Repository
amd/gaia agent skills
- skills
- 44
- GitHub stars
- 1.6k
GitHub description: “Build AI agents for your PC”
- Stars
- 1,580 (176 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Dec 2024
- Homepage
- github.com/amd/gaia
- Source
- github.com/amd/gaia
- ai
- amd
- genai
- ryzenai
- agents
- aipc
- local
- privacy
Install all skills
npx skills add amd/gaiaAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in amd/gaia, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Adds a release eval scorecard to a GAIA hub agent by writing a harness adapter, running a real eval, and wiring the result into the agent's README and release gate. | amd/ | 1.6k | — | ~2.6k | Automated safety check: Pass | MIT | today |
| 2 | Walks through releasing a GAIA sidecar agent as a frozen binary plus npm client through the tag-triggered Agent Hub CI pipeline, with a human gate before publishing. | amd/ | 1.6k | — | ~3.6k | Automated safety check: Pass | MIT | today |
| 3 | Mines local Claude Code session transcripts with a deterministic Python pipeline to show what the agent is actually used for, how often it fails and what it costs. | amd/ | 1.6k | — | ~2.3k | Automated safety check: Pass | MIT | today |
| 4 | Benchmarks AMD's GAIA agent against Claude Code and across models on quality, honesty, steps, tokens, time and real cost, using gaia eval tasks. | amd/ | 1.6k | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 5 | Guides safe code changes by finding the right file with grep or semantic search, reading before editing, reproducing bugs first, and proving a fix with a real test run. | amd/ | 1.6k | — | ~2.1k | Automated safety check: Pass | MIT | today |
| 6 | Walks through scaffolding, writing and testing a new GAIA agent as a Python class with the SDK, from the base Agent subclass to registered tool methods. | amd/ | 1.6k | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 7 | Turns a source document such as a README or spec into an executive slide deck as one self-contained HTML file that prints to PDF, one slide per page. | amd/ | 1.6k | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 8 | Turns a source document such as a README or spec into a technical slide deck for engineers, as one self-contained HTML file that prints to PDF with one slide per page. | amd/ | 1.6k | — | ~1.6k | Automated safety check: Pass | MIT | today |
| 9 | Embeds one of this repo's pre-built hub agents (under hub/agents/) into a developer's own application. | amd/ | 1.6k | — | ~2.1k | Automated safety check: Pass | MIT | today |
| 10 | 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. | amd/ | 1.6k | — | ~2.2k | Automated safety check: Pass | MIT | today |
| 11 | 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… | amd/ | 1.6k | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 12 | Transcribe and summarize a meeting recording — speaker-attributed transcript, corrected mis-hearings, then a brief with decisions and action items. | amd/ | 1.6k | — | ~1.9k | Automated safety check: Pass | MIT | today |
| 13 | A skill your agent uses when integrating the @amd-gaia/agent-email npm package — embedding the GAIA email agent (a local triage/draft/send sidecar) into a Node, TypeScript, or Electron app. | amd/ | 1.6k | — | ~7.4k | Automated safety check: Pass | MIT | today |
| 14 | 14.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. | amd/ | 1.6k | — | ~8.8k | Automated safety check: Pass | MIT | today |
| 15 | 15.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… | amd/ | 1.6k | — | ~8k | Automated safety check: Notes | MIT | today |
| 16 | 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… | amd/ | 1.6k | — | ~6.4k | Automated safety check: Pass | MIT | today |
| 17 | Triage GitHub work with the gh CLI — your unread notification inbox, or one repository's issue backlog. | amd/ | 1.6k | — | ~2.3k | Automated safety check: Warn | MIT | today |
| 18 | 18.Check In Run a short personal check-in that picks up where the last one left off, following up on what the user said they would do and recording what changed. | amd/ | 1.6k | — | ~668 | Automated safety check: Pass | MIT | today |
| 19 | 19.Daily Brief Compose a short briefing from several sources at once — headlines, tracked topics, and the user's own open items — as one digest instead of separate answers. | amd/ | 1.6k | — | ~680 | Automated safety check: Pass | MIT | today |
| 20 | 20.Data Explore Load messy tabular data into SQL scratchpad tables and answer questions with real queries instead of eyeballing. | amd/ | 1.6k | — | ~633 | Automated safety check: Pass | MIT | today |
| 21 | Index a document or folder and answer questions about it with quotes from the source. | amd/ | 1.6k | — | ~555 | Automated safety check: Pass | MIT | today |
| 22 | 22.File Ops Read, write, and edit files on disk safely — locate the right file, change only what was asked, and confirm before anything destructive. | amd/ | 1.6k | — | ~926 | Automated safety check: Pass | MIT | today |
| 23 | The GAIA terminal UI (gaia-tui) — 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. | amd/ | 1.6k | — | ~866 | Automated safety check: Pass | MIT | today |
| 24 | 24.Image Gen Turn a description into an image file with local Stable Diffusion, then iterate on it. | amd/ | 1.6k | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 25 | 25.Inbox Triage Triage a mailbox — group what arrived, judge what is urgent and what actually needs the user, and say what to do about it. | amd/ | 1.6k | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 26 | Patterns, gotchas, and conventions for threading changes through LemonadeClient, its callers, and the GAIA test suite. | amd/ | 1.6k | — | ~2.5k | Automated safety check: Pass | MIT | today |
| 27 | A skill your agent uses when taking an existing in-repo GAIA agent to a published, day-one-usable hub package — porting a legacy agent under hub/agents/<id/, deciding whether an agent should ship at… | amd/ | 1.6k | — | ~2.4k | Automated safety check: Pass | MIT | today |
| 28 | 28.Price Watch Check product pages for a price drop, comparing against the lowest price seen before and alerting only on a new low. | amd/ | 1.6k | — | ~658 | Automated safety check: Pass | MIT | today |
| 29 | Recommend films, books, games, restaurants, or gear using what the user has already said they like and dislike, plus a web search for current options. | amd/ | 1.6k | — | ~622 | Automated safety check: Pass | MIT | today |
| 30 | Research a topic on the open web and write a cited Markdown report. | amd/ | 1.6k | — | ~620 | Automated safety check: Pass | MIT | today |
| 31 | 31.Rss Digest Read an RSS or Atom feed and summarize the newest entries. An agent skill from amd/gaia. | amd/ | 1.6k | — | ~787 | Automated safety check: Pass | MIT | today |
| 32 | 32.Source Watch Check a web page or feed for something worth telling the user about, remembering what was already reported so nothing repeats. | amd/ | 1.6k | — | ~698 | Automated safety check: Pass | MIT | today |
| 33 | 33.Summarize Summarize a document, meeting transcript, or email — pick a style that matches what the content actually is, and fold long input forward in sections instead of losing the back half. | amd/ | 1.6k | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 34 | Enumerate every requested item in long text documents or transcripts, with fields and source evidence. | amd/ | 1.6k | — | ~524 | Automated safety check: Pass | MIT | today |
| 35 | 35.Gaia Voice How GAIA talks and what it must never claim. An agent skill from amd/gaia. | amd/ | 1.6k | — | ~862 | Automated safety check: Pass | MIT | today |
| 36 | The non-obvious invariants of the proactive nightly Claude audit workflow (.github/workflows/claude-nightly-audit.yml): the day-of-week mode selector, the two-key dedup scheme (clusterkey per… | amd/ | 1.6k | — | ~4.4k | Automated safety check: Pass | MIT | today |
| 37 | Pull the concrete commitments out of a thread — who owes what, by when. | amd/ | 1.6k | — | ~393 | Automated safety check: Pass | MIT | today |
| 38 | Decide which messages need attention now, which can wait, and which belong to someone else. | amd/ | 1.6k | — | ~416 | Automated safety check: Pass | MIT | today |
| 39 | 39.Inbox Triage Sort an inbox into what needs a reply, what needs a decision, and what is just noise. | amd/ | 1.6k | — | ~320 | Automated safety check: Pass | MIT | today |
| 40 | Turn meeting requests in email into calendar decisions — accept, decline, or propose another time. | amd/ | 1.6k | — | ~420 | Automated safety check: Pass | MIT | today |
| 41 | Condense newsletters, promotions, and other bulk mail into one short digest and clear them out. | amd/ | 1.6k | — | ~335 | Automated safety check: Pass | MIT | today |
| 42 | Assemble scattered booking confirmations into one chronological itinerary. | amd/ | 1.6k | — | ~361 | Automated safety check: Pass | MIT | today |
| 43 | Help a developer report a GAIA TUI, WebUI or agent problem, explicitly share a snapshot with Claude Code or Codex through MCP, and validate isolated worktree fixes. | amd/ | 1.6k | — | ~882 | Automated safety check: Pass | MIT | today |
| 44 | A skill your agent uses 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. | amd/ | 1.6k | — | ~9.7k | Automated safety check: Warn | MIT | today |
Questions, answered from the data.
What is the best skill in amd/gaia?
GAIA Agent Eval Scorecard from amd/gaia ranks first of the 44 skills in amd/gaia listed here, with the highest score: its repository has 1.6k GitHub stars, its SKILL.md loads about 2.6k tokens and it passes the automated safety check with no findings. Next come GAIA Sidecar Agent Release and Analyzing Claude Code Sessions.
Are the skills in amd/gaia official?
None yet. All 44 skills in amd/gaia listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from amd/gaia?
Run npx skills add amd/gaia in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.