Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Python 开发规范 — measured AI agent skill | DecimalAI

doccker/python-dev

SkillScore100Maintained

Python 开发规范，包含 PEP 8 风格、类型注解、异常处理、测试规范等

codingby doccker

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

decimalai skills pull doccker-python-dev

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/doccker-python-dev/SKILL.md

Raw file: /s/doccker-python-dev/SKILL.md ↗ · machine-readable summary at /s/doccker-python-dev.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 1h ago

Yes — +14% lift-14% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-08	✗→✓	▲ Improved	-16%	0%
case-01	✗→✓	▲ Improved	-18%	0%
case-09	✗→✓	▲ Improved	-18%	0%
case-02	✓→✓	＝ Same ✓	-20%	0%
case-03	✓→✓	＝ Same ✓	-14%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

doccker / cc-use-exp

skills/python-dev/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v3

Skill contents

SKILL.md

<instructions>

Python 开发规范

> 参考来源: PEP 8、Google Python Style Guide

🛠️ 工具链与格式化

Black 为强制格式化标准。
Ruff 为首选代码静态检查工具（其速度极快且涵盖广泛规则）。
MyPy / Pyright 用于强制类型检查。

命名约定

| 类型 | 规则 | 示例 | |------|------|------| | 模块/包 | 小写下划线 | user_service.py | | 类名 | 大驼峰 | UserService | | 函数/变量 | 小写下划线 | get_user_by_id | | 私有方法 | 单下划线前缀 | _internal_logic |

🐍 Pythonic 特色

类型注解 (Type Hinting)：所有公开接口必须定义类型。Python 3.10+ 优先使用 | 表示联合类型（Union）。
生成器 (Yield)：大数据处理必须使用生成器以降低内存消耗。
上下文管理器：文件/连接/锁定操作必须使用 with 语句。

异步编程原则

并发获取多个 I/O 密集任务时，使用 asyncio.gather(*tasks)。
必须为并发量大的异步任务设置信号量 asyncio.Semaphore(limit)。
耗时的 CPU 密集任务必须使用 multiprocessing 剥离，防止阻塞 Event Loop。

异常处理

python
# ✅ 捕获具体异常并记录堆栈
try:
    user = repository.find(id)
except DatabaseError as e:
    logger.error("Failed to find user %s", id, exc_info=True)
    raise ServiceError(f"DB error: {e}") from e

> 📋 本回复遵循：python-dev - 章节]

</instructions>

Want to see if doccker/python-dev would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.