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/Git & Pull Requests
telagod avatar

Analyzing Changes

telagod/code-abyss

This is a pre-commit gate that tells you if your code changes are missing documentation updates. It categorizes files into code/docs/tests/config, flags when you've changed over 50 lines without touching DESIGN.md, and warns if new files don't have README entries. Works in three modes: working (self-check while coding), staged (before commit), and committed (post-mortem review). The thresholds are opinionated but sensible: 30+ lines without test updates gets flagged, and it'll yell at you for config changes without migration notes. Not a replacement for actual code review, just automated bookkeeping to catch documentation drift before it becomes archaeology work six months later.

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

Install

$ npx -y skills add telagod/code-abyss --skill analyzing-changes --agent claude-code

Installs into .claude/skills of the current project.

Files

变更校验关卡

看清「改了什么、影响哪里、文档是否跟上」——是变更的体检,不是审查替代品。

何时使用

场景跑判据
提交前(任何代码改动)✅默认门禁
重构完成✅评估辐射面
设计级改动✅DESIGN.md 是否同步
PR review✅替代手工 diff 计数
跨模块大改✅看依赖图是否成环
紧急 hotfix⚠跑,但允许文档同步延后到稳定后

三种模式

模式时机用途
working (默认)写代码过程中自检,看「我现在的工作面有哪些待整理」
stagedgit add 后、commit 前提交闸,看「这一 commit 的合理性」
committedcommit 完成后review,看「上一段历史改了哪些范围」

警告判定

警告触发处置
代码 >50 行 而 DESIGN.md 未更新设计层面变化未留痕补 DESIGN.md「改了什么/为何」段
代码 >30 行 而无测试更新测试覆盖滞后补单测/集成测;或在 PR 注明「该路径已有 E2E 覆盖」
新增文件而 README.md 未更新用户视角文档滞后补模块入口说明
配置变更未记录部署可能踩坑CHANGELOG / DESIGN 留迁移说明
删除文件引用可能未清理全仓 grep 文件名/导出符号

解读输出

工具产出三类信号:

  1. 文件分类 — 自动分代码/文档/测试/配置;用于判断「是否纯文档变更」
  2. 模块识别 — 把变更聚到模块边界;用于判断「跨模块改动」
  3. 影响评估 — 行数 + 文件数;用于判断「改动是否需要拆 PR」

拆 PR 的判据(基于 commit 角度):

  • 跨 ≥3 模块且无统一主题 → 拆
  • 单 commit >500 行非生成代码 → 拆
  • 一次同时改架构 + 实现 + 文档 → 通常合理(同主题)

与其他 skill 联动

  • 设计级变更 → 触发 verifying-modules 看新模块文档完整性
  • 安全相关变更 → 触发 analyzing-security
  • 重构 → 触发 checking-code-quality 防退化

使用

node scripts/change_analyzer.js                   # working(默认)
node scripts/change_analyzer.js --mode staged     # 暂存区
node scripts/change_analyzer.js --mode committed  # 已提交
node scripts/change_analyzer.js -v                # 详细
node scripts/change_analyzer.js --json            # CI 用

人工复核

工具给信号,人下结论。先读受影响模块 README/DESIGN,确认:

  • 职责边界是否仍清晰
  • 设计决策是否仍成立
  • 测试是否覆盖新路径

设计级改动须于 DESIGN.md 留痕:改了什么、为何改、影响何处。三段缺一不可。

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
Git & Pull Requests, Documentation, Code Review & Quality, Design & UI/UX
License
MIT
First seen
Jun 11, 2026

More from telagod/code-abyss

All 30
  • 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
  • Designing Hardware Products
  • Detecting And Responding
  • Developing Mobile Apps
  • Developing Software
  • Engineering Data Pipelines
  • Generating Docs
  • Indexing Code
  • Operating Kicad Eda
  • Orchestrating Adversarial Reviews
  • Processing Docx
  • Processing Pdfs
  • Provisioning Infrastructure

Recommended

More Git & Pull Requests
1telagod avatarautomating-devopstelagod/code-abyssDevOps knowledge reference covering Git workflows, testing strategies, DevSecOps, release pipeline orchestration (release.yml, multi-arch images, cosign integra0installs
2telagod avatarorchestrating-adversarial-reviewstelagod/code-abyssMulti-agent adversarial-verification orchestration for high-confidence conclusions. Fan-out finders, then verify every finding through a three-prism panel (expl0installs
3TencentCloudBase avatardocs-workflowsTencentCloudBase/CloudBase-AI-ToolkitDocumentation and extension workflows derived from local slash commands (docs, explanation, issues, prototypes, tutorials, MCP design review).0installs
4thinkinaixyz avatardeepchat-releasethinkinaixyz/deepchatPrepare and publish DeepChat releases in this repository. Use when Codex needs to bump the app version, update CHANGELOG.md, keep release notes bilingual from v0installs
5thinkinaixyz avatardeepchat-sddthinkinaixyz/deepchatUse for any DeepChat code, configuration, documentation, feature, issue fix, refactor, or architecture change before implementation. This skill enforces the pro0installs
6UKGovernmentBEIS avatarcode-quality-fix-allUKGovernmentBEIS/inspect_evalsFix code quality issues identified in a code quality review stored in agent_artefacts/code_quality/<topic>/. Systematically addresses issues found by the code-q0installs