skill-creator-plus

Skill Creator Plus

An enhanced skill creation wizard based on the official skill-creator, with built-in compliance check rules, supporting two usage modes:

Usage Modes

Mode 1: Creation Mode

Used when creating a new skill, following this process:

Understand the skill requirements (collect concrete examples)
Plan reusable resources (scripts/, references/, assets/)
Initialize the skill (create the directory structure)
Edit the skill (implement resources + write SKILL.md)
Compliance check (built-in check rules)
Iterate (improve based on usage feedback)

Mode 2: Review Mode

Used when reviewing the compliance of an existing skill:

Specify the skill path to review
Scan the directory structure and files
Review item by item according to the checklist
Generate a structured review report

Mode 1: Creation Mode

Step 1: Understand the skill requirements

Conditions for skipping this step: the skill's usage pattern is already very clear.

Collect concrete usage examples:

"What functionality should this skill support?"
"Can you give some concrete usage scenarios?"
"What would users say to trigger this skill?"

Completion criteria: clearly know the skill's functional boundaries and trigger scenarios.

Step 2: Plan reusable resources

Analyze each usage scenario to determine the required resources:

Resource types

Type	Directory	Purpose	When needed
Scripts	`scripts/`	Executable code	When the same code is rewritten repeatedly
References	`references/`	Detailed documentation	When schema/API documentation is needed
Assets	`assets/`	Output templates	When templates/icons/fonts are needed

Directory structure specification

Follow this structure when creating:

skill-name/
├── SKILL.md          # 必需 - 主文档
├── LICENSE.txt       # 推荐 - 许可证
├── references/       # 可选 - 参考文档
├── scripts/          # 可选 - 可执行脚本
└── assets/           # 可选 - 输出资源

Prohibited to create：

README.md - Duplicates SKILL.md
docs/ - Should use references/
test/ - Development files should not be in the release version
__pycache__/ - Python cache should not be committed
.env - Sensitive configuration should not be committed

Step 3: Initialize the skill

Create the skill directory and basic files:

Create skill directory <skill-name>/
Create SKILL.md and add frontmatter
Create LICENSE.txt(recommended)
Create the required subdirectories (scripts/, references/, assets/）

Step 4: Edit the skill

4.1 Frontmatter specification

---
name: skill-name                    # 小写字母 + 连字符
description: 功能描述。本技能应在...时使用  # 第三人称 + 触发场景
license: CC BY-NC-SA 4.0 - 详见 LICENSE.txt
---

description writing requirements：

Use third person: "This skill should be used when..."
Include trigger scenarios: clearly state when to use it
Keep the length within 100 characters
Do not add a "When to use" section in the SKILL.md body

Prohibited fields：

version - Version information should be managed in CHANGELOG.md

4.2 SKILL.md Content Specifications

Keep It Concise：

Avoid large blocks of code (>20 lines should be moved to scripts/）
Use concise examples, showing only key API calls
Focus on the workflow, explaining "what to do" and "how to do it"

Progressive Disclosure：

Core process in the SKILL.md body
Detailed documentation placed in references/ in
Reference references files in SKILL.md

4.3 Configuration File Specifications

Naming Rules：

Type	Format	Whether to Commit
Template file	`.example.`	Commit
Actual configuration	`*`	Ignored by .gitignore

Example:

config.example.yaml → Commit
config.yaml → Ignore
.env.example → Commit
.env → Ignore

4.4 Output Mode Specifications

For skills that require consistent output, provide output format guidance.

Strict Mode(API responses, data formats):

ALWAYS use this exact template structure:

# [Analysis Title]

## Executive summary
[One-paragraph overview]

## Key findings
- Finding 1 with supporting data
- Finding 2 with supporting data

Flexible Mode(analysis reports, creative content):

Here is a sensible default format, but use your best judgment:

# [Analysis Title]

## Executive summary
[Overview]

Adjust sections as needed for the specific context.

4.5 Workflow Mode Specifications

Sequential Workflow：

Filling a PDF form involves these steps:

1. Analyze the form (run analyze_form.py)
2. Create field mapping (edit fields.json)
3. Validate mapping (run validate_fields.py)
4. Fill the form (run fill_form.py)

Conditional Workflow：

1. Determine the modification type:
   **Creating new content?** → Follow "Creation workflow" below
   **Editing existing content?** → Follow "Editing workflow" below

2. Creation workflow:
   - Step 1: ...
   - Step 2: ...

4.6 Skill Collaboration Specifications

Loose Coupling Principle：

Describe collaboration scenarios in natural language
Explain what the skill "does" and "how it cooperates"
Do not directly reference the internal script paths of other skills
Do not import modules from other skills in code

Recommended approach：

## 与其他技能配合

下载的视频可以使用 FunASR 技能转录为带时间戳的 Markdown 文件。
两个技能独立运行，可根据需要灵活组合使用。

Approach to avoid：

## 与其他技能配合

转录时运行：
python ../../skills/funasr-transcribe/scripts/transcribe.py

4.7 Orchestration Design

For skills that may participate in complex workflow orchestration:

Input/Output Declaration：

## 输入/输出

### 输入
- 必需：`--input` 参数说明
- 可选：`--flag` 参数说明

### 输出
- 输出文件：`output/path.md` 说明
- 副作用：如创建目录、修改文件等

Single Responsibility：

The skill does only one thing
Avoid mixing multiple tasks

Idempotency：

The result is the same when executed multiple times
No cumulative effect

Step 5: Compliance Check

Before packaging, check each item according to the following checklist:

5.1 Directory Structure

Check Item	Status
SKILL.md exists	✅/❌
No README.md	✅/⚠️
No docs/ directory	✅/⚠️
No test/ directory	✅/⚠️
None pycache/	✅/❌
No .env file	✅/❌

5.2 Frontmatter

Check Item	Status
name field exists and is correctly formatted	✅/❌
description field exists	✅/❌
description uses third person	✅/❌
description includes negative trigger conditions	✅/⚠️
description length ≤ 1024 characters	✅/❌
No version field	✅/⚠️

5.3 SKILL.md Line Count

Check Item	Status
SKILL.md line count ≤ 500 lines	✅/⚠️

5.4 Directory Hierarchy

Check Item	Status
references/ flat structure (one level)	✅/⚠️
scripts/ flat structure (one level)	✅/⚠️
assets/ flat structure (one level)	✅/⚠️

5.5 Documentation Consistency

Check Item	Status
Referenced script files exist	✅/❌
Referenced reference documents exist	✅/❌
Referenced resource files exist	✅/❌

5.6 Configuration Files

Check Item	Status
Template uses .example. naming	✅/⚠️
example field matches the code	✅/❌

5.7 Skill Collaboration

Check Item	Status
Does not directly reference other skill paths	✅/⚠️
Uses natural language to describe collaboration	✅/⚠️

5.8 Modular Design

Check Item	Status
Independent functionality is decoupled into separate scripts	✅/⚠️
Does not directly call internal scripts across skills	✅/⚠️

5.9 Security Audit

Check Item	Status
No hardcoded API keys	✅/❌
No dangerous delete commands (rm -rf ~, etc.)	✅/❌
Delete commands use a safe method	✅/⚠️

Issue Severity：

Level	Description	Handling
❌ Critical	Blocks normal use of the skill	Must fix
⚠️ Warning	Affects maintainability	Recommended to fix

Step 6: Iteration

Improve the skill based on feedback from actual use:

Use the skill to handle real tasks
Identify difficulties or efficiency issues
Update SKILL.md or related resources

Mode 2: Review Mode

Review the compliance of an existing skill and generate a structured review report.

Review Process

Specify the target - Provide the path of the skill to review
Scan files - List all files in the skill directory
Check item by item - Review according to the checklist (using the same rules as Step 5)
Generate report - Output structured review results

Review Report Format

# [skill-name] 格式审查报告

**审查时间**: YYYY-MM-DD HH:MM
**技能路径**: /path/to/skill

## 审查摘要

| 检查项 | 状态 | 问题数 |
|--------|------|--------|
| 目录结构 | ✅/⚠️/❌ | N |
| Frontmatter | ✅/⚠️/❌ | N |
| SKILL.md 行数 | ✅/⚠️ | N |
| 目录层级 | ✅/⚠️ | N |
| 文档一致性 | ✅/⚠️/❌ | N |
| 配置文件 | ✅/⚠️/❌ | N |
| 技能协作 | ✅/⚠️/❌ | N |
| 模块化设计 | ✅/⚠️ | N |
| 安全审计 | ✅/❌ | N |

## 详细问题

### ❌ 严重问题（必须修复）

1. **[问题标题]**
   - 位置: `文件路径:行号`
   - 规范: 违反的规范条款
   - 建议: 修复建议

### ⚠️ 建议优化

1. **[问题标题]**
   - 位置: `文件路径`
   - 建议: 优化建议

## 审查完成

- 总问题数: N
- 严重问题: N
- 建议优化: N

How to Execute the Review

Use Glob to list all files in the skill directory
Use Read to read SKILL.md and key files
Review item by item according to the Step 5 checklist
Generate a structured review report

Specification Reference

For detailed specification standards, see references/skill-standards.md

About this skill

Usage Modes

Mode 1: Creation Mode

Mode 2: Review Mode

Mode 1: Creation Mode

Step 1: Understand the skill requirements

Step 1: Understand the skill requirements

Step 2: Plan reusable resources

Resource types

Directory structure specification

Step 3: Initialize the skill

Step 4: Edit the skill

4.1 Frontmatter specification

4.2 SKILL.md Content Specifications

4.3 Configuration File Specifications

4.4 Output Mode Specifications

4.5 Workflow Mode Specifications

4.6 Skill Collaboration Specifications

4.7 Orchestration Design

Step 5: Compliance Check

5.1 Directory Structure

5.2 Frontmatter

5.3 SKILL.md Line Count

5.4 Directory Hierarchy

5.5 Documentation Consistency

5.6 Configuration Files

5.7 Skill Collaboration

5.8 Modular Design

5.9 Security Audit

Step 6: Iteration

Mode 2: Review Mode

Review Process

Review Report Format

How to Execute the Review

Specification Reference