プロトタイプ · プレビュー版:公式レジストリのすべてのサーバーを掲載し、30分ごとに同期しています。Google でログインするとレビューを書けます。プロトタイプ · 30分ごとに更新
PopNx MCPAIを使う人のためのMCPサーバー · やさしい言葉で解説

skills Skill

リポジトリ ↗

作者:BuilderIO★ 4,672 (whole repo)25 個の skill

★ Stars are for the whole repo, not each skill

Pick the skill to install

What it does

This repo is a collection of 25 skills

  • Connects Instruction files the AI reads, with steps that call an outside service
  • Account or key Some steps need a key for PROVIDER_WEBHOOK_SECRET (per the README)
  • Category 自動化とエージェント
Maker’s original description
Skills for agents
作者向け:README にバッジを付ける

作者の方は、このコードを README に貼れます。バッジはこのページにリンクします。

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

似た Skill

同じ種類の作業。Skill 一覧と同じ並び

似たものと比べる
これ
skills
skillsnacosanatomyleon
作者BuilderIOvercel-labsalibabawheresryan22leon-ai
Skill 数251111
GitHub スター4,67239,65833,52427,66717,688
最終コード更新2026年11月17日2026年11月16日2026年11月13日2026年10月19日2026年11月13日
ライセンスMITMITApache-2.0MITMIT

BuilderIO による 25 個の Skill(指示セット)。AI が読んでそのとおりに作業します · MCP server ではありません

Pick the skill to install

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

Install the whole set (25)

If you want every one, let the AI install them in one go. Know 2 things first

  • Every installed skill’s description is loaded into every chat. The more you install, the easier it is for the AI to pick the wrong one
  • Some skills duplicate tools the AI already has built in. Installing only the ones you use works better
Where to install
Please install all 25 skills from https://github.com/builderio/skills: adding-a-skill, agent-watchdog, an, efficient-fable, efficient-frontier, factory, factory-babysit-pr, factory-collect, factory-human-digest, factory-lookback, factory-recover, factory-review-prs, factory-ship, factory-watchdog, plan-arbiter, plow-ahead, quick-recap, read-the-damn-docs, rewind, stay-within-limits, turn-into-app, visual-edit, visual-plan, visual-recap, webmcp, for all my projects, putting each at ~/.claude/skills/<skill name> (in Codex use ~/.agents/skills/<skill name>, in Cursor ~/.cursor/skills/<skill name>). Folders in the repo: adding-a-skill = .agents/skills/adding-a-skill · agent-watchdog = skills/agent-watchdog · an = skills/an · efficient-fable = skills/efficient-fable · efficient-frontier = skills/efficient-frontier · factory = skills/factory · factory-babysit-pr = skills/factory-babysit-pr · factory-collect = skills/factory-collect · factory-human-digest = skills/factory-human-digest · factory-lookback = skills/factory-lookback · factory-recover = skills/factory-recover · factory-review-prs = skills/factory-review-prs · factory-ship = skills/factory-ship · factory-watchdog = skills/factory-watchdog · plan-arbiter = skills/plan-arbiter · plow-ahead = skills/plow-ahead · quick-recap = skills/quick-recap · read-the-damn-docs = skills/read-the-damn-docs · rewind = skills/rewind · stay-within-limits = skills/stay-within-limits · turn-into-app = skills/turn-into-app · visual-edit = skills/visual-edit · visual-plan = skills/visual-plan · visual-recap = skills/visual-recap · webmcp = skills/webmcp. First show me every file and tell me whether any has scripts or changes machine settings, then tell me the full path you will install each one to and wait for me to agree.
Please install all 25 skills from https://github.com/builderio/skills: adding-a-skill, agent-watchdog, an, efficient-fable, efficient-frontier, factory, factory-babysit-pr, factory-collect, factory-human-digest, factory-lookback, factory-recover, factory-review-prs, factory-ship, factory-watchdog, plan-arbiter, plow-ahead, quick-recap, read-the-damn-docs, rewind, stay-within-limits, turn-into-app, visual-edit, visual-plan, visual-recap, webmcp, into the project this chat is open in (at .claude/skills/<skill name>; in Codex use .agents/skills/<skill name>, in Cursor .cursor/skills/<skill name>). Folders in the repo: adding-a-skill = .agents/skills/adding-a-skill · agent-watchdog = skills/agent-watchdog · an = skills/an · efficient-fable = skills/efficient-fable · efficient-frontier = skills/efficient-frontier · factory = skills/factory · factory-babysit-pr = skills/factory-babysit-pr · factory-collect = skills/factory-collect · factory-human-digest = skills/factory-human-digest · factory-lookback = skills/factory-lookback · factory-recover = skills/factory-recover · factory-review-prs = skills/factory-review-prs · factory-ship = skills/factory-ship · factory-watchdog = skills/factory-watchdog · plan-arbiter = skills/plan-arbiter · plow-ahead = skills/plow-ahead · quick-recap = skills/quick-recap · read-the-damn-docs = skills/read-the-damn-docs · rewind = skills/rewind · stay-within-limits = skills/stay-within-limits · turn-into-app = skills/turn-into-app · visual-edit = skills/visual-edit · visual-plan = skills/visual-plan · visual-recap = skills/visual-recap · webmcp = skills/webmcp. First show me every file and tell me whether any has scripts or changes machine settings, then tell me the project name and the full path you will install each one to and wait for me to agree.

Uploading to Claude on the web and apps: you need 25 uploads, one ZIP per skill. Open each skill in the list below to download it

Checked against official docs 2026年11月12日 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com

  • adding-a-skill

    Use in the BuilderIO/skills repo whenever adding, updating, publishing, documenting, validating, or wiring a public skill. Covers the repo-local skill files, root catalog docs, plugin metadata, @agent-native/skills dynamic install path, optional managed AGENTS/CLAUDE instruction blocks in ../agent-…

  • agent-watchdog

    Use when asked to watch, babysit, audit, review, compare, or fix another agent's work from a Codex session ID, Claude Code session/transcript, chat/thread link, PR, branch, log, or pasted run summary. Monitor until the other agent is done or blocked, reconstruct what the user asked, independently i…

  • an

    Open and operate Agent-Native workspace apps through Dispatch MCP, with inline app surfaces, browser-session authentication, and current screen state.

  • efficient-fable

    Alias for /efficient-orchestrator. Run only when the user explicitly invokes /efficient-fable; never self-activate.

  • efficient-frontier

    Alias for /efficient-orchestrator. Run only when the user explicitly invokes /efficient-frontier; never self-activate.

  • factory

    Experimental workflow for configuring an autonomous software delivery factory. Use when choosing feedback sources, schedules, worktree behavior, autonomy gates, or host automations.

  • factory-babysit-pr

    Experimental workflow for babysitting one explicitly authorized pull or merge request. Use to monitor its live review state and checks, fix actionable in-scope findings, and apply separate reply, approval, merge, and soak gates.

  • factory-collect

    Experimental workflow for collecting and triaging product feedback, product telemetry, runtime errors, and issue reports. Use when scanning configured signal sources and applying separate fix, reply, or close rules.

  • factory-human-digest

    Experimental workflow for summarizing work that still needs human judgment across configured pull requests, issues, feedback, errors, and delivery signals. Use for a human decision queue or bounded review.

  • factory-lookback

    Experimental workflow for auditing recurring feedback, telemetry, errors, and brittle delivery paths to find systemic fixes. Use for periodic or requested cross-source lookbacks, not routine single-item intake.

  • factory-recover

    Experimental workflow for finding and resuming interrupted coding runs. Use after an agent host restart or an interrupted automation.

  • factory-review-prs

    Experimental workflow for reviewing configured repositories' pull requests. Use for manual or scheduled PR triage, approval, or merge decisions.

  • factory-ship

    Experimental workflow for publishing and completing configured software delivery work. Use when the user or an enabled factory policy asks to ship.

  • factory-watchdog

    Experimental workflow for monitoring explicitly authorized delivery tasks and reporting stalled work. Use for scheduled ship follow-through.

  • plan-arbiter

    Use when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed plans, session IDs, transcripts, plan documents, PR descriptions, or pasted strategies; or when the user wants one recommen…

  • plow-ahead

    Use when the user explicitly wants autonomous progress without routine clarification stops: "plow ahead", "do not stop", "use your best judgment", "keep going until done", "finish while I am away", "do not ask questions unless truly blocked", or similar. Convert ordinary ambiguity into stated assum…

  • quick-recap

    Use when adding or following the red/yellow/green final status block convention for agent responses, especially by installing managed AGENTS.md or CLAUDE.md instructions.

  • read-the-damn-docs

    Use when implementing, integrating, upgrading, debugging, or answering anything involving third-party APIs, libraries, frameworks, CLIs, cloud services, model/provider SDKs, fast-moving product behavior, user requests for latest/current/official behavior, unfamiliar repo docs/specs, errors that may…

  • rewind

    Retrieve recent local Clips Rewind context when the user says "Look at Rewind," asks what just happened, or refers to something they recently said or saw.

  • stay-within-limits

    Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.

  • turn-into-app

    Turns a thread, skill, spreadsheet, or Claude/ChatGPT project into a polished, visual Agent-Native app: populated domain screens with the in-app agent working behind contextual controls. Use when a user invokes `/turn-into-app`, or asks to turn a workflow, skill, spreadsheet, or project into an app…

  • visual-edit

    Open and collaboratively edit a running local app in Design, with shared fallback previews and source handoff. Use when the user asks to inspect, share, or edit a real local app in Design.

  • visual-plan

    Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review when useful.

  • visual-recap

    Turn a PR, branch, commit, or git diff into an interactive visual recap with diagrams, file maps, API/schema summaries, annotated diffs, and focused review notes.

  • webmcp

    Open a user-provided URL in the host's built-in browser and use the page's MCP or WebMCP tools before browser UI automation for app communication or edits.

Skill と MCP の違い

MCP = 手

AI を外部のサービスやデータにつなぎます(例:Notion を読む、請求書を作る)。プログラムやサーバーが動いている必要があります。

Skill = 手順書

作業のやり方を AI に教えるテキストファイル。どのサービスにもつながりません。

重なる部分もあります。ツールを呼ぶスクリプト付きの Skill や、知識だけを渡す MCP もあります。やりたい作業から選んでください。

使えるアプリ

Claude CodeCodexCursorGitHub CopilotOpenCode

提供元の README と repo のフォルダから判断

インストール

Pick a skill first

This repo has 25 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 ↑

The maker’s command installs the whole set of 25
Node.js を入れる(まだなければ)

もう入っていますか?先に確認 · ターミナルを開き、このコマンドを入力して Enter

node -v
  • バージョン番号(例 v26.13.1)が出る = 入っています。この手順は飛ばせます
  • "command not found"(Windows では "is not recognized")が出る = まだ入っていないか、入れた直後でターミナルを開き直す必要があります
ターミナルの開き方

Mac:⌘ + Space を押し、Terminal と入力して Enter

Windows:スタートメニューを開き、Windows PowerShell と入力して「開く」

まだ入っていない場合: 公式ダウンロードページで LTS 版と、クリックで進むインストーラーを選びます:Mac は .pkg、Windows は .msi。ダブルクリックして最後まで進めるだけで、curl コマンドは不要です

Node.js のダウンロードページを開く ↗

入れ終わったらターミナルを閉じて開き直し、同じコマンドをもう一度実行します。バージョン番号が出れば完了です: node -v

一度入れれば、Node.js を使うすべてのツールで使えます

npx @agent-native/skills@latest add

提供元の README から引用。提供元のコードをダウンロードして実行します

話し合い

質問、コツの共有、使えないことの報告ができます。「役に立った」の多い順です。

まだ投稿はありません。最初の質問や共有をどうぞ。

ここの投稿は利用者によるもので、PopNx チームのものではありません。

ログインして投稿

GitHub の情報

GitHub スター
4,672
Stars are for the whole repo, not each skill
提供元
BuilderIO
ライセンス
MIT
最終コード更新
2026年11月17日
repo 内の SKILL.md(翻訳版とテンプレートを含む)
25
トピック
skills