Skip to content
cccskills
FreePublished on GitHub

genai-iterate

Iterate on a GenAI notebook against the self-hosted stack via the genai-stack CLI (config dirs, auth, subdomains, quantization, GPU/VRAM). Arguments: <notebook|service> [--service comfyui|forge|vllm] [--quant int4|fp8] [--validate] [--bg]

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md3.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

GenAI Iterate

Iterer sur un notebook GenAI (MyIA.AI.Notebooks/GenAI/) contre la stack auto-hebergee, en pilotant le CLI scripts/genai-stack/genai.py. Couvre l'Epic #1385 (GenAI series + hosting). Pour les cycles batch, deleguer a l'agent genai-iterator en async.

Arguments

  • <notebook|service> : chemin notebook ou nom de service (comfyui-qwen, forge-turbo, vllm-zimage).
  • --service comfyui|forge|vllm : service cible si ambigu.
  • --quant int4|fp8 : forcer une quantization (Nunchaku INT4 ~4GB / FP8 ~29GB).
  • --validate : lancer la validation stack (genai.py validate + skill validate-genai).
  • --bg : iteration en background.

Process

Phase 0 — Config & secrets (HARD)

  • .env reel = MyIA.AI.Notebooks/GenAI/.env (gitignored) ; template .env.example (carte sous-domaines).
  • Secrets uniquement dans .env. Jamais de literal inline, jamais os.getenv("KEY","<fallback>"), jamais imprimer une valeur de token (cf .claude/rules/secrets-hygiene.md).

Phase 1 — Pre-flight (CLI genai-stack)

python genai.py docker status # service up ? (docker exige sa sous-commande : status/start/stop — commands/docker.py:277)
python genai.py auth audit    # token present + correct (Bearer comfyui / Basic forge / none vllm) ? (auth exige une action : init/sync/audit/get-token/reconstruct-env)
python genai.py gpu           # VRAM libre sur le GPU cible ?
python genai.py quant summary # bonne quant chargee ?
  • comfyui-qwen : GPU0, Bearer (COMFYUI_API_TOKEN ou alias COMFYUI_AUTH_TOKEN). forge-turbo : GPU1, Basic (FORGE_USER/FORGE_PASSWORD). vllm-zimage : GPU1, no auth. VRAM idle = docs/genai/genai-services.md.

Phase 2 — Quantization (arbitrage VRAM)

  • GPU 8GB => genai.py quant apply qwen (Nunchaku INT4 ~4GB) obligatoire.
  • GPU haut de gamme => FP8 possible (genai.py quant apply zimage).
  • Simuler d'abord : genai.py quant apply <service> --dry-run.

Phase 3 — Iteration notebook

  • Moderniser libs/APIs obsoletes (deleguer notebook-modernizer).
  • Executer via MCP Jupyter (deleguer notebook-executor).
  • Valider structure/exec/pedagogie (deleguer notebook-validator).

Phase 4 — Commit (regle C.2)

  • Notebook AVEC outputs reels. Pas de markdown en remplacement d'execution.
  • Pas de leak LOCAL_MODE dans les outputs committes (re-executer en remote propre).
  • Pas d'URL placeholder yourdomain.com — vrai sous-domaine.

FLAGS connus (inventaire 2026-05-23)

  • 02-5-Multi-Model-TTS-Gateway 401.
  • Naming COMFYUI_API_TOKEN = COMFYUI_AUTH_TOKEN (alias canonique, deux noms pour le même secret — géré par render_envs.py). COMFYUI_BEARER_TOKEN n'est plus géré.

Anti-patterns interdits

  • Literal de secret inline / os.getenv avec fallback secret / imprimer un token.
  • Empiler deux gros modeles au-dela de la VRAM d'un GPU (OOM).
  • Committer avec LOCAL_MODE actif ou sans outputs reels.
  • Script ad-hoc au lieu du CLI genai.py.

Voir aussi

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Cycle 30 min du secrétaire vérificateur myia-po-2028:CoursIA-3. Atteste en tiers, du plus ancien au plus récent, les PRs ouvertes sans dossier valide (chaque READY, une fois lu et approuvé par ai-01, est mergé sans attendre son cycle), et fait circuler l'information sur workspace-CoursIA-3.

The English summary is being prepared. Showing the original description.

jsboige/CoursIA16Updated Oct 21, 2026

Analyze a Slidev deck qualitatively — organ reports (structure, composition) + vision AI on rendered PNGs. Arguments: <deck_id> [--slides 1,5,10]

The English summary is being prepared. Showing the original description.

jsboige/CoursIA16Updated Oct 21, 2026

Build or improve Jupyter notebooks iteratively with quality scoring. Arguments: <new|improve|fix> <path> [--topic] [--domain] [--level] [--quality] [--max-iter]

The English summary is being prepared. Showing the original description.

jsboige/CoursIA16Updated Oct 21, 2026

Detect cell-ordering / enchainement problems in Jupyter notebooks (canonical-order slippage, misplaced or forgotten cells). Arguments: [target] [--severity HIGH|MED|LOW] [--json]

The English summary is being prepared. Showing the original description.

jsboige/CoursIA16Updated Oct 21, 2026

Clean up and reorganize markdown in enriched Jupyter notebooks. Arguments: [target] [--dry-run] [--aggressive] [--hierarchy-only]

The English summary is being prepared. Showing the original description.

jsboige/CoursIA16Updated Oct 21, 2026

Cycle de coordination ai-01 (coordinateur UNIQUEMENT — jamais sur un worker). Lit memoire + dashboards + inbox + GitHub, merge les PRs pretes, tranche les design-gates, dispatche des grains par lane, reporte. Arguments: [--dispatch] [--focus <topic>]

The English summary is being prepared. Showing the original description.

jsboige/CoursIA16Updated Oct 21, 2026

See all skills by jsboige

Report a problem with this skill