#documentation

Project memory system for AI coding assistants (Claude Code, Cursor, Codex): session logs, project wiki, rules, TODOs, and handoff.

Turn feature requests into review-ready pull requests: issue, implementation, tests, a review-and-fix loop, and docs. Runs locally or on GitHub Actions, and is built for complex brownfield repos. Each week its retrospective reads what you actually merged and proposes improvements to your skill extensions.

AILmanac — the always-current, community almanac for getting the most out of Claude and every AI. For all levels.

一个简单好用的 context 分层管理工具：遵循 CoALA 认知架构，兼容 Matt Pocock skills，配合工程执行 skill 使用，1+1>2

PLC, Arduino IDE compatible, fully programmable by AI.

GitHub repo 展示层管家 Claude Skill — 一句『按 X 风格写 README』或『把这个推到 GitHub』 → 三件套(README 17 段重写 / 公式化 100 字描述 / 6 类 10-15 个 topic 加标) + 两可选附加步(⓪ Bootstrap 全新目录一键 git init + gh repo create + push / ④ LICENSE 自动补全),与 8+ git 操作向 skill 严格分工,专填 repo 展示层空白

8 款生产级 AI Agent Skill：持久记忆、代码安全评审、自然语言数据分析、调试复现、测试生成、IaC 安全扫描、性能诊断、文档生成 | 8 production-ready agent skills (memory, code-review security, NL data analysis, agentic debugger, testforge, iac-guard, perf-doctor, docsmith). Pure Python stdlib, zero dependencies.

Index Any Local Documentation as AI Skill – Claude Code Knowledge 2026

A bilingual Claude Code skill set for diagram-first system understanding, with one main workflow skill and one companion orchestration/reference skill.

Repository-native Work, Docs, History and durable Memory for humans and AI agents — Markdown as the source of truth, with a local UI, CLI and MCP server

turn the docs your agent writes into something worth reading. rust cli + claude code skill that renders markdown to polished html with a structured visuals sidecar.

A reusable AI-first development framework for building software with AI agents.

🪶 Modern JMeter docs with search, theme, and more

Turn Claude Code into a team that has to prove it. 44 skills, 8 review agents, a validation router and a knowledge layer where nothing is claimed without a check that could have failed.

从零理解 OpenAI Codex Coding Agent：Agent Loop、Runtime、Context、Tool、安全边界与源码实现。

A Claude Code skill that generates README, architecture docs, API reference, onboarding guides, deployment docs, and ADRs from an existing codebase.

APICheck：AI API 中转站单次检测与服务商参考排行平台（源代码未公开）

BeforeCode — Spec-first software planning toolkit for humans and AI coding agents.

Shared engineering rules, agent instructions, API standards, Laravel/Next.js patterns, testing rules, and reusable project checklists for all AI-powered portfolio systems.

AI 编程工具与客户端的 CodeFlow API 中文配置指南

Install a reasoning layer at the point of creation: one-line intent notes that tell AI (and humans) WHY code, plans, and content exist. Claude Code drop-in + tool-agnostic convention.

Reusable framework for requirements work: BRD/NFR/ADR templates, quality rules, and agent skills that draft and review requirements against them. Templates and prompts stay in sync by design.

Claude Code plugin: architecture reference docs (DESIGN.md + docs/design/) stamped to commits, with verify/query/changelog/critique/runbooks/onboarding, a greenfield design interview, and product-discovery mockups

A suite of Claude Code skills that keep a project's record, roadmap, docs and tooling honest — a secretary to coding, not the coder.

Traefik v3.7 documentation converted to LLM-friendly Markdown (llms.txt, llms-full.txt, per-page files), rebuilt automatically when upstream changes.

Make technical Markdown read like a story — semantic visuals, memes, reveals, and agent Skills without HTML bloat.

Diagrams as D2 source rendered to PNG, so the picture lives in git next to the code. A skill for Claude Code, Opencode and Codex.

Agent skill that scaffolds a repository so coding agents navigate it from committed docs — AGENTS.md doc index, docs/ standards, and commit-time gates.

Your documentation makes claims. This checks whether they are still true, against git and the filesystem. Dead commit references, false merge claims, broken links, tags that never shipped, files that contradict each other. Works on the README you already have.

Top Free Context Engineering Plugin 2026 - Claude Code, Cursor & Codex Setup

A Claude Code skill that writes and reviews your README.

[ENG]An AI agent skill that automates document updates when adding external libraries. / [JPN]外部ライブラリ追加時のドキュメント更新を自動化するAIエージェント用スキル

Lint the documentation & metadata quality of VGI (Vector Gateway Interface) data workers — descriptions, column comments, tags, and example queries — with a quality score, per-version baselines, and agent-friendly output.

Unofficial CureMD documentation hub — a community field guide and AI-assistant skills for the CureMD EHR: FHIR API, HL7, USCDI, SMART-on-FHIR, integration channels, and compliance. Compiled from CureMD's public docs.

org + origami — weekly pull request recaps and an evidence-backed map of a GitHub organization's repos, deploy tooling and servers, in the terminal, in git, and as Claude Code context.

Website for agent-passport.org — the Agent Passport System protocol. Hosted on GitHub Pages.

Connect LLM agents to your WireBoard analytics data using the Model Context Protocol for real-time and historical project insights.

Source-grounded knowledge maps for humans and agents.