Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →xu-xiang/plankton-code-quality
使用 Plankton 实现编写时代码质量强制执行 —— 通过钩子在每次文件编辑时进行自动格式化、代码检查，并由 Claude 驱动自动修复。
Passed 21 of 21 test cases with the skill, and 10 of 21 without it.
and 17 more in the full report
12 fixed10 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
For validating Dockerfile syntax and best practices within containerized repository setups, which linter utility is specified and what minimum version is required?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies hadolint as the Dockerfile linter | Passed | Passed |
| Requires hadolint version 2.12.0 or higher | Missed | Passed |
The instructions your model reads when the skill loads.
Plankton（感谢 @alxfazio）的集成参考，这是一个针对 Claude Code 的编写时（Write-time）代码质量强制执行系统。Plankton 通过工具调用后钩子（PostToolUse hooks）在每次文件编辑时运行格式化程序和 Linter，然后启动 Claude 子进程（Subprocess）来修复智能体（Agent）未捕捉到的违规项。
每当 Claude Code 编辑或写入文件时，Plankton 的 multi_linter.sh 工具调用后钩子（PostToolUse hook）就会运行：
阶段 1: 自动格式化 (静默)
├─ 运行格式化程序 (ruff format, biome, shfmt, taplo, markdownlint)
├─ 静默修复 40-50% 的问题
└─ 不向主智能体输出任何内容
阶段 2: 收集违规项 (JSON)
├─ 运行 Linter 并收集无法自动修复的违规项
├─ 返回结构化 JSON: {line, column, code, message, linter}
└─ 仍不向主智能体输出任何内容
阶段 3: 委派 + 验证
├─ 启动带有违规 JSON 的 claude -p 子进程
├─ 根据违规复杂性路由到不同层级的模型：
│ ├─ Haiku: 格式化、导入、样式 (E/W/F 代码) — 120s 超时
│ ├─ Sonnet: 复杂性、重构 (C901, PLR 代码) — 300s 超时
│ └─ Opus: 类型系统、深度推理 (unresolved-attribute) — 600s 超时
├─ 重新运行阶段 1+2 以验证修复结果
└─ 如果清理完成则 Exit 0，如果仍存在违规项则 Exit 2（报告给主智能体）
test cases passed, vs 10 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.