原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。使用 Google 登录即可撰写评价。原型 · 每 30 分钟更新
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

apexyard Skill

代码仓库 ↗

作者:me2resh★ 549 (whole repo)69 个 skill

★ Stars are for the whole repo, not each skill

Pick the skill to install

What it does

This repo is a collection of 69 skills

  • Connects Instruction files the AI reads
  • Account or key Not confirmed yet (README not read yet)
  • Category 写代码
Maker’s original description
Your AI engineering org, governed. Ship agent-built code safely to production.
给作者:在 README 中加徽章

如果你是作者,可把这段代码贴到 README。徽章会链接回本页。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/me2resh-apexyard.svg)](https://mcp.popnx.com/en/skills/me2resh-apexyard)

可搭配使用

在同一工作中把 AI 连到服务的 MCP

REA

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

作者:morluto广泛使用↓ 38.9万/周★ 46.6万6天前更新

MCP · 连接服务在你的电脑上运行

Fallow

Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.

作者:fallow-rs广泛使用↓ 244.1万/周★ 5379昨天更新

MCP · 连接服务在你的电脑上运行

Desktop Commander

MCP server for terminal commands, file operations, and process management

作者:wonderwhy-er广泛使用↓ 74万/周★ 1万6天前更新

MCP · 连接服务在你的电脑上运行

相似的 Skill

同类工作,排序与 Skill 列表相同

与相似项目对比
本项
apexyard
reaandrej-karpathy-skillsgraphifyMoneyPrinterTurbo
作者me2reshmorlutomultica-aiGraphify-Labsharry0703
Skill 数691111
GitHub 星标549467,235234,125149,873144,332
最近代码更新2026年11月18日2026年11月18日2026年4月20日2026年11月18日2026年11月18日
许可证MITMIT–Apache-2.0MIT

me2resh 提供的 69 个 Skill(指令集),AI 读取后照做 · 不是 MCP server

Pick the skill to install

Install only the ones you use. Open a skill to see how to install it

This set has 69 skills, too many to install at once: every installed skill’s description loads into every chat, so the AI picks the wrong one more easily. Pick only the ones you use from the list below

Showing 30 of 69 See all on GitHub

  • accessibility-audit

    WCAG 2.2 AA audit — perceivable, operable, understandable, robust criteria. Deep-dive for /launch-check accessibility.

  • agdr

    Browse / search / show / stats AgDRs across the portfolio — recalls "have we decided this before?".

  • analytics-audit

    Analytics audit — SDK config, event naming, funnel completeness, dashboards. Deep-dive for /launch-check analytics.

  • approve-architecture

    Record per-PR architecture-review approval for design-artifact PRs (required by the architecture gate). ONLY on an explicit per-PR architect "approved".

  • approve-design

    Record per-PR design-review approval (UI merge gate). ONLY on an explicit per-PR designer "approved".

  • approve-merge

    Record per-PR CEO approval and merge in one turn. ONLY on an explicit per-PR "approved" — never on umbrella "go".

  • audit-deps

    Audit dependencies for vulnerabilities, outdated packages, and license compliance.

  • bug

    Create a structured bug ticket (Given/When/Then scenario, repro steps, severity).

  • c4

    Generate C4 L1 (Context) + L2 (Container) Mermaid diagrams from a project's codebase. Structurizr DSL escape hatch (--dsl) for L3+ component precision.

  • challenge

    Invoke The Contrarian (Naqid) to steelman-then-challenge an idea, feature, decision, or plan — surfaces assumptions, failure modes, and alternatives. Advisory only; never blocks a gate.

  • code-review

    Review a PR for quality, security, and standards compliance. Invokes the Code Reviewer agent (Rex).

  • codify-rule

    Turn a review comment that caught a Rex-miss into a draft handbook entry — Y/N gate, source-PR footer, bucket-routed.

  • compliance-check

    GDPR + ePrivacy audit — consent, privacy policy, data handling, right-to-deletion, DPAs. Deep-dive for /launch-check compliance.

  • debug

    Hypothesis-driven debugging — architecture-first reading + evidence-before-fix. For bugs that resisted naïve fix attempts.

  • decide

    Make a technical decision with structured reasoning and create an Agent Decision Record (AgDR).

  • design-review

    Review a technical design / migration AgDR / feature spec for architectural soundness BEFORE the Build phase. Invokes the Solution Architect agent (Tariq) — the non-code analog of /code-review.

  • design-sync

    Sync a local component library to a claude.ai/design design-system project incrementally — one component at a time, never a wholesale replace. Drives the DesignSync tool.

  • dfd

    DFD with trust boundaries + data classifications (Mermaid + optional Threat Dragon JSON). Source-of-truth for /threat-model.

  • docs-audit

    Diataxis docs audit — tutorials, how-to, reference, explanation; checks README, API docs, deployment guides, changelog, staleness.

  • eval-agents

    Score a review agent (Rex/Hakim/Tariq) against a labeled PR corpus — ground-truth defect-set overlap, never a prose rubric. Headline metric is approve-precision.

  • extract-features

    Six-axis Feature Inventory (routes / models / jobs / tests / UI / docs) — a "what we must preserve" spec for greenfield rewrites.

  • fan-out

    Spawn N parallel Agent calls in one message (per-task agent type, worktree isolation, background mode).

  • feature

    Create a structured feature ticket (user story, acceptance criteria, design notes) for a new user-facing feature.

  • feature-diagram

    Per-feature Mermaid flowchart — routes / models / jobs / screens. Consumes /extract-features inventory.

  • geo-audit

    GEO + AEO audit — `llms.txt`, `AGENTS.md`, AI-crawler robots, JSON-LD citation grounding. Sibling to /seo-audit.

  • handover

    Onboard an external repo via a structured handover assessment + harnessability scoring across 5 codebase dimensions.

  • idea

    Capture a new product idea / feature concept / internal tool proposal to the ideas backlog (pre-triage).

  • inbox

    Show every item across managed projects needing the user's attention — PRs, assigned issues, comments, blockers.

  • investigation

    Create an investigation ticket + live-doc for sustained root-cause work (retros, bug archaeology, regression hunts).

  • journey

    Self-contained HTML user-journey map (boxes/arrows with per-page modals) — preview between PRD and tech-design.

Skill 和 MCP 有什么不同

MCP = 手

把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。

Skill = 手册

教 AI 怎么做某项工作的文本文件,不连接任何服务。

有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。

适用的应用

Claude CodeCodexCursorOpenCode

依据开发者 README 和 repo 中的文件夹

安装

Pick a skill first

This repo has 69 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP

Let the AI install it
Upload to claude.ai

Go to the skill list ↑

讨论

提问、分享技巧或报告无法使用。按“有帮助”数量排序。

还没有帖子,欢迎第一个提问或分享。

此处内容由用户撰写,不代表 PopNx 团队。

登录后发帖

来自 GitHub

GitHub 星标
549
Stars are for the whole repo, not each skill
开发者
me2resh
许可证
MIT
最近代码更新
2026年11月18日
repo 中的 SKILL.md 文件(含译本和模板)
30
主题
agentic-coding, ai-agents, ai-governance, claude-code, claude-code-hooks, claude-code-skills, code-review, developer-tools, multi-agent, sdlc, software-engineering