build-with-deepmind
Skill1 starsChanged 5 months agoMITView on GitHub
Builds products on Google DeepMind Gemini, Gemma, Nano, Live agents, proactive async agents, and edge deployment. Use when integrating Gemini API, Gemma open models, Android on-device AI, conversational/voice agents, agent manager patterns, or edge Gemma inference.
In this repository51 other files it gives its agents.
- architect-enterprise-aiSkill
- author-agent-skillsSkill
- build-agent-harnessesSkill
- build-aiewf-2024-ragSkill
- build-generative-mediaSkill
- build-multimodal-productsSkill
- build-rag-search-stacksSkill
- build-robotics-aiSkill
- build-with-microsoft-aiSkill
- build-with-openaiSkill
- deploy-public-sector-aiSkill
- design-agent-skillsSkill
- evaluate-with-braintrustSkill
- lead-ai-engineering-teamsSkill
- lead-ai-transformationSkill
- learn-summit-2023-remoteSkill
- learn-summit-2023-talksSkill
- navigate-aie-europe-2026Skill
- navigate-aiewf-2024-keynotesSkill
- observe-ai-productionSkill
- operate-agent-memorySkill
- operate-legal-ai-agentsSkill
- operate-openclaw-agentsSkill
- optimize-llm-inferenceSkill
- plan-sovereign-aiSkill
- price-ai-productsSkill
- run-aiewf-2024-evalsSkill
- run-llm-evalsSkill
- run-summit-2023-workshopsSkill
- secure-ai-agentsSkill
- ship-ai-as-pmSkill
- ship-aiewf-2024-agentsSkill
- train-llms-locallySkill
- architecture-reviewSkill
- chat-failure-auditSkill
- create-a-skillSkill
- cross-model-reviewSkill
- cto-weekly-reviewSkill
- friction-auditSkill
- ig-carouselSkill
- pdf-reportSkill
- raise-prSkill
- reel-editSkill
- research-reportSkill
- ship-checkSkill
- spec-grounded-designSkill
- state-lifetime-decisionSkill
- ste100Skill
- scroll-engineeringSkill
- ui-uxSkill
- verify-like-a-userSkill
The file
Files
Build with DeepMind
Action playbook from nine Google DeepMind @ AI Engineer talks. Do not summarize talks — pick a workflow theme and execute it.
Supporting files:
- workflows.md
- source-index.md
Optional: ./skill-outputs/build-with-deepmind/
Step 0 — Pick workflow theme
What is the user trying to do?
├─ Gemini API / Gemini 3 / multimodal generation → gemini-api
├─ Gemma open models, fine-tune, self-host → gemma-open
├─ Android on-device Gemini Nano → gemini-nano
├─ Voice / Live conversational agents → live-agents
├─ Proactive async coding agents (Jules patterns) → proactive-agents
├─ Agent manager / browser / IDE control plane → agent-manager
├─ Edge Gemma deployment → edge-ai
└─ Train/serve diffusion image/video at scale → generative-scaleOpen workflows.md for the matching section.
Install
cp -r skills/build-with-deepmind ~/.claude/skills/
cp -r skills/build-with-deepmind ~/.cursor/skills/
cp -r skills/build-with-deepmind ~/.codex/skills/
cp -r skills/build-with-deepmind ~/.agents/skills/Source: playlists/google-deepmind-ai-engineer/ in ingest-into-skills.
Cross-cutting rules
| Rule | Source |
| Track Gemini model + API + app releases together | [src-001 @ 0:04:53] |
| Eval tool-calling when upgrading Gemini generations | [src-002 @ 0:02:12] |
| Match Gemma size to device latency budget | [src-003 @ 0:01:28] |
| Live API for realtime voice; batch API for async | [src-005 @ 0:09:04] |
| Log proactive agent actions for trust | [src-006 @ 0:09:00] |
Output to user
- Name theme + deliverables
- Save artifacts under
./skill-outputs/build-with-deepmind/when requested - Do not auto-commit
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

