← 返回 Skills 市场
a2mus

Doro Command Creator

作者 Mus Titou · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
477
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install doro-command-creator
功能描述
WHAT: Create Claude Code slash commands - reusable markdown workflows invoked with /command-name. WHEN: User wants to create, make, or add a slash command. U...
使用说明 (SKILL.md)

Command Creator

Slash commands are markdown files in .claude/commands/ (project) or ~/.claude/commands/ (global) that expand into prompts when invoked.

Command Structure

---
description: Brief description for /help (required)
argument-hint: \x3Crequired> or [optional] (if takes arguments)
---

# Command Title

[Instructions for agent to execute autonomously]

Creation Workflow

Step 1: Determine Location

  1. Check if in git repo: git rev-parse --is-inside-work-tree
  2. Default: Git repo → .claude/commands/, No git → ~/.claude/commands/
  3. Override if user explicitly says "global" or "project"

Report chosen location before proceeding.

Step 2: Identify Pattern

Load references/patterns.md and present options:

Pattern Structure Use When
Workflow Automation Analyze → Act → Report Multi-step with clear sequence
Iterative Fixing Run → Parse → Fix → Repeat Fix issues until passing
Agent Delegation Context → Delegate → Iterate Complex tasks, user review
Simple Execution Parse → Execute → Return Wrapper for existing tools

Ask: "Which pattern is closest to what you want?"

Step 3: Gather Information

A. Name and Purpose

  • "What should the command be called?" (kebab-case: my-command)
  • "What does it do?" (for description field)

B. Arguments

  • "Does it take arguments? Required or optional?"
  • Required: \x3Cplaceholder>, Optional: [placeholder]

C. Workflow Steps

  • "What specific steps should it follow?"
  • "What tools or commands should it use?"

D. Constraints

  • "Any specific tools to use or avoid?"
  • "Any files to read for context?"

Step 4: Generate Command

Load references/best-practices.md for:

  • Template structure
  • Writing style (imperative form)
  • Quality checklist

Key principles:

  • Use imperative form: "Run X", not "You should run X"
  • Be explicit: "Run make lint", not "Check for errors"
  • Include expected outcomes
  • Define error handling
  • State success criteria

Step 5: Create File

mkdir -p [directory-path]

Write the command file. Report:

  • File location
  • What the command does
  • How to use: /command-name [args]

Step 6: Test (Optional)

Suggest: "Test with /command-name [args]"

Iterate based on feedback.


Writing Guidelines

Imperative form (verb-first):

  • ✅ "Run git status"
  • ❌ "You should run git status"

Specific, not vague:

  • ✅ "Run make lint to check for errors"
  • ❌ "Check for errors"

Include outcomes:

  • ✅ "Run git status - should show modified files"
  • ❌ "Run git status"

Realistic examples:

  • git commit -m "Add OAuth2 authentication"
  • git commit -m "foo bar"

Command Patterns Quick Reference

Workflow Automation

1. Check for .PLAN.md
2. Analyze git status/diff
3. Perform actions
4. Report results

Iterative Fixing

1. Run make all-ci (max 10 iterations)
2. Parse errors by category
3. Apply targeted fixes
4. Repeat until success or stuck

Agent Delegation

1. Present context
2. Invoke subagent with Task tool
3. Iterate with user feedback
4. Save output after approval

See references/examples.md for full command examples.


Quality Checklist

Before finalizing:

  • Name is kebab-case (my-command, not my_command)
  • Description is action-oriented
  • Steps are numbered and specific
  • Tool usage explicitly specified
  • Error handling defined
  • Success criteria stated
  • Uses imperative form

NEVER

  • Use underscores in command names (use hyphens)
  • Write vague instructions ("fix errors")
  • Skip error handling
  • Use second person ("You should...")
  • Create commands without testing
  • Leave success criteria undefined
安全使用建议
This skill appears to do what it says: help you author slash-command markdown files. It asks for no secrets and installs nothing, which is good. Important cautions: the examples and templates show commands that run shell tools (git, make, gt), edit files, and can create commits/PRs — those are powerful actions. Before you (or an agent) invoke any generated command, review the command file content and confirm you want it to run the listed operations. Prefer creating/testing commands in a disposable repository or using the project-scoped location (.claude/commands/) rather than a global location (~/.claude/commands/) until you're confident. If you are concerned about autonomous agents running repository-changing commands, restrict the agent's tool permissions or require explicit user approval before executing any generated command.
功能分析
Type: OpenClaw Skill Name: doro-command-creator Version: 1.0.0 The skill 'doro-command-creator' (also 'command-creator') is designed to help an AI agent create new slash commands by writing markdown files to `.claude/commands/` or `~/.claude/commands/`. The instructions in `SKILL.md` and related reference files (`best-practices.md`, `examples.md`, `patterns.md`) guide the agent through a structured process including determining location (`git rev-parse --is-inside-work-tree`), gathering user input, and generating the command file (`mkdir -p`, write file). While the generated commands can contain powerful shell commands, the skill itself does not exhibit malicious intent; its instructions are focused on creating these commands safely and effectively, even including 'NEVER' sections to prevent agent misbehavior. The `README.md` includes an `npx add` command for installation, which is a standard method for fetching external dependencies, not an instruction for the agent to execute maliciously.
能力评估
Purpose & Capability
The skill declares no env vars, no installs, and is instruction-only. Its guidance to check git state and write files to .claude/commands or ~/.claude/commands is consistent with a tool that creates slash-command markdown files.
Instruction Scope
The SKILL.md stays on-topic (how to design and write slash-command files) but includes templates and examples that instruct agents to run and automate repository-changing operations (git add/commit, make all-ci, gt submit, Edit tool, TodoWrite, Task tool). This is expected for commands that themselves will perform CI/git actions, but users should be aware generated commands may execute or propose file edits and CI runs — review them before invocation.
Install Mechanism
No install spec and no code files with executable installs are present (instruction-only). This minimizes disk/installation risk.
Credentials
The skill requests no environment variables or credentials. References to tools (git, make, gt, Bash tool, Edit/Read tools, TodoWrite, Task tool) are plausible for creating/testing commands; no unrelated secrets are requested.
Persistence & Privilege
always:false and no instructions to modify other skills or system-wide agent settings. The skill instructs creating files under project or user-level .claude directories only, which is appropriate for its purpose.
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 doro-command-creator
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /doro-command-creator 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 release of doro-command-creator - Enables users to create and manage reusable slash commands for workflow automation. - Guides users step-by-step: location detection, pattern selection, input gathering, command generation, file creation, and optional testing. - Provides best practices for command structure, clarity, specificity, and error handling. - Includes command pattern references, quality checklist, and writing guidelines for consistent results. - Supports both project-specific and global command storage, with automatic suggestions.
元数据
Slug doro-command-creator
版本 1.0.0
许可证
累计安装 1
当前安装数 1
历史版本数 1
常见问题

Doro Command Creator 是什么?

WHAT: Create Claude Code slash commands - reusable markdown workflows invoked with /command-name. WHEN: User wants to create, make, or add a slash command. U... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 477 次。

如何安装 Doro Command Creator?

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

Doro Command Creator 是免费的吗?

是的,Doro Command Creator 完全免费(开源免费),可自由下载、安装和使用。

Doro Command Creator 支持哪些平台?

Doro Command Creator 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 Doro Command Creator?

由 Mus Titou(@a2mus)开发并维护,当前版本 v1.0.0。

💬 留言讨论