactors
  • research + implementation tasks
  • tasks that may require sub-agents

Plan Shape

A good plan includes:

  1. Goal
  2. Constraints
  3. Ordered steps
  4. Verification points
  5. Possible blockers

Good Step Format

Each step should answer:

  • what to do
  • what tool/file it touches
  • what counts as success

Example:

  1. Inspect installed files and runtime requirements.
  2. Install missing low-risk dependencies.
  3. Run smoke tests.
  4. Separate working / needs-auth / broken states.
  5. Report results.

Execution Rule

After writing the plan:

  • execute in order
  • update the plan if reality changes
  • do not hide changed assumptions

Lightweight vs Heavyweight

Lightweight plan

Use for 3-5 step tasks.

Heavyweight plan

Use when:

  • many files or tools are involved
  • external systems are involved
  • the task may run long
  • sub-agents may help

Reporting

Summarize with:

  • planned scope
  • what completed
  • what changed during execution
  • what remains

Practical Examples

Example: Skill setup pass

  1. Inspect files and dependencies
  2. Install missing low-risk runtime tools
  3. Run smoke tests
  4. Split results into working / needs-auth / blocked
  5. Report next steps

Example: Browser automation task

  1. Confirm target site and success condition
  2. Test a minimal path first
  3. Add login/session handling if needed
  4. Re-test the actual target flow
  5. Record blockers clearly
安全使用建议
This skill is a generic planning guide and is internally consistent. Before following any plan the agent produces: review any step that reads local files or installs software, approve installs explicitly, avoid providing secrets or service credentials unless you expect them to be needed and trust the destination, and monitor/report the agent's actions when it interacts with external systems or runs tooling. If you want stricter limits, require human confirmation for file access or package installs triggered by plans.
功能分析
Type: OpenClaw Skill Name: jisang1000-writing-plans Version: 1.0.0 The skill bundle contains purely instructional content designed to guide an AI agent in breaking down complex tasks into structured plans. There is no executable code, no network activity, and no evidence of malicious intent or prompt injection; the files (SKILL.md and references/publish-notes.md) focus entirely on organizational best practices for agentic workflows.
能力评估
Purpose & Capability
Name/description match the content: the skill provides structured guidance for breaking multi-step tasks into ordered plans. There are no unexpected binaries, env vars, or installs required.
Instruction Scope
The SKILL.md recommends actions such as 'inspect installed files and runtime requirements' and 'install missing low-risk dependencies.' Those are reasonable for a planning helper, but they imply the agent may read local files or attempt installs when following the plan — the skill itself does not declare or constrain those reads/installs.
Install Mechanism
No install spec or code files are present; this is instruction-only so nothing will be downloaded or written by the skill itself.
Credentials
The skill requests no environment variables, credentials, or config paths. Although it mentions possible sub-agents and external systems, it does not request tokens or secrets itself.
Persistence & Privilege
always is false and the skill is user-invocable. It does not request persistent presence or attempt to modify other skills or global agent settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install jisang1000-writing-plans
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /jisang1000-writing-plans 触发
  4. 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
v1.0.0
Initial publish
元数据
Slug jisang1000-writing-plans
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Writing Plans 是什么?

Break work into clear, ordered plans before execution. Use when a task is multi-step, long-running, easy to derail, or needs coordination across tools, files... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 251 次。

如何安装 Writing Plans?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install jisang1000-writing-plans」即可一键安装,无需额外配置。

Writing Plans 是免费的吗?

是的,Writing Plans 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Writing Plans 支持哪些平台?

Writing Plans 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 Writing Plans?

由 jisang1000(@jisang1000)开发并维护,当前版本 v1.0.0。

💬 留言讨论