프로토타입 · 미리 보기: 공식 레지스트리의 모든 서버를 담고 있으며 30분마다 동기화해요. Google로 로그인하면 리뷰를 쓸 수 있어요.프로토타입 · 30분마다 업데이트
PopNx MCPAI를 쓰는 사람을 위한 MCP 서버 · 쉬운 말로 설명해요

gaia Skill

저장소 ↗

제작자: amd★ 1,624 (whole repo)skill 102개

★ Stars are for the whole repo, not each skill

Pick the skill to install

What it does

This repo is a collection of 102 skills

  • Connects Instruction files the AI reads
  • Account or key Not confirmed yet (README not read yet)
  • Category 자동화와 에이전트
Maker’s original description
Build AI agents for your PC
제작자용: README에 배지 달기

제작자라면 이 코드를 README에 붙여 넣으세요. 배지는 이 페이지로 연결됩니다.

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

비슷한 Skill

같은 종류의 작업, Skill 목록과 같은 순서

비슷한 항목과 비교
이 항목
gaia
skillsnacosanatomyleon
제작자amdvercel-labsalibabawheresryan22leon-ai
Skill 수1021111
GitHub 별1,62439,65833,52427,66717,684
마지막 코드 변경2026년 11월 17일2026년 11월 16일2026년 11월 13일2026년 10월 19일2026년 11월 13일
라이선스MITMITApache-2.0MITMIT

amd의 Skill(지시 묶음) 102개, AI가 읽고 그대로 일해요 · MCP server가 아니에요

Pick the skill to install

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

This set has 102 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 29 of 102 See all on GitHub

  • action-item-extraction

    Pull the concrete commitments out of a thread — who owes what, by when. Use when the user asks what they need to do, what they promised, what is outstanding, or for action items from a conversation.

  • adding-eval-scorecard

    Adopt the per-agent eval scorecard for a GAIA hub agent: write the harness→payload adapter, run the eval to produce a REAL scorecard, link + surface it from the agent's README, wire the release gate, and (for a new agent) generalize the format. Use when asked to 'add a scorecard', 'adopt the eval s…

  • agent-hub-release

    Cut or wire the frozen-binary + npm release of an agent GAIA itself ships (the email/flagship CI pipeline: freeze -> download-server Worker /publish -> npm OIDC). Use when releasing a sidecar agent under hub/agents/ or editing a release_agent_ .yml. Maintainer release tooling only — GAIA has no pub…

  • analyzing-claude-sessions

    Analyze your own local Claude Code session transcripts to find what you actually use the agent for, how effective it is, where it fails, and what it costs. Use when asked to mine Claude Code sessions, extract use-cases or workflows from session history, measure agent effectiveness or error rates, a…

  • benchmarking-the-agent

    Measure the flagship GAIA agent against Claude Code and across models — quality, truthfulness, steps, tokens, time and real cost — with `gaia eval tasks`. Use when asked to benchmark the agent, compare models or harnesses, check whether a change cost quality, work out what a run costs, or reproduce…

  • coding

    Work on a codebase — read, search, edit and verify source files. Use when the user asks to fix a bug, add a feature, refactor, explain code, make a test pass, or change anything in a repository. Covers finding the right file, editing safely, and proving the change works before reporting it.

  • contributor-triage

    Load whenever the user is auditing, triaging, reviewing, or completing amd/gaia pull requests or issues — 'audit/triage PRs', 'what's outstanding', 'complete the ready PRs', 'merge what's ready', 'check third-party/external/community PRs or issues', 'approve workflows for contributors', 'what's lef…

  • driving-the-tui

    Use when testing or validating the GAIA TUI (tui/) by actually running it — driving screens, clicking and scrolling with the mouse, sending queries to an agent, capturing screenshots and video of a session, and reading its diagnostics, logs and traces. Covers the loopback control API end to end, ru…

  • escalation-routing

    Decide which messages need attention now, which can wait, and which belong to someone else. Use when the user asks what is urgent, what needs escalating, what they should look at first, or who should handle something.

  • gaia-build-agent

    Build a new GAIA agent with the SDK end-to-end: scaffold the package, write the Agent subclass, register @tool functions, compose reusable tool mixins, set the model + system prompt, and test it locally. Use when creating a NEW agent (a Python class inheriting from the base Agent) for the GAIA repo…

  • gaia-executive-presentation

    Generate an EXECUTIVE slide presentation (leadership / decision-maker audience) from a source document as self-contained HTML that prints cleanly to PDF, one slide per page. Use when the user asks for an executive presentation, a leadership briefing, a pitch or exec deck, or to turn a README/spec/d…

  • gaia-release

    Cut a GAIA release end-to-end: draft notes, open release PR, run pre-tag verification, push the tag, monitor the publish pipeline, and produce the Discord announcement. Also cuts release candidates (vX.Y.Z-rcN) for testing before the final. Use when the user asks to 'cut a release', 'cut a release…

  • gaia-technical-presentation

    Generate a TECHNICAL slide presentation (engineering audience) from a source document as self-contained HTML that prints cleanly to PDF, one slide per page. Use when the user asks for a technical presentation, engineering slides, an architecture or deep-dive deck, or to turn a README/spec/design do…

  • gaia-testing

    GAIA's multi-tier regression harness — runs unit, integration, and real-world (on-machine) tiers and brings back screenshots, logs, traces, planted-fact retrieval proof, and per-operation timing with anomaly flags, all collected to the local machine (no remote login needed to view). It carries GAIA…

  • gaia-tui-manual

    The GAIA terminal UI (gaia-cli) — how to build it, launch it with a real pty, drive it through the loopback control API, choose a local or cloud model provider, and read its logs. Use when running, testing, debugging, or documenting the TUI, when a preflight row blocks a launch, when driving the TU…

  • github-issue-response

    Respond to a GitHub issue, PR comment, discussion reply, or review on amd/gaia. Use when writing any reply that will be posted to GitHub — triaging a bug report, answering a usage question, responding to a feature request, replying to a contributor on a PR, or handling a reported security issue. Co…

  • inbox-triage

    Sort an inbox into what needs a reply, what needs a decision, and what is just noise. Use when the user asks to triage, catch up on, clean up, or make sense of their inbox.

  • integrate-hub-agent

    Embeds one of this repo's pre-built hub agents (under hub/agents/) into a developer's own application. Use when a developer wants to integrate, add, embed, or wire a GAIA hub agent into their app, project, or codebase — e.g. 'integrate a hub agent into my app', 'add the agent to my project', 'embed…

  • lemonade-client-patterns

    Patterns, gotchas, and conventions for threading changes through LemonadeClient, its callers, and the GAIA test suite. Apply when modifying lemonade_client.py, its providers, VLMClient, UI routers, or any file that calls Lemonade HTTP endpoints.

  • meeting-scheduling

    Turn meeting requests in email into calendar decisions — accept, decline, or propose another time. Use when a message asks to meet, when the user asks about invitations, or when checking whether a proposed time is free.

  • newsletter-digest

    Condense newsletters, promotions, and other bulk mail into one short digest and clear them out. Use when the user asks what they missed in their subscriptions, wants a digest of bulk mail, or asks to clean up promotions.

  • npm

    Use when integrating the @amd-gaia/gaia npm package — running GAIA's flagship agent, or embedding its local sidecar into a Node, TypeScript, or Electron app. Covers the one-command path, the SHA-256 integrity gate, platform coverage, starting the sidecar, the /v1/gaia/query SSE contract, and the go…

  • pr-backlog-triage

    Interactively clear a backlog of open amd/gaia PRs to zero (or to a short, justified human-review list) by fanning out one isolated subagent per PR. Use when the user asks to 'audit open PRs', 'triage the backlog', 'fix CI and merge what's safe', or similar — not for reviewing a single named PR som…

  • reviewing-agent-ui

    Review the Agent UI by looking at it, in English and Arabic, on the real desktop app when it matters. Use before calling any change to src/gaia/apps/webui, the Electron shell, or user-facing backend strings done, and when asked to test, polish or check the UI. Covers which screens to open, what to…

  • security-assessment

    Assess a reported security vulnerability in GAIA and fill a PSIRT / JIRA triage: decide if it is valid & exploitable, whether it needs a CVE + bulletin, and produce the CVSS 4.0 score, CWE, and CVE description. Use when triaging a researcher report, a security advisory, or a claude-security-audit f…

  • testing-agent-ui-release

    Release-test the GAIA desktop Agent UI end to end with computer use. Plan from what merged since the last RC or final release, drive the real desktop app through the Claude desktop app's computer use, keep a live report of what passed, failed and was never tested, file GitHub issues for what broke,…

  • testing-the-gaia-agent

    Test the flagship GAIA agent end-to-end through the Go TUI — launch it, drive it without colliding with other agents, run the capability ladder, verify skills really call their tools instead of fabricating, and check the permission gate. Use when validating the gaia agent, its skills, or the TUI ch…

  • travel-itinerary

    Assemble scattered booking confirmations into one chronological itinerary. Use when the user asks about an upcoming trip, their flight or hotel details, or wants an itinerary built from their email.

  • weekly-audit-patterns

    The non-obvious invariants of GAIA's proactive Claude audits: the one-audit-a-night rotation (claude-audit-rotation.yml) over the code audit (claude-nightly-audit.yml), security audit and doc walkthrough; the quota gate and since-last-success carry-over; the two-key dedup scheme (cluster_key per de…

Skill과 MCP의 차이

MCP = 손

AI를 외부 서비스나 데이터에 연결합니다(예: Notion 읽기, 청구서 만들기). 프로그램이나 서버가 실행 중이어야 합니다.

Skill = 안내서

작업 방법을 AI에게 가르치는 텍스트 파일. 어떤 서비스에도 연결되지 않습니다.

겹치는 경우도 있습니다. 도구를 부르는 스크립트가 있는 Skill도, 지식만 보내는 MCP도 있습니다. 하려는 작업을 기준으로 고르세요.

쓸 수 있는 앱

Claude Code

제작자 README와 repo 폴더 기준

설치

Pick a skill first

This repo has 102 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 ↑

토론

질문하고, 팁을 나누고, 안 되는 점을 알려 주세요. "도움이 됨"이 많은 순서예요.

아직 글이 없어요. 처음으로 질문하거나 공유해 보세요.

이곳의 글은 사용자가 쓴 것으로, PopNx 팀의 글이 아니에요.

로그인하고 글쓰기

GitHub 정보

GitHub 스타
1,624
Stars are for the whole repo, not each skill
제작자
amd
라이선스
MIT
최근 코드 수정
2026년 11월 17일
repo 안 SKILL.md(번역본과 템플릿 포함)
30
토픽
agents, ai, aipc, amd, genai, local, privacy, ryzenai