← 返回 Skills 市场
hyharry

Create Plugin

作者 Yi · GitHub ↗ · v0.1.0 · MIT-0
cross-platform ✓ 安全检测通过
151
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install create-plugin-deepwiki
功能描述
Create minimal, convention-matching plugins or extensions for an existing codebase. Use when the user asks for a plugin, extension, custom module, integratio...
使用说明 (SKILL.md)

Create Plugin

Build the smallest plugin that solves the requested problem while fitting the host codebase.

Workflow

  1. Learn the codebase before designing anything.

    • Read the GitHub repository first.
    • Read official docs linked from the repository, especially installation, API, examples, and contribution/style guidance.
    • If the deepwiki skill is installed, use DeepWiki MCP for public-repo source-code queries before guessing.
    • Use DeepWiki MCP for three things in particular:
      • structure to map the documentation/wiki layout,
      • contents to read relevant topic pages,
      • ask to query extension points, module organization, APIs, naming patterns, and built-in examples to copy.
    • Ask questions that are concrete and code-oriented, for example:
      • "What are the main extension points for adding a new plugin/module?"
      • "Which built-in modules are the smallest and best examples to study first?"
      • "How is the package organized, and where should a minimal extension live?"
  2. Learn the modular structure.

    • Identify the extension points, package layout, naming conventions, imports, base classes, and how existing modules are organized.
    • Use DeepWiki MCP source-code queries to accelerate this discovery when the repo is public.
    • Inspect one or two similar built-in modules or extensions and mirror their shape.
  3. Make a short plan before coding.

    • State the minimal implementation approach.
    • Prefer the smallest API and fewest files that still feel native to the project.
    • Call out any deliberate simplifications.
  4. Implement the plugin.

    • Match the host project's conventions first: formatting, file layout, typing style, docstrings, imports, naming, and dependency choices.
    • Prefer readability over novelty.
    • Avoid adding dependencies unless clearly justified.
    • Do not modify upstream/vendor code unless the user explicitly asks for an in-tree patch.
  5. Check convention fit.

    • Verify that names, module boundaries, and public API feel consistent with the host codebase.
    • If the environment is difficult, it is acceptable to skip full runtime testing, but still do lightweight checks that are feasible, such as syntax checks, lint-style review, or import-path review.
    • Be explicit about what was and was not verified.
  6. Document the plugin.

    • Add minimal usage documentation.
    • Explain the core API, state/inputs/outputs if relevant, and the main simplifying assumptions.
    • Keep documentation proportionate to the plugin size.

Design Rules

  • Start from existing examples in the host repo before inventing structure.
  • Keep the extension minimal and easy to read.
  • Prefer a narrow, obvious API.
  • Follow the host project's patterns more than generic best practices when the two differ.
  • When uncertain, choose the simpler design and note the limitation.
  • Do not promise physical/functional fidelity beyond what the implementation actually does.

Output Checklist

Before finishing, confirm all of the following:

  • the repository and docs were reviewed first
  • the modular structure was inspected
  • a plan was made before implementation
  • the plugin is minimal and readable
  • the code follows host-project conventions as closely as practical
  • documentation was added
  • verification scope is stated honestly

References

  • For a worked example based on CAX, read references/cax-recrystallization-example.md.
  • Only read the reference when the current task is similar or when you want an example of how to apply this workflow to a scientific/plugin-style extension.
  • If the deepwiki skill is available, read its SKILL and use its ask, structure, and contents commands for public GitHub repositories during the repo-learning phase.
安全使用建议
This skill is an instruction-only workflow for producing small, repo-specific plugins and appears internally consistent. Before installing or invoking: (1) Be aware it recommends reading target GitHub repos and (if available) calling the DeepWiki MCP skill — evaluate whether you trust DeepWiki and whether the agent should access that external service. (2) The skill does not request credentials; if you ask it to work on private repositories, the agent or platform may need repo access credentials separately — the skill itself won't request or store them. (3) Because it's autonomous-invocation-capable (the platform default), consider whether you want the agent to call it without confirmation in workflows that might expose private code. (4) If you plan to have the skill produce patches to upstream repos or create PRs, explicitly instruct it to do so and verify any commits before merging. If you want a deeper risk check, provide the target repository and whether it is public or private and whether DeepWiki MCP is available/authorized; that will let a more specific review of the planned operations change the assessment.
功能分析
Type: OpenClaw Skill Name: create-plugin-deepwiki Version: 0.1.0 The skill bundle provides a structured workflow for an AI agent to create minimal plugins for existing codebases. It emphasizes reading documentation, following host project conventions, and using the 'deepwiki' MCP tool for repository analysis (SKILL.md). There are no indicators of data exfiltration, malicious execution, or prompt injection; the instructions are focused on standard software development practices and documentation.
能力评估
Purpose & Capability
Name/description match the content: the skill is an instruction workflow for writing minimal, convention-matching plugins. It does not request unrelated credentials, binaries, or installs.
Instruction Scope
Runtime instructions focus on reading the target repository/docs, planning, implementing, testing, and documenting a plugin. It does not instruct the agent to read unrelated system files, harvest environment variables, or send data to unexpected endpoints. It does reference using the DeepWiki MCP skill when available, which is relevant for public-repo source queries.
Install Mechanism
No install spec or code files are present (instruction-only), so there is no on-disk install risk. This is the lowest-risk install posture.
Credentials
The skill requires no environment variables, credentials, or config paths. It does not ask for secrets or unrelated service tokens.
Persistence & Privilege
always is false and the skill does not request permanent system presence or modifications to other skills or system-wide settings. Autonomous invocation is allowed (platform default) but is not coupled with broad privileges.
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 create-plugin-deepwiki
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /create-plugin-deepwiki 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
v0.1.0
Initial release: plugin-writing workflow with DeepWiki MCP guidance and CAX example.
元数据
Slug create-plugin-deepwiki
版本 0.1.0
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

Create Plugin 是什么?

Create minimal, convention-matching plugins or extensions for an existing codebase. Use when the user asks for a plugin, extension, custom module, integratio... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 151 次。

如何安装 Create Plugin?

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

Create Plugin 是免费的吗?

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

Create Plugin 支持哪些平台?

Create Plugin 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 Create Plugin?

由 Yi(@hyharry)开发并维护,当前版本 v0.1.0。

💬 留言讨论