Claude Marketplaces
SkillsMCP serversMarketplacesDigestTools
Submit

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index

Site

  • About
  • Tools
  • Submit
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
Crafted at
Skills/Documentation
telagod avatar

Generating Docs

telagod/code-abyss

This generates README and DESIGN scaffolds for new modules by analyzing directory structure, dependencies, and code signatures. It's automatic, not user-invoked, so it runs right after module creation to give you templates while decisions are fresh. The Python support is strongest (pulls docstrings, class signatures), while other languages get directory trees and dependency lists. The key insight here is brutally honest: it fills the easy parts like module names and file lists, but leaves TODO placeholders for everything that matters, like why you made specific design choices or what you deliberately chose not to build. The source is clear that leaving those TODOs unfilled past a day means you'll forget the reasoning and documentation quality tanks. Supports a force flag but warns against using it if humans have already written content.

GitHub stars
224
last updated
Jun 10, 2026
View on GitHubSave

Install

$ npx -y skills add telagod/code-abyss --skill generating-docs --agent claude-code

Installs into .claude/skills of the current project.

Files

造典关卡 · 文档生成器

生成的是骨架,不是答案。填决策理由是人的工作,工具不能代劳。

何时使用

场景跑理由
新模块创建后第一时间✅趁记忆新鲜填决策
verifying-modules 报「缺 README/DESIGN」✅直接补救
重构后边界变化⚠看是否要重生成或手动改;不要 --force 覆盖已有内容
已有完整文档❌不要破坏人工写的内容

生成内容

README.md(自动可填部分)

字段自动来源待人补
模块名目录名是否有更好的展示名
描述顶级 docstring(Python)「存在理由」必须人写
特性TODO(占位)列 3–5 个核心能力
依赖requirements.txt / package.json / Cargo.toml 等是否有运行时假设
使用方法TODO(占位)5 分钟跑通示例
API 概览公开类/函数签名调用顺序、生命周期
目录结构tree 输出—

DESIGN.md(骨架占位)

字段自动待人补(最重要)
设计目标 / 非目标TODO核心决策驱动力
架构TODO含一张图最好
核心组件公开类/函数列表各组件的协作关系
决策表TODO方案对比 + 选择理由
技术选型依赖列表选 X 不选 Y 的理由
权衡TODO牺牲了什么
安全考量TODO信任边界、威胁模型

语言支持

语言提取深度
Python类、函数、docstring、依赖(最完整)
Go / TypeScript / Rust目录结构 + 依赖
其他基础目录结构

流程

doc_generator.js 生成骨架
        ↓
人工填 TODO(决策理由、使用示例、非目标)
        ↓
verify-module 校验完整性
        ↓
通过则提交

何时不要 --force

  • 目标文件已有人工内容 —— --force 会无差别覆盖。先 diff 旧版,手动合并。
  • CI 环境 —— 生成应在开发机做,CI 只校验,不生成。

与其他 skill 联动

  • 跑完后 → 必跑 verifying-modules
  • 大模块 → 拆分前先 designing-architectures 想清楚边界

使用

node scripts/doc_generator.js <模块路径>
node scripts/doc_generator.js <模块路径> --force   # 强制覆盖(慎用)
node scripts/doc_generator.js <模块路径> --json    # CI 用

收口

工具给骨架,TODO 不补完不算交付。生成后 5 分钟内人工填决策;超过 1 天会忘原因,文档质量陡降。

SKILL.md on GitHub

Sponsors

SnugThe clipboard manager you and your agent can use, safelyAgent CaffeineClose your lid, come back to finished workWaxBlock anything with supervision, without erasing your iPhoneOpen StepsSponsoredFree and open-source skills that make AI coding agents easier to understand, verify, and control.

Details

Repository
github.com/telagod/code-abyss
Categories
Documentation, Design & UI/UX
License
MIT
First seen
Jun 11, 2026

More from telagod/code-abyss

All 30
  • Indexing Code
  • Operating Kicad Eda
  • Orchestrating Adversarial Reviews
  • Processing Docx
  • Processing Pdfs
  • Provisioning Infrastructure
  • Reducing Aigc Detection
  • Securing Cloud And Supply Chain
  • Securing Systems
  • Shipping Changes
  • Verifying Modules
  • Analyzing Changes
  • Analyzing Security
  • Analyzing Spreadsheets
  • Applying Ui Design System
  • Architecting Security
  • Automating Devops
  • Building Agent Systems
  • Checking Code Quality
  • Creating Presentations
  • Cultivating Personas
  • Cultivating Skills
  • Defending Applications
  • Designing Architectures

Recommended

More Documentation
1thinkinaixyz avatardoc-coauthoringthinkinaixyz/deepchatGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs,0installs
2tldraw avatarwrite-docstldraw/tldrawWriting SDK documentation for tldraw. Use when creating new documentation articles, updating existing docs, or when documentation writing guidance is needed. Ap0installs
3google avataradk-dev-guidegoogle/adk-docsALWAYS ACTIVE — read at the start of any ADK agent development session. ADK development lifecycle and mandatory coding guidelines — spec-driven workflow, code p2.7Kinstalls
4google avataradk-eval-guidegoogle/adk-docsMUST READ before running any ADK evaluation. ADK evaluation methodology — eval metrics, evalset schema, LLM-as-judge, tool trajectory scoring, and common failur2.6Kinstalls
5google avataradk-deploy-guidegoogle/adk-docsMUST READ before deploying any ADK agent. ADK deployment guide — Agent Engine, Cloud Run, GKE, CI/CD pipelines, secrets, observability, and production workflows2.6Kinstalls
6google avataradk-observability-guidegoogle/adk-docsMUST READ before setting up observability for ADK agents or when analyzing production traffic, debugging agent behavior, or improving agent performance. ADK obs2.6Kinstalls