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

Aegis Skill

リポジトリ ↗

作者:GanyuanRan★ 1,442 (whole repo)22 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 22 skills

  • Connects Instruction files the AI reads
  • Account or key No key found in README or SKILL.md
  • Category コーディング
Maker’s original description
Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.
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/ganyuanran-aegis.svg)](https://mcp.popnx.com/en/skills/ganyuanran-aegis)

一緒に使える

同じ作業で AI をサービスにつなぐ MCP

REA

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

作者:morluto広く使われている↓ 38.9万/週★ 46.8万7 日前更新

MCP · サービスにつなぐパソコンで動く

Fallow

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

作者:fallow-rs広く使われている↓ 244.1万/週★ 5383一昨日更新

MCP · サービスにつなぐパソコンで動く

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
Aegis
reaandrej-karpathy-skillsgraphifyMoneyPrinterTurbo
作者GanyuanRanmorlutomultica-aiGraphify-Labsharry0703
Skill 数221111
GitHub スター1,442467,235234,125149,873144,332
最終コード更新2026年11月14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
ライセンスMITMIT–Apache-2.0MIT

GanyuanRan による 22 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 (22)

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 22 skills from https://github.com/ganyuanran/aegis: anti-entropy-governance, brainstorming, communicating-concisely, dispatching-parallel-agents, establishing-project-context, executing-plans, finishing-a-development-branch, first-principles-review, goal-framing, long-task-continuation, receiving-code-review, recording-architecture-decisions, requesting-code-review, subagent-driven-development, systematic-debugging, test-driven-development, update-aegis, using-aegis, using-git-worktrees, verification-before-completion, writing-plans, writing-skills, 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: anti-entropy-governance = skills/anti-entropy-governance · brainstorming = skills/brainstorming · communicating-concisely = skills/communicating-concisely · dispatching-parallel-agents = skills/dispatching-parallel-agents · establishing-project-context = skills/establishing-project-context · executing-plans = skills/executing-plans · finishing-a-development-branch = skills/finishing-a-development-branch · first-principles-review = skills/first-principles-review · goal-framing = skills/goal-framing · long-task-continuation = skills/long-task-continuation · receiving-code-review = skills/receiving-code-review · recording-architecture-decisions = skills/recording-architecture-decisions · requesting-code-review = skills/requesting-code-review · subagent-driven-development = skills/subagent-driven-development · systematic-debugging = skills/systematic-debugging · test-driven-development = skills/test-driven-development · update-aegis = skills/update-aegis · using-aegis = skills/using-aegis · using-git-worktrees = skills/using-git-worktrees · verification-before-completion = skills/verification-before-completion · writing-plans = skills/writing-plans · writing-skills = skills/writing-skills. 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 22 skills from https://github.com/ganyuanran/aegis: anti-entropy-governance, brainstorming, communicating-concisely, dispatching-parallel-agents, establishing-project-context, executing-plans, finishing-a-development-branch, first-principles-review, goal-framing, long-task-continuation, receiving-code-review, recording-architecture-decisions, requesting-code-review, subagent-driven-development, systematic-debugging, test-driven-development, update-aegis, using-aegis, using-git-worktrees, verification-before-completion, writing-plans, writing-skills, 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: anti-entropy-governance = skills/anti-entropy-governance · brainstorming = skills/brainstorming · communicating-concisely = skills/communicating-concisely · dispatching-parallel-agents = skills/dispatching-parallel-agents · establishing-project-context = skills/establishing-project-context · executing-plans = skills/executing-plans · finishing-a-development-branch = skills/finishing-a-development-branch · first-principles-review = skills/first-principles-review · goal-framing = skills/goal-framing · long-task-continuation = skills/long-task-continuation · receiving-code-review = skills/receiving-code-review · recording-architecture-decisions = skills/recording-architecture-decisions · requesting-code-review = skills/requesting-code-review · subagent-driven-development = skills/subagent-driven-development · systematic-debugging = skills/systematic-debugging · test-driven-development = skills/test-driven-development · update-aegis = skills/update-aegis · using-aegis = skills/using-aegis · using-git-worktrees = skills/using-git-worktrees · verification-before-completion = skills/verification-before-completion · writing-plans = skills/writing-plans · writing-skills = skills/writing-skills. 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 22 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

  • anti-entropy-governance

    Use when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-truth boundaries; identify opportunities automatically; destructive execution requires explicit confirmation.

  • brainstorming

    Use when defining ambiguous or high-complexity new features, product behavior, UI/component design, architecture choices, contract changes, or when grilling/pressure-testing a plan or design. Routine small requests stay on the fast path.

  • communicating-concisely

    Use when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise explicitly requests a much shorter answer.

  • dispatching-parallel-agents

    Use when facing 2+ independent tasks without a written plan, with no conflicting shared mutable state or sequential dependencies, where parallel delegation beats inline cost; otherwise inline. Planned tasks use subagent-driven-development.

  • establishing-project-context

    Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.

  • executing-plans

    Use when executing a written implementation plan across sessions or with review checkpoints. Small or single-slice plans stay inline. For same-session independent tasks, use subagent-driven-development instead.

  • finishing-a-development-branch

    Use when verified work needs integration or cleanup of an existing task-created branch/worktree, or the user explicitly requests merge, PR, or branch lifecycle handling.

  • first-principles-review

    Use when asked for first-principles or Occam's-razor review, or when high-risk decisions involve competing constraints, fallback growth, duplicate owners, or architecture direction risk. Ordinary bug fixes stay on the fast path.

  • goal-framing

    Use when the user explicitly sets an Aegis goal with /aegis-goal, Aegis goal:, or asks to define goal, success evidence, stop condition, or task boundaries before work.

  • long-task-continuation

    Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.

  • receiving-code-review

    Use when receiving code review feedback before implementing suggestions, especially when feedback is unclear, risky, disputed, or technically questionable.

  • recording-architecture-decisions

    Use when the user asks to create, write, update, amend, supersede, or evaluate an ADR, architecture decision record, durable architecture decision, decision log, or baseline sync after architecture-changing work.

  • requesting-code-review

    Use when requesting independent code review, after implementation slices, before merging high-risk work, or when verification exposes evidence, baseline, architecture, compatibility, or retirement uncertainty.

  • subagent-driven-development

    Use when executing a written implementation plan with independent tasks in the current session where delegation beats inline coordination cost; otherwise inline. Ad-hoc 2+ tasks without a plan use dispatching-parallel-agents.

  • systematic-debugging

    Use when encountering a bug, test failure, or unexpected behavior, before proposing fixes

  • test-driven-development

    Use when the user explicitly requests strict or test-first TDD, or when the current conversation already contains an explicit `TDD Route: strict` decision from another Aegis workflow.

  • update-aegis

    Use when the user says `aegis:update`, asks to update or upgrade an installed Aegis method-pack, wants the latest Aegis version, or asks whether Aegis is current on this host.

  • using-aegis

    Use when starting a turn or checking Aegis skill routing.

  • using-git-worktrees

    Use when a coding task needs a concurrent checkout, unrelated dirty state blocks safe branch switching, or the user or repository explicitly requires a worktree.

  • verification-before-completion

    Use when about to claim work is complete, fixed, passing, verified, release-ready, or ready to commit, merge, publish, or hand off.

  • writing-plans

    Use when you have an approved spec or written requirements for a multi-step task that needs a durable plan document before touching code. Small, single-owner, or fast-path tasks do not need this skill.

  • writing-skills

    Use when creating new skills, editing existing skills, or verifying skills work before deployment

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 CodeCodexGemini CLIGitHub 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 22 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 ↑

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
1,442
Stars are for the whole repo, not each skill
提供元
GanyuanRan
ライセンス
MIT
最終コード更新
2026年11月14日
repo 内の SKILL.md(翻訳版とテンプレートを含む)
22
トピック
agent-skills, ai-agents, ai-coding, architecture-driven-development, awsome-coding-plugin, baseline-first, claude-code, codex, coding-agents, dive, dsh-plugin, evidence-driven