菜单
Modal CLI for serverless GPU/cloud compute. Use when user mentions modal, deploying to modal, running GPU workloads, or serverless Python functions. Check `which modal` first — if missing, offer: `pip install modal && modal setup`. Covers run/serve/deploy, apps, containers, secrets, volumes, and workspace management.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Generate images using OpenAI (default) or Gemini. Use when asked to generate, create, or make images. Supports text-to-image and image editing with reference images.
Plans, audits, and implements scalable programmatic SEO systems with URL inventory, intent mapping, metadata, schema, internal linking, sitemaps, ISR/static rendering, and quality gates. Use when the user mentions 'programmatic SEO,' 'pSEO,' '100k pages,' 'generate SEO pages,' 'scaled landing pages,' 'template pages,' 'SEO page factory,' 'dynamic SEO routes,' 'sitemap shards,' 'keyword cannibalization,' 'doorway pages,' or 'thin content at scale.' Does not replace general SEO audits, AI SEO citation work, or llms.txt tasks unless PSEO scale is central.
Use when setting up, deploying, or debugging Nia's Twilio-based channels: voice (phone), SMS, and WhatsApp. All three share one Twilio number, one webhook server, and one set of credentials under channels.twilio. Covers config schema, cloudflared named-tunnel setup, Twilio Console webhook wiring, `nia phone` CLI, `place_call` / `send_message` MCP tools, the WhatsApp Sandbox 24h customer-service window, and the shared TwilioWebhookServer's dedup + rate-limit middleware. Trigger on mentions of "phone", "call", "voice", "sms", "whatsapp", "twilio", "realtime", "media stream", "cloudflared", or when deploying Nia to a new machine and a Twilio surface needs to come up.
Persistent task management via Beads CLI (bd). Use when user mentions tasks, todos, issues, or tracking work. Check `which bd` first — if missing, offer: `npm install -g @beads/bd`. All commands: run from `$BEATS_DIR` (for example `~/.niahere/beads`) and use `bd <command>`. Always label: `--label project:<project-name>`. Run `bd --help` or `bd help --all` for available commands. Not for ephemeral in-conversation tracking.
QA test a web application using Playwright. Use when asked to "qa", "QA", "test this site", "find bugs", "dogfood", "verify frontend behavior", "check UI rendering", "test user flows", "debug visual issues", "take a snapshot", "take a screenshot", "browser automation", "Playwright MCP", "ref system", or review quality of any web app (local or deployed). Five modes: diff-aware (auto on feature branches), full (systematic exploration), quick (30-second smoke test), single-page (verify one page or component), regression (compare against baseline). Produces structured report with health score, screenshots, and repro steps. Uses Playwright MCP tools or CLI fallback. Includes Playwright MCP reference (tool selection, ref system, token optimization, session management).
Transcribe or subtitle audio/video files using whisper.cpp (whisper-cpp), with a default medium model path and ffmpeg-based extraction.
| name | modal-cli |
| description | Modal CLI for serverless GPU/cloud compute. Use when user mentions modal, deploying to modal, running GPU workloads, or serverless Python functions. Check `which modal` first — if missing, offer: `pip install modal && modal setup`. Covers run/serve/deploy, apps, containers, secrets, volumes, and workspace management. |
Before any modal command, verify the CLI is available:
which modal
If not found, ask the user:
Modal CLI not found. Install it?
pip install modal
After install, run auth setup:
modal setup
This opens a browser for token auth. If modal still isn't on PATH after pip install, use:
python -m modal setup
If found but not authed, check with:
modal token info
If that errors, run modal setup to authenticate.
| Command | Purpose |
|---|---|
modal run <file> | One-off execution of a script/function |
modal serve <file> | Local dev with hot-reload |
modal deploy <file> | Production deployment |
modal app list | List deployed apps |
modal app logs <name> | Stream logs for a deployed app |
modal app stop <name> | Stop a running app |
modal shell | Interactive shell in Modal environment |
pip install modal
modal setup
modal run hello.py # validate end-to-end
modal run my_app.py # test locally
modal serve my_app.py # hot-reload dev
modal deploy my_app.py # ship it
modal container list
modal container logs <id>
modal container exec <id> -- bash -lc "nvidia-smi"
modal secret create my-secret KEY=value
modal volume create my-vol
modal environment create dev
modal config set-environment dev
modal token info — check current authmodal token new — create token via browsermodal token set — set token credentials directlymodal profile list / activate — switch workspacesmodal config show — print effective configEnvironment variables: MODAL_TOKEN_ID, MODAL_TOKEN_SECRET, MODAL_ENVIRONMENT, MODAL_PROFILE
modal secret list/create/delete (supports .env import)modal volume create/list/ls/put/get/rm/deletemodal dict create/list/items/get/clear/deletemodal queue create/list/peek/len/clear/deletemodal nfs list/create/ls/put/get/rm/deletemodal environment list/create/delete/updatemodal deploy or modal runmodal app listmodal app logs <name>modal shell or modal container execmodal setup