一键导入
documentation
Documentation standards for code, APIs, and project docs. Use when writing docstrings, README files, API docs, or any project documentation.
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。
菜单
Documentation standards for code, APIs, and project docs. Use when writing docstrings, README files, API docs, or any project documentation.
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
DEEP multi-step research harness. Decomposes queries into sub-questions, executes parallel web searches via Pieces MCP, iteratively refines with gap detection, and synthesizes cited reports. Architecture inspired by GPT Researcher (27.6k stars), Vane/Perplexica (35.2k stars), and Gemini Deep Research. Use when user asks for deep research, investigation, analysis, comparison, or any task requiring exhaustive web research.
DEFAULT THINKING MODE — not a feature, but how the agent operates. Every task gets innovation-overdrive thinking: research, ground, reflect on contradictions, propose, then build. This is the agent's identity, not a command. Integrates MiMo-Code's 6-phase memory consolidation.
Chain execution manager: validates dependencies, enforces order, tracks violations. Use to verify that all required skill chains were executed and to get the correct execution order.
API design patterns, REST conventions, and endpoint standards. Use when creating or modifying API endpoints. Covers routing, request/response patterns, error handling, and versioning.
Architectural design, system patterns, and dependency management. Use when designing new modules, refactoring existing systems, or making architectural decisions. Covers layering, coupling, cohesion, and design patterns.
Trigger-driven automation definitions and runner management. Use when creating, running, or managing skill-based automation pipelines.
| name | documentation |
| description | Documentation standards for code, APIs, and project docs. Use when writing docstrings, README files, API docs, or any project documentation. |
| chains_with | ["communication","automated-learning"] |
The next person to read this code. It might be you, 6 months from now, at 2 AM, with a production incident.
def function_name(param: type) -> return_type:
"""One-line summary.
Detailed description if needed (2-3 sentences max).
Args:
param: Description including units and constraints.
Returns:
Description including range and edge cases.
Raises:
ValueError: If param is out of valid range.
Examples:
>>> function_name(42)
84.0
"""
# BAD: What the code does (obvious from reading it)
x = x + 1 # Increment x by 1
# GOOD: Why the code does it (context for decision)
# Using 21-day window for short-term vol estimation
# (standard in risk mgmt for ~1 month trading days)
vol = returns.rolling(21).std()
# Project Name
## Overview
[One paragraph: what, why, who]
## Quick Start
[Install, configure, run — 30 seconds]
## Architecture
[Key components, data flow diagram]
## Usage
[Common commands, API examples]
## Testing
[How to run tests, coverage expectations]
## Contributing
[PR process, coding standards]
## License
Every API endpoint needs:
| Element | Rule |
|---|---|
| Headings | H1 for title, H2 for sections, H3 for subsections |
| Lists | Consistent bullet style (use - not *) |
| Code blocks | Always specify language: ```python |
| Tables | Aligned columns |
| Links | Descriptive text, not "click here" |
| Bold | For emphasis only |
| Images | Alt text required |
# Changelog
## [1.2.0] - 2026-05-27
### Added
- Quantum POC benchmark comparison
- Bootstrap confidence intervals for VaR
### Changed
- MC engine default scenarios from 1000 to 5000
### Fixed
- Stress VaR inversion edge case
- Import order in api_server.py
## [1.1.0] - 2026-05-20
### Added
- Backtesting validation (Kupiec, Christoffersen)
i++ # increment i)