Skip to content
Back to search

everything-ai-coding

聚合精选编程 AI 扩展资源:MCP Servers、Skills、Rules、Prompts,周更索引 + 一键安装。

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/zgsm-ai/everything-ai-coding with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/zgsm-ai/everything-ai-coding'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/zgsm-ai--everything-ai-coding/badge.svg)](/listings/zgsm-ai--everything-ai-coding)

HTML

<a href="/listings/zgsm-ai--everything-ai-coding"><img src="/api/listings/zgsm-ai--everything-ai-coding/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

These steps run a script from the network that findsafeskills does not scan.

Install for your platform with one command:

**macOS / Linux**

# Costrict CLI (run from your project root)
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform costrict

# VSCode Costrict extension
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform vscode-costrict

# Claude Code
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform claude-code

# Opencode (run from your project root)
curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform opencode

**Windows (PowerShell)**

# Costrict CLI
irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1 | iex

# Specify the platform manually if auto-detection fails
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1))) -Platform costrict

After installation, try a search command:

# Claude Code
/eac:search typescript

# Opencode / Costrict CLI / VSCode Costrict (Roo Code)
/eac-search typescript

<video src="https://github.com/user-attachments/assets/e58f0b08-73c0-4fba-ac95-138c8087a917" controls width="100%"></video>

You can also hand the installation off to another agent with this prompt:

You are an installation assistant. Open the following URL, read the "For Agents" section,
and follow it exactly to install Everything AI Coding for the platform you are currently running on.

Do not clone the repository. Only read this raw file:
https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/README.md

After installation, report which platform path was used and whether verification succeeded.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 453 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <img src="assets/logo.png" alt="Everything AI Coding logo" width="600" />
  3. <p><strong><!-- README_APPROX_COUNT:START -->44000<!-- README_APPROX_COUNT:END -->+ curated AI coding resources — browse, evaluate, install</strong><br/>MCP Servers · Skills · Rules · Prompts · Plugins</p>
  4. <p>
  5. <a href="https://github.com/zgsm-ai/everything-ai-coding/stargazers"><img src="https://img.shields.io/github/stars/zgsm-ai/everything-ai-coding?style=flat-square&color=4A90D9" alt="Stars" /></a>
  6. <a href="https://github.com/zgsm-ai/everything-ai-coding/blob/main/LICENSE"><img src="https://img.shields.io/github/license/zgsm-ai/everything-ai-coding?style=flat-square" alt="License" /></a>
  7. <a href="https://github.com/zgsm-ai/everything-ai-coding/commits/main"><img src="https://img.shields.io/github/last-commit/zgsm-ai/everything-ai-coding?style=flat-square" alt="Last Commit" /></a>
  8. <img src="https://img.shields.io/badge/resources-44086-2ECC71?style=flat-square" alt="Resources" />
  9. </p>
  10. <p>
  11. <a href="./README.md"><strong>English</strong></a> ·
  12. <a href="./README.zh-CN.md">简体中文</a>
  13. </p>
  14. <p>
  15. <a href="#knowledge-base">Knowledge Base</a> ·
  16. <a href="https://zgsm-ai.github.io/everything-ai-coding/">Browse Catalog</a> ·
  17. <a href="#data-sources--quality">Data Sources</a> ·
  18. <a href="#coding-hub">Coding Hub</a> ·
  19. <a href="#contributing">Contributing</a>
  20. </p>
  21. <img src="assets/title-card.jpg" alt="Everything AI Coding title card" width="900" />
  22. </div>
  23. ## Why Everything AI Coding?
  24. AI coding agents are improving fast, but the ecosystem around them is still fragmented. Finding a reliable MCP server, reusable skill, practical rule set, or prompt collection usually means searching across multiple repositories and formats.
  25. Everything AI Coding is a **curated knowledge base** that continuously collects, deduplicates, enriches, and scores resources from 9+ upstream sources. Every entry includes quality signals — LLM-scored coding relevance, documentation quality, specificity, plus health metrics like freshness and community popularity — so you can evaluate before you install. Browse right here on GitHub, explore interactively with the [web catalog](https://zgsm-ai.github.io/everything-ai-coding/), or search and install with one command using the [Coding Hub](#coding-hub) tool.
  26. <a id="knowledge-base"></a>
  27. ## 📚 Knowledge Base
  28. ### [🔌 MCP Servers](./catalog/mcp/) — <!-- README_COUNT_MCP:START -->5210<!-- README_COUNT_MCP:END --> entries
  29. Model Context Protocol servers that connect AI agents to external tools, databases, and services.
  30. <!-- README_TOP5_MCP:START -->
  31. | Name | ⭐ Stars | Score | Description |
  32. |------|----------|-------|-------------|
  33. | [Headroom](https://github.com/headroomlabs-ai/headroom) | 79.8k | 98 | AI context compression layer for agents, reducing token usage 60-95%… |
  34. | [upstash/context7](https://github.com/upstash/context7) | 64.9k | 98 | An MCP server that injects real-time, version-specific library docume… |
  35. | [ChromeDevTools/chrome-devtools-mcp](https://github.com/ChromeDevTools/chrome-devtools-mcp) | 57.4k | 98 | Official Google MCP server enabling AI coding agents to control Chrom… |
  36. | [DeusData/codebase-memory-mcp](https://github.com/DeusData/codebase-memory-mcp) | 48.7k | 98 | Code intelligence MCP server that indexes codebases into a persistent… |
  37. | [microsoft/playwright-mcp](https://github.com/microsoft/playwright-mcp) | 39.7k | 98 | Official Microsoft MCP server enabling AI to control web browsers via… |
  38. <!-- README_TOP5_MCP:END -->
  39. [Browse all MCP servers →](./catalog/mcp/) · [Browse interactively →](https://zgsm-ai.github.io/everything-ai-coding/#/browse?type=mcp)
  40. ---
  41. ### [🎯 Skills](./catalog/skills/) — <!-- README_COUNT_SKILL:START -->26379<!-- README_COUNT_SKILL:END --> entries
  42. Reusable agent capabilities and workflows for AI coding assistants.
  43. <!-- README_TOP5_SKILL:START -->
  44. | Name | Source | Score | Description |
  45. |------|--------|-------|-------------|
  46. | [skill-creator](https://github.com/anthropics/skills/tree/main/skills/skill-creator) | Anthropic Official | 96 | A comprehensive skill for creating, testing, and optimizing AI assist… |
  47. | [bug-triage](https://github.com/AgentWrapper/agent-orchestrator/tree/main/skills/bug-triage) | github-trending | 96 | A detailed skill for triaging bugs in the ReverbCode repository, incl… |
  48. | [a-stock-data](https://github.com/simonlin1212/a-stock-data/tree/main/) | github-trending | 96 | A comprehensive Python toolkit for A-share financial data covering 7… |
  49. | [acpx](https://github.com/openclaw/acpx/tree/main/skills/acpx) | github-trending | 96 | A headless CLI for orchestrating AI coding agents via ACP, managing s… |
  50. | [crabbox](https://github.com/openclaw/acpx/tree/main/.agents/skills/crabbox) | github-trending | 96 | A CLI wrapper for orchestrating remote Linux validation across AWS, B… |
  51. <!-- README_TOP5_SKILL:END -->
  52. [Browse all skills →](./catalog/skills/) · [Browse interactively →](https://zgsm-ai.github.io/everything-ai-coding/#/browse?type=skill)
  53. ---
  54. ### [📋 Rules](./catalog/rules/) — <!-- README_COUNT_RULE:START -->243<!-- README_COUNT_RULE:END --> entries
  55. Coding conventions and AI behavior guidelines for consistent development.
  56. <!-- README_TOP5_RULE:START -->
  57. | Name | Source | Score | Category |
  58. |------|--------|-------|----------|
  59. | [python-checklist-py2-总规范](https://github.com/yhangf/csc-plugins/tree/main/cospowers-integration-verification-plugin/rules/coding-standards/python-checklist-py2-总规范.md) | plugin-bundled-rule | 95 | backend |
  60. | [shell_checklist](https://github.com/yhangf/csc-plugins/tree/main/cospowers-integration-verification-plugin/rules/coding-standards/shell_checklist.md) | plugin-bundled-rule | 95 | tooling |
  61. | [Go单元测试规范](https://github.com/yhangf/csc-plugins/tree/main/cospowers-integration-verification-plugin/rules/testing-standards/Go单元测试规范.md) | plugin-bundled-rule | 95 | backend |
  62. | [单元测试规范](https://github.com/yhangf/csc-plugins/tree/main/cospowers-integration-verification-plugin/rules/testing-standards/单元测试规范.md) | plugin-bundled-rule | 95 | tooling |
  63. | [python-checklist-py2-总规范](https://github.com/yhangf/csc-plugins/tree/main/cospowers-tdd-development-plugin/rules/coding-standards/python-checklist-py2-总规范.md) | plugin-bundled-rule | 95 | backend |
  64. <!-- README_TOP5_RULE:END -->
  65. [Browse all rules →](./catalog/rules/) · [Browse interactively →](https://zgsm-ai.github.io/everything-ai-coding/#/browse?type=rule)
  66. ---
  67. ### [💡 Prompts](./catalog/prompts/) — <!-- README_COUNT_PROMPT:START -->939<!-- README_COUNT_PROMPT:END --> entries
  68. Developer-focused prompt templates for common coding tasks.
  69. <!-- README_TOP5_PROMPT:START -->
  70. | Name | Source | Score | Category |
  71. |------|--------|-------|----------|
  72. | [Comprehensive repository analysis](https://github.com/f/prompts.chat/blob/HEAD/PROMPTS.md#comprehensive-repository-analysis) | prompts.chat | 96 | security |
  73. | [Frontend Developer Skill](https://github.com/f/prompts.chat/blob/HEAD/PROMPTS.md#frontend-developer-skill) | prompts.chat | 96 | frontend |
  74. | [Backend Architect](https://github.com/f/prompts.chat/blob/HEAD/PROMPTS.md#backend-architect) | prompts.chat | 96 | database |
  75. | [Frontend Developer](https://github.com/f/prompts.chat/blob/HEAD/PROMPTS.md#frontend-developer) | prompts.chat | 96 | frontend |
  76. | [Mobile App Builder](https://github.com/f/prompts.chat/blob/HEAD/PROMPTS.md#mobile-app-builder) | prompts.chat | 96 | frontend |
  77. <!-- README_TOP5_PROMPT:END -->
  78. [Browse all prompts →](./catalog/prompts/) · [Browse interactively →](https://zgsm-ai.github.io/everything-ai-coding/#/browse?type=prompt)
  79. ---
  80. ### [🧩 Plugins](./catalog/plugins/) — <!-- README_COUNT_PLUGIN:START -->2901<!-- README_COUNT_PLUGIN:END --> entries
  81. Bundled marketplace plugins (skills + commands + agents + MCP servers).
  82. > Primarily for Claude Code; opencode partially compatible (npm); cursor / windsurf / costrict have no equivalent mechanism.
  83. <!-- README_TOP5_PLUGIN:START -->
  84. | Name | Source | Score | Description |
  85. |------|--------|-------|-------------|
  86. | [superpowers](https://github.com/obra/superpowers.git) | Anthropic Official | 100 | Teaches Claude Code systematic development workflows including TDD, d… |
  87. | [hyperframes](https://github.com/heygen-com/hyperframes.git) | Anthropic Official | 100 | HyperFrames lets developers write HTML/CSS/JS to create deterministic… |
  88. | [chrome-devtools-mcp](https://github.com/ChromeDevTools/chrome-devtools-mcp.git) | Anthropic Official | 100 | Chrome DevTools MCP server for AI coding agents to debug, automate, a… |
  89. | [claude-code-setup](https://github.com/anthropics/claude-plugins-official/tree/main/plugins/claude-code-setup) | Anthropic Official | 100 | A Claude Code plugin that analyzes codebases to recommend tailored au… |
  90. | [mcp-tunnels](https://github.com/anthropics/claude-plugins-official/tree/main/plugins/mcp-tunnels) | Anthropic Official | 100 | A Claude plugin for connecting to private MCP servers via Anthropic t… |
  91. <!-- README_TOP5_PLUGIN:END -->
  92. [Browse all plugins →](./catalog/plugins/) · [Browse interactively →](https://zgsm-ai.github.io/everything-ai-coding/#/browse?type=plugin)
  93. > **Private-deployment mirror:** the plugin catalog is the upstream data source for [costrict-plugin-marketplace](https://github.com/costrict-plugins-repo/costrict-plugin-marketplace), which bundles every verified plugin as bare git repos for customers running `csc` in air-gapped networks. See that project's README for the bundle format and the client `import.sh` flow.
  94. ---
  95. <a id="data-sources--quality"></a>
  96. ## Data Sources & Quality
  97. Everything AI Coding aggregates data from multiple upstream sources, then enriches, scores, and republishes the cleaned catalog.
  98. | Type | Sources |
  99. |------|---------|
  100. | MCP | [awesome-mcp-servers](https://github.com/wong2/awesome-mcp-servers) · [Awesome-MCP-ZH](https://github.com/yzfly/Awesome-MCP-ZH) · [mcp.so](https://mcp.so) · [registry.modelcontextprotocol.io](https://registry.modelcontextprotocol.io) (official registry, `active` + `isLatest`, ~7,500 entries) |
  101. | Skills | Tier 1: [anthropics/skills](https://github.com/anthropics/skills) · [Ai-Agent-Skills](https://github.com/skillcreatorai/Ai-Agent-Skills) · [antigravity-awesome-skills](https://github.com/sickn33/antigravity-awesome-skills) · [ai-agents-public](https://github.com/vasilyu1983/ai-agents-public) · [skills.sh](https://skills.sh) (via [mastra-ai/skills-api](https://github.com/mastra-ai/skills-api), `install_count ≥ 1000`)<br/>Tier 2: [awesome-repo-configs](https://github.com/Chat2AnyLLM/awesome-repo-configs) · [awesome-openclaw-skills](https://github.com/VoltAgent/awesome-openclaw-skills) · [openclaw/skills](https://github.com/openclaw/skills)<br/>Tier 3: `catalog/skills/curated.json` |
  102. | Rules | [awesome-cursorrules](https://github.com/PatrickJS/awesome-cursorrules) · [rules-2.1-optimized](https://github.com/Mr-chen-05/rules-2.1-optimized) · [SchneiderSam/awesome-windsurfrules](https://github.com/SchneiderSam/awesome-windsurfrules) + [balqaasem/awesome-windsurfrules](https://github.com/balqaasem/awesome-windsurfrules) (cross-repo dedup) |
  103. | Prompts | [prompts.chat](https://github.com/f/prompts.chat) · [wonderful-prompts](https://github.com/langgptai/wonderful-prompts) |
  104. ### Quality scoring
  105. Every entry is scored on a 0–100 composite scale: `final_score = LLM × 0.85 + health × 0.15`.
  106. **LLM dimensions** (1–5, up to 6 per type): coding relevance, doc completeness, description accuracy, writing quality, specificity, install clarity (MCP & Skills only)
  107. **Health signals**: freshness (🟢 Active / 🟡 Stale / 🔴 Abandoned), popularity (GitHub stars), source trust (upstream reputation)
  108. **Decisions**: accept (≥ 65) · review (50–64) · reject (< 50)
  109. Each sub-directory README shows the Top 100 entries ranked by this composite score.
  110. ### Pipeline
  111. 1. **Sync** — `scripts/sync_*.py` pull from upstream sources weekly
  112. 2. **Merge** — `scripts/merge_index.py` deduplicates across sources, merges metadata
  113. 3. **Evaluate** — Single LLM call: 6-dimension scoring + enrichment (tags, summary, tech_stack) + health signals
  114. 4. **Download** — `scripts/download_catalog.py` fetches per-entry files into `catalog-download/` and reconciles `catalog/index.json` with what actually landed ([docs](./scripts/download_catalog.md))
  115. 5. **Bundle** — `scripts/build_catalog_bundle.py` packs `index.json` + `catalog-download/` into `dist/catalog-bundle.tar.gz` for downstream consumers ([docs](./scripts/build_catalog_bundle.md))
  116. 6. **Publish** — GitHub Actions refresh the catalog, generate README tables, and update the web catalog
  117. <details>
  118. <summary>Repository structure</summary>
  119. ```text
  120. everything-ai-coding/
  121. ├── install.sh / install.ps1 # One-command installers
  122. ├── catalog/ # Generated catalog data
  123. │ ├── index.json # Full merged index (4000+ entries)
  124. │ ├── search-index.json # Lightweight search index
  125. │ ├── mcp/ # MCP servers — index + README
  126. │ ├── skills/ # Skills — index + README
  127. │ ├── rules/ # Rules — index + README
  128. │ └── prompts/ # Prompts — index + README
  129. ├── platforms/ # Per-platform skill + command definitions
  130. ├── scripts/ # Sync, merge, scoring, and generation scripts
  131. └── .github/workflows/ # CI automation
  132. ```
  133. </details>
  134. ---
  135. <a id="coding-hub"></a>
  136. ## 🛠 Coding Hub — Search & Install
  137. Everything AI Coding also ships as a CLI tool that lets you search, browse, and install resources directly from your AI coding agent.
  138. ### Quick Start
  139. Install for your platform with one command:
  140. **macOS / Linux**
  141. ```bash
  142. # Costrict CLI (run from your project root)
  143. curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform costrict
  144. # VSCode Costrict extension
  145. curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform vscode-costrict
  146. # Claude Code
  147. curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform claude-code
  148. # Opencode (run from your project root)
  149. curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform opencode
  150. ```
  151. **Windows (PowerShell)**
  152. ```powershell
  153. # Costrict CLI
  154. irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1 | iex
  155. # Specify the platform manually if auto-detection fails
  156. & ([scriptblock]::Create((irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1))) -Platform costrict
  157. ```
  158. After installation, try a search command:
  159. ```bash
  160. # Claude Code
  161. /eac:search typescript
  162. # Opencode / Costrict CLI / VSCode Costrict (Roo Code)
  163. /eac-search typescript
  164. ```
  165. <video src="https://github.com/user-attachments/assets/e58f0b08-73c0-4fba-ac95-138c8087a917" controls width="100%"></video>
  166. You can also hand the installation off to another agent with this prompt:
  167. ```text
  168. You are an installation assistant. Open the following URL, read the "For Agents" section,
  169. and follow it exactly to install Everything AI Coding for the platform you are currently running on.
  170. Do not clone the repository. Only read this raw file:
  171. https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/README.md
  172. After installation, report which platform path was used and whether verification succeeded.
  173. ```
  174. ### Platforms
  175. Everything AI Coding supports four AI coding platforms. The resource catalog is shared, while command names and installation paths vary slightly by platform.
  176. | | Claude Code | Costrict | Opencode | VSCode Costrict (Roo Code) |
  177. |---|---|---|---|---|
  178. | Search | `/eac:search <kw> [type:mcp]` | `/eac-search <kw> [type:mcp]` | `/eac-search <kw> [type:mcp]` | `/eac-search <kw> [type:mcp]` |
  179. | Browse | `/eac:browse [category]` | `/eac-browse [category]` | `/eac-browse [category]` | `/eac-browse [category]` |
  180. | Recommend | `/eac:recommend` | `/eac-recommend` | `/eac-recommend` | `/eac-recommend` |
  181. | Install | `/eac:install <id>` | `/eac-install <id>` | `/eac-install <id>` | `/eac-install <id>` |
  182. | Uninstall | `/eac:uninstall <id>` | `/eac-uninstall <id>` | `/eac-uninstall <id>` | `/eac-uninstall <id>` |
  183. | Update | `/eac:update` | `/eac-update` | `/eac-update` | `/eac-update` |
  184. | Evo | `/eac:evo <id>` | `/eac-evo <id>` | `/eac-evo <id>` | `/eac-evo <id>` |
  185. <details>
  186. <summary>Platform path differences</summary>
  187. | | Claude Code | Costrict | VSCode Costrict | Opencode |
  188. |---|---|---|---|---|
  189. | Global skill path | `~/.claude/skills/eac/` | `~/.costrict/skills/eac/` | `~/.costrict/skills/eac/` | `~/.opencode/skills/eac/` |
  190. | Command path | same global dir | `.costrict/eac/commands/` (project) | `~/.roo/commands/` (global) | `.opencode/command/` (project) |
  191. | Separator | `:` | `-` | `-` | `-` |
  192. - **Costrict CLI** installs command files per project, so run the installer in each repository root.
  193. - **VSCode Costrict / Roo Code** installs command files globally under `~/.roo/commands/`.
  194. - **Claude Code** can load the full skill and subcommands from the global skills directory.
  195. - **Opencode** installs commands per project under `.opencode/command/`.
  196. </details>
  197. <a id="for-agents"></a>
  198. ### For Agents
  199. > If you are an AI agent installing Everything AI Coding automatically, follow this section exactly.
  200. #### Step 1: Run the installer
  201. The install scripts auto-detect the host platform when possible.
  202. **macOS / Linux**
  203. ```bash
  204. curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash
  205. ```
  206. **Windows (PowerShell)**
  207. ```powershell
  208. irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1 | iex
  209. ```
  210. Auto-detection uses process-level environment variables that each platform injects at startup:
  211. | Environment variable | Platform |
  212. |----------------------|----------|
  213. | `COSTRICT_CALLER=vscode` | VSCode Costrict extension |
  214. | `COSTRICT_RUNNING=1` | Costrict CLI |
  215. | `CLAUDECODE=1` | Claude Code |
  216. | `OPENCODE=1` | Opencode |
  217. If auto-detection fails, specify the platform manually.
  218. **macOS / Linux**
  219. ```bash
  220. curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform <platform>
  221. ```
  222. **Windows (PowerShell)**
  223. ```powershell
  224. & ([scriptblock]::Create((irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1))) -Platform <platform>
  225. ```
  226. Examples:
  227. ```bash
  228. # Claude Code (macOS/Linux)
  229. curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform claude-code
  230. # Opencode (run from the project root)
  231. curl -fsSL https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.sh | bash -s -- --platform opencode
  232. ```
  233. ```powershell
  234. # Claude Code (Windows)
  235. & ([scriptblock]::Create((irm https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/install.ps1))) -Platform claude-code
  236. ```
  237. <details>
  238. <summary>Fallback: manual installation without <code>curl | bash</code></summary>
  239. Run the platform-specific commands below if you need to download the files directly.
  240. **Costrict CLI** (global skill + project commands)
  241. ```bash
  242. mkdir -p ~/.costrict/skills/eac
  243. curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/costrict/skills/eac/SKILL.md" -o ~/.costrict/skills/eac/SKILL.md
  244. mkdir -p .costrict/eac/commands
  245. for cmd in search browse recommend install uninstall update; do
  246. curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/costrict/commands/eac/eac-${cmd}.md" -o .costrict/eac/commands/eac-${cmd}.md
  247. done
  248. ```
  249. **VSCode Costrict extension / Roo Code** (global skill + global commands)
  250. ```bash
  251. mkdir -p ~/.costrict/skills/eac
  252. curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/vscode-costrict/skills/eac/SKILL.md" -o ~/.costrict/skills/eac/SKILL.md
  253. mkdir -p ~/.roo/commands
  254. for cmd in search browse recommend install uninstall update; do
  255. curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/vscode-costrict/commands/eac/eac-${cmd}.md" -o ~/.roo/commands/eac-${cmd}.md
  256. done
  257. ```
  258. **Claude Code** (global skill + global commands)
  259. ```bash
  260. mkdir -p ~/.claude/skills/eac
  261. curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/claude-code/skills/eac/SKILL.md" -o ~/.claude/skills/eac/SKILL.md
  262. for cmd in search browse recommend install uninstall update; do
  263. curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/claude-code/commands/eac/${cmd}.md" -o ~/.claude/skills/eac/${cmd}.md
  264. done
  265. ```
  266. **Opencode** (global skill + project commands)
  267. ```bash
  268. mkdir -p ~/.opencode/skills/eac
  269. curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/opencode/skills/eac/SKILL.md" -o ~/.opencode/skills/eac/SKILL.md
  270. mkdir -p .opencode/command
  271. for cmd in search browse recommend install uninstall update; do
  272. curl -fsSL "https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/platforms/opencode/command/eac-${cmd}.md" -o .opencode/command/eac-${cmd}.md
  273. done
  274. ```
  275. </details>
  276. #### Step 2: Verify the installation
  277. Run a search command to confirm that the commands are available:
  278. ```text
  279. # Costrict CLI / Opencode
  280. /eac-search typescript
  281. # VSCode Costrict extension
  282. Send this in the chat: "Search typescript with eac"
  283. # Claude Code
  284. /eac:search typescript
  285. ```
  286. Expected result: a Markdown table of matching resources. If the command is missing, the installation did not land in the correct platform path.
  287. #### Available commands
  288. | Command | Description |
  289. |---------|-------------|
  290. | `search <keyword> [type:mcp\|skill\|rule\|prompt]` | Search resources, optionally filtered by type |
  291. | `browse [category] [type:...]` | Browse by category |
  292. | `recommend [type:...]` | Recommend resources based on the current project stack |
  293. | `install <id>` | Install a resource |
  294. | `uninstall <id>` | Uninstall a resource |
  295. | `update` | Pull the latest Everything AI Coding files |
  296. | `evo <id>` | Evolve a locally installed skill / prompt / rule via a 7-dimension quality rubric (adapted from [darwin-skill](https://github.com/alchaincyf/darwin-skill)) |
  297. #### Data endpoints
  298. Search, browse, and recommend operate on a lightweight search index. Installation fetches a per-entry API document.
  299. | Purpose | URL |
  300. |---------|-----|
  301. | Search index | `https://zgsm-ai.github.io/everything-ai-coding/api/v1/search-index.json` |
  302. | Entry API | `https://zgsm-ai.github.io/everything-ai-coding/api/v1/{type}/{id}.json` |
  303. | Type index | `https://zgsm-ai.github.io/everything-ai-coding/api/v1/{type}/index.json` |
  304. | Full index fallback | `https://raw.githubusercontent.com/zgsm-ai/everything-ai-coding/main/catalog/index.json` |
  305. ## Why Costrict?
  306. If you like the Everything AI Coding workflow, try **[Costrict](https://github.com/zgsm-ai/costrict)** — our broader AI coding agent platform built for stronger automation and team workflows.
  307. [Explore Costrict →](https://github.com/zgsm-ai/costrict)
  308. <a id="contributing"></a>
  309. ## Contributing
  310. Contributions are welcome. Open a PR against the appropriate directory under `catalog/` and make sure the resource:
  311. - is relevant to coding or AI-assisted development,
  312. - has an accurate `source_url`, `description`, and tags,
  313. - follows `catalog/schema.json`.
  314. If you need maintainers' context instead of quick-start instructions, see the repository wiki in [`docs/wiki/`](./docs/wiki/README.md).
  315. ## Acknowledgments
  316. The `/eac:evo` command's quality rubric is adapted from **[darwin-skill](https://github.com/alchaincyf/darwin-skill)** by 花叔 (MIT License) — an autonomous skill optimization system inspired by Karpathy's autoresearch. darwin-skill first systematized a "structure + effectiveness" dual-evaluation framework for SKILL.md files with a ratchet mechanism for keeping only measurable improvements. Everything AI Coding simplifies it for on-demand client-side use: the dynamic live-testing dimension and the ratchet are deferred; the core dimensions (workflow clarity, instruction specificity, edge-case coverage, checkpoint design, overall architecture, etc.) are preserved and rewritten for our on-demand evo context. See [`docs/wiki/evo-rubric.md`](./docs/wiki/evo-rubric.md) for the full rubric specification.
  317. Thanks to 花叔 for making the ideas and the original skill publicly available.
  318. ## Disclaimer
  319. Everything AI Coding is an index and installation helper for third-party open-source resources. Every MCP server, skill, rule, and prompt listed in the catalog remains the property of its original author.
  320. This repository does **not** guarantee the safety, availability, accuracy, or compliance of third-party resources. Review source code and licenses before use, and open an issue if you find security or copyright problems.
  321. Everything AI Coding is released under the [MIT License](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.