simplify

作者: huggingface

測試通過後重構程式碼。紅-綠-重構中的「重構」階段。

npx skills add https://github.com/huggingface/openenv --skill simplify

/simplify

Refactor and clean up code after tests pass.

Usage

/simplify
/simplify src/openenv/core/client.py

When to Use

  • After /implement makes tests pass
  • When code is correct but could be cleaner
  • Before creating a PR (optional polish step)

When NOT to Use

  • Tests are failing (fix tests first)
  • You want to add new functionality (use /write-tests first)
  • Code is already clean and simple

What It Does

  1. Runs tests to ensure they pass (baseline)
  2. Identifies opportunities for simplification
  3. Refactors while keeping tests green
  4. Runs tests after each change to verify nothing broke

Philosophy

This is TDD's third phase: Red → Green → Refactor.

The goal is NOT to add features or change behavior. The goal is to make the code:

  • Easier to read
  • Easier to maintain
  • More consistent with project patterns
  • Less code

Guidelines

Good Simplifications

  • Inline needless helpers and indirection (see Simplicity in CLAUDE.md)
  • Rename variables for clarity
  • Remove dead code
  • Simplify complex conditionals
  • Use more Pythonic idioms

NOT Simplifications (Avoid)

  • Adding new features
  • Changing public APIs
  • "Improving" code that works and is readable
  • Adding abstractions for hypothetical future needs

Completion Criteria

  1. All tests still pass
  2. Code is cleaner/simpler than before
  3. No new functionality was added
  4. Changes follow project patterns (see PATTERNS.md)

Integration with TDD Workflow

/write-tests  →  create failing tests (Red)
    ↓
/implement    →  make tests pass (Green)
    ↓
/simplify     →  clean up code (Refactor)
    ↓
/pre-submit-pr   →  validate before PR

來自 huggingface 的更多技能

sync-models
huggingface
將 chat-ui 的模型配置與 HuggingFace 路由器同步——為新模型新增描述、標記具備推理能力的模型、為 32B 以上的模型啟用 artifacts…
custom-blocks
huggingface
Use when the user has written (or wants to write) a `ModularPipelineBlocks` subclass in a local Python file and needs to package it into a Hub-uploadable…
self-review
huggingface
Use before opening a PR, or whenever asked to self-review a diffusers contribution. Applies the same rubric as the `@claude` CI (checks the diff against…
hf-cloud-sagemaker-production-defaults
huggingface
建立一個啟用自動擴展、CloudWatch 警報和標籤功能的 SageMaker 端點(即時或非同步)。每當即將建立…時,請使用此技能。
hf-cloud-serving-image-selection
huggingface
為 SageMaker 模型部署選擇合適的服務容器,並找出其目前的映像 URI。每當要將模型部署到…時,請使用此技能。
Hugging Face Cli
huggingface
Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute jobs on HF infrastructure. Covers authentication, file transfers, repository creation, cache operations, and cloud compute.
Hugging Face Datasets
huggingface
在 Hugging Face Hub 上建立與管理資料集。支援初始化儲存庫、定義配置/系統提示、串流更新資料列,以及基於 SQL 的資料集查詢/轉換。設計與 HF MCP 伺服器搭配使用,以實現完整的資料集工作流程。
Hugging Face Evaluation
huggingface
在 Hugging Face 模型卡中新增與管理評估結果。支援從 README 內容中提取評估表格、從 Artificial Analysis API 匯入分數,以及使用 vLLM/lighteval 執行自訂模型評估。可搭配 model-index 中繼資料格式使用。