菜单
Template for creating new skills in gptme-contrib. Use this as a starting point when creating your own skills.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | template-skill |
| description | Template for creating new skills in gptme-contrib. Use this as a starting point when creating your own skills. |
This is a minimal skill template demonstrating the basic structure of a gptme skill.
Skills are enhanced lessons that bundle:
Every skill needs:
Required fields:
type: skill - Distinguishes from lessonsname: skill-name - Skill identifier (must match directory name)description: ... - What the skill does and when to use itstatus: active - active, automated, deprecated, or archivedmatch: {keywords: [...]} - Trigger keywordsOptional fields:
scripts: [] - List of bundled Python scriptsdependencies: [] - Required Python packageshooks: [] - Execution hooks (future feature)The markdown body can include:
---
type: skill
name: my-skill
description: Brief description of what the skill does
status: active
match:
keywords: [keyword1, keyword2]
scripts: []
dependencies: []
---
# My Skill
Instructions for using this skill...
---
type: skill
name: data-analysis
description: Data analysis workflows with pandas and visualization
status: active
match:
keywords: [data analysis, pandas, visualization]
scripts:
- helpers.py
- plot_utils.py
dependencies:
- pandas
- matplotlib
---
# Data Analysis Skill
Use this skill for data analysis tasks...
## Bundled Scripts
- `helpers.py`: Common data manipulation functions
- `plot_utils.py`: Visualization utilities
## Usage
```python
# Import bundled helpers
from helpers import load_data, clean_data
from plot_utils import plot_distribution
# Analyze data
df = load_data("data.csv")
df = clean_data(df)
plot_distribution(df["column"])
## Integration with Lessons
Skills complement lessons:
- **Lessons**: Behavioral patterns and best practices (auto-included)
- **Skills**: Executable workflows with bundled tools (explicitly loaded)
Example:
- Lesson teaches: "Use type hints in Python"
- Skill provides: Type checking utilities and templates
## Related
- [Skills README](../README.md) - Skills system overview
Add foundational CS knowledge (7 classic books) and session-memory search to Claude Code or Claude Desktop via MCP. Lets Claude answer "how does X work?" by querying indexed books inline, and "what did we discuss about Y?" by searching past sessions. Use this skill when setting up or troubleshooting the rag-mcp-server.
Query a Home Assistant instance for presence, sensor data, calendar events, and cameras
Analyze your gptme conversation history for insights like token usage, costs, model preferences, and usage patterns — inspired by Spotify Wrapped.
Guide to creating gptme plugins with tools, hooks, and commands — covers ToolSpec, lifecycle hooks, custom /commands, testing, and pyproject.toml setup.
Conduct a structured interview about a new project and generate a ready-to-use CLAUDE.md/AGENTS.md starter so the agent knows your conventions from session one.
Use when creating or revising an agent's SOUL.md, splitting runtime voice out of broader identity docs, or tightening a vague persona file into a short, opinionated, voice-only artifact without changing the agent's core identity.