代码格式化

format

by BytesAgain

Auto-format source code with language detection, presets, and diff preview. Use when formatting code, enforcing styles, or batch-formatting projects.

4.5k编码与调试未扫描2026年3月23日

安装

claude skill add --url github.com/openclaw/skills/tree/main/skills/bytesagain/format

文档

Format

Developer toolkit for checking, validating, formatting, linting, converting, and managing code and text entries. All operations are logged with timestamps and stored locally for full traceability.

Commands

CommandUsageDescription
checkformat check <input>Record a check entry or view recent checks
validateformat validate <input>Record a validation entry or view recent validations
generateformat generate <input>Record a generate entry or view recent generations
formatformat format <input>Record a format entry or view recent formatting operations
lintformat lint <input>Record a lint entry or view recent lint results
explainformat explain <input>Record an explain entry or view recent explanations
convertformat convert <input>Record a convert entry or view recent conversions
templateformat template <input>Record a template entry or view recent templates
diffformat diff <input>Record a diff entry or view recent diffs
previewformat preview <input>Record a preview entry or view recent previews
fixformat fix <input>Record a fix entry or view recent fixes
reportformat report <input>Record a report entry or view recent reports
statsformat statsShow summary statistics across all entry types
export <fmt>format export json|csv|txtExport all entries to JSON, CSV, or plain text
search <term>format search <term>Search across all log files for a keyword
recentformat recentShow the 20 most recent history entries
statusformat statusHealth check — version, entry count, disk usage, last activity
helpformat helpShow help with all available commands
versionformat versionPrint version string

Each command (check, validate, generate, format, lint, explain, convert, template, diff, preview, fix, report) works the same way:

  • With arguments: Saves the input with a timestamp to <command>.log and logs to history.log.
  • Without arguments: Displays the 20 most recent entries from <command>.log.

Data Storage

All data is stored locally at ~/.local/share/format/:

  • <command>.log — Timestamped entries for each command (e.g., check.log, lint.log)
  • history.log — Unified activity log across all commands
  • export.json, export.csv, export.txt — Generated export files

No cloud, no network calls, no API keys required. Fully offline.

Requirements

  • Bash 4+ (uses set -euo pipefail)
  • Standard Unix utilities (date, wc, du, grep, head, tail)
  • No external dependencies

When to Use

  1. Logging code review notes — Use format check or format lint to record issues found during code reviews, keeping a timestamped trail of findings.
  2. Tracking format and conversion tasks — Use format convert and format format to log what was converted or reformatted, building an audit trail.
  3. Generating reports from logged data — Use format report to record report items, then format export json to extract structured data for dashboards or further processing.
  4. Searching past operations — Use format search <term> to find specific entries across all log files when you need to recall what was done previously.
  5. Monitoring toolkit health — Use format status to verify the tool is operational, check disk usage, and see when the last activity occurred.

Examples

bash
# Record a check entry
format check "validate JSON schema for config.yaml"

# Record a lint finding
format lint "unused import in main.go line 42"

# View recent format operations (no args = list mode)
format format

# Convert and log the action
format convert "CSV to JSON for user_data.csv"

# Generate a diff note
format diff "comparison between v1.2 and v1.3 API responses"

# Search all logs for a keyword
format search "config"

# Export everything to JSON
format export json

# View summary statistics
format stats

# Health check
format status

# View recent activity
format recent

How It Works

Format stores all data locally in ~/.local/share/format/. Each command logs activity with timestamps in the format YYYY-MM-DD HH:MM|<input>, enabling full traceability. The unified history.log records every operation with MM-DD HH:MM <command>: <input> format for cross-command auditing.


Powered by BytesAgain | bytesagain.com | hello@bytesagain.com

相关 Skills

前端设计

by anthropics

Universal
热门

面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。

想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。

编码与调试
未扫描139.0k

网页应用测试

by anthropics

Universal
热门

用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。

借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。

编码与调试
未扫描139.0k

网页构建器

by anthropics

Universal
热门

面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。

在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。

编码与调试
未扫描139.0k

相关 MCP 服务

GitHub

编辑精选

by GitHub

热门

GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。

这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。

编码与调试
86.1k

by Context7

热门

Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。

它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。

编码与调试
55.8k

by tldraw

热门

tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。

这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。

编码与调试
47.1k

相关资讯

Web2BigTable 提出一种双层多智能体框架,上层协调器将任务分解为子问题,下层工作智能体并行执行,通过运行-验证-反思闭环和共享工作空间,实现覆盖广、一致性高的结构化信息提取。在 WideSearch 基准上,其 Avg@4 成功率 38.50(远超第二名 5.10),Row F1 达 63.53,Item F1 达 80.12,并在深度搜索任务中展现泛化能力。

深度·5月6日·61 分钟

仅通过10.6k数据点的简单SFT训练,OpenSeeker-v2在4个基准上刷新了30B级别搜索智能体的最优性能,超越了采用大规模预训练+强化学习流水线的商业系统。其关键在于三种数据合成策略:扩展知识图谱规模、扩大工具集以及严格低步过滤。

深度·5月6日·12 分钟

Claude Mythos 确实发现了真实漏洞,但媒体报道严重偏离事实。漏洞发现依赖多智能体管道而非纯模型能力,且更小更便宜的模型也能复现部分结果。此次发布与 Anthropic 的 IPO 计划紧密相关,存在明显的叙事操控。

深度·4月18日·5 分钟

评论