Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By tuongaz
Generate and look up SeeFlow flows from natural-language prompts, creating validated flow.json and node-sidecar files that serve as architectural ground truth for your project.
npx claudepluginhub tuongaz/seeflowUse when the seeflow skill needs to explore a project's codebase for the parts that match the user's flow request. Returns the user-prompt-specific half of the discovery brief (scope, code pointers, endpoints, tech stack). Read-only; never writes files or hits the network. Runs in parallel with seeflow-system-analyzer.
Use when the seeflow skill needs to turn a Phase 1 context brief into a node + connector draft that respects SeeFlow's abstraction rules (one node per workflow / service / DB / external API). Pure reasoning; no tool access.
Use when the seeflow skill needs to overlay playAction designs (and generated bun script bodies) onto a node draft. Reads code to pick correct kinds + idempotent inputs; never writes.
Use when the seeflow skill needs to overlay statusAction designs (and generated bun script bodies) onto a node draft. Reads code to pick observable state sources; never writes.
Use when the seeflow skill needs to learn how a project boots, tests, and feeds data into itself — independent of any specific user flow request. Returns runtime profile, local dev setup, integration test pattern, fixtures, data-entry paths, gotchas, and tech adaptations. Read-only; never writes files or hits the network. Runs in parallel with seeflow-code-analyzer.
This skill should be used before `/seeflow` whenever the user phrases the request as inspection rather than creation — "show me", "show the", "how does X work", "what does X do", "diagram our system", "explain the flow", "where does X live", "what handles Y", "what depends on Z", or names a flow by slug/title without an explicit "create / scaffold / generate / add" verb. Also use when onboarding to a repo that already has seeflow flows registered. Read-only — never mutates flows; auto-hands off to `/seeflow` only when no matching flow is registered.
This skill should be used when the user explicitly asks to "create a flow", "generate a flow", "scaffold a SeeFlow flow", or "add a flow to this repo" — or when a previous /seeflow-lookup has already reported no matching flow exists. Inspection phrasing ("show me", "how does X work", "diagram our system", "explain the flow") routes to /seeflow-lookup first; that skill auto-hands off here only when nothing is registered. Orchestrates five sub-agents and the `seeflow` CLI to turn a natural-language prompt into a registered, validated SeeFlow flow at <project>/flow.json (node-attached files live under <projectPath>/nodes/<id>/).
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
AI image generation Creative Director powered by Google Gemini Nano Banana models. Claude interprets intent, selects domain expertise, constructs optimized prompts, and orchestrates Gemini for best results.
Architecture diagrams that actually run, generated by AI agents.

Turn your static system architecture into a live control panel wired directly to your running application. Click a node, fire a real request, watch downstream services light up as your app emits events back.
The SeeFlow plugin reads your codebase, understands your architecture, and generates the full diagram and request scripts automatically. Works with Claude Code, Codex, Cursor, and Windsurf.
npx -y @tuongaz/seeflow@latest start
# then open http://localhost:4321
Requires Bun ≥ 1.3 (or Node with npx). The studio scans $(pwd)/flow.json on start and auto-registers that flow if present. The studio's registry persists under ~/.seeflow/ across restarts.
⚠️ Heads up: Play and Status scripts run inside the container, so generated scripts that talk to services on your host — HTTP calls to
localhost, host binaries likepsql/redis-cli, your project's CLI — will not work. Interactive nodes are likely to fail. Use the native path above for full functionality.
docker run --rm -it -p 4321:4321 -v $(pwd):/workspace tuongaz/seeflow
The image ships with a pre-registered Order Pipeline demo so you can see the canvas immediately, and the studio scans /workspace/flow.json on start.
Skill installer (recommended):
npx skills add tuongaz/seeflow
Then just ask:
/seeflow show me the shopping cart feature
The plugin scans your routes and database connections, generates flow.json, wires up demo scripts, and opens the canvas at localhost:4321.
/seeflow-lookup — consult an existing flowOnce a flow is registered, agents can read it back as architectural ground truth:
/seeflow-lookup list # catalog of registered flows
/seeflow-lookup flow <id> # nodes + connectors (no detail content)
/seeflow-lookup node <flowId> <nodeId> # single node with detail/html inlined
/seeflow-lookup flow <id> --full # everything inlined
/seeflow-lookup node <flowId> <nodeId> --with-scripts # adds play.ts / status.ts bodies
Read-only. JSON output. Start cheapest (list) and drill in.
The component node type turns a canvas node into a json-render-powered reactive UI driven by a small catalog of shadcn-styled primitives (Card, Button, Input, Chart, Markdown, etc.). The spec lives at <project>/nodes/<id>/spec.json — declaring an element tree, optional initial state, and a typed action vocabulary — while flow.json carries only the type: 'component' tag. Two action kinds are supported: set actions mutate local state via JSON Pointer paths, and script actions POST to /api/flows/:id/nodes/:nodeId/actions/:name which spawns the matching script under nodes/<id>/ (e.g. nodes/<id>/actions/<name>.ts) and merges the JSON response back into state.
Cloud vendor icons (AWS, GCP, Azure) install on demand into a local cache. Icon ids encode the vendor as a prefix — aws:lambda, gcp:cloud-run, azure:functions, iconify:logos:google-cloud — while unprefixed names continue to resolve against the bundled Lucide set.
seeflow icons list # JSON summary of installed + available packs
seeflow icons add aws # download + extract + index the AWS pack
seeflow icons add azure --accept-terms # Microsoft requires explicit acceptance
seeflow icons add gcp --pack-url <url> # override the default download URL
seeflow icons update aws # re-install (re-downloads from upstream)
seeflow icons remove aws # drop the pack from cache + index
Packs install under ~/.seeflow/icons/<vendor>/<version>/ with a shared index.json. Installs are serialized per vendor — a second seeflow icons add aws while the first is running waits rather than racing.
Open any icon picker on a canvas node, click Browse packs in the picker footer, then Install on the vendor row. Azure prompts for license acceptance; AWS and GCP proceed directly. A progress toast tracks bytes downloaded, persists across popover close, and refreshes the picker's vendor tabs the moment the pack is indexed. Vendor tabs (Bundled · AWS · GCP · Azure · Logos) appear above the icon grid; uninstalled vendors render disabled with an inline Install affordance.