productionize
Production readiness review — strip prototype scaffolding, harden code, validate cost model, generate prod/ artifacts
What this skill does
# Productionize **You are the Productionize Orchestrator** — reviewing a pipeline for production readiness and generating hardened production artifacts in a `prod/` subdirectory. ## Natural Language Triggers - "productionize this pipeline" - "make this production ready" - "production readiness review" - "harden this pipeline" - "prepare this for deployment" ## Parameters ### Pipeline directory (positional) Path to pipeline directory. ### --dry-run (optional) Print the review report without writing any files. ## Execution ### Step 1: Readiness Review Check the following items. Use ✓ / ⚠ / ✗: **Prompts:** - ✓ All prompt files exist and have version headers - ✓ Evaluator prompt is separate from generator prompts - ⚠ System prompt >2000 tokens — consider trimming - ✗ No evaluator prompt found — add one before production **Eval:** - ✓ `eval/cases.jsonl` exists with ≥5 cases - ✓ `eval/results.jsonl` exists with recent run (within 7 days) - ✓ Pass rate ≥85% in most recent eval run - ⚠ Pass rate <85% — do not productionize until quality gate passes - ✗ No eval run found — run: `aiwg nlp eval <dir>` **Code:** - ✓ Code stub exists - ⚠ Framework dependency found (langchain/langgraph) — consider removing if not load-bearing - ✗ No timeout handling on LLM calls - ✗ No retry logic for rate limits (429) and transient errors (502/503) - ✗ No structured output validation (schema defined but not enforced at runtime) - ✗ No token budget cap (max_tokens not set) **Cost:** - ✓ `cost-model.yaml` exists - ⚠ No `cost-model.yaml` — generate: `aiwg nlp estimate-cost <dir>` ### Step 2: Generate Production Artifacts If no ✗ items (or user confirms proceed with warnings): Generate `prod/` directory: ``` prod/ ├── prompts/ # Copied from dev (hardened if changes made) ├── src/ │ └── pipeline.py # Hardened version: timeouts, retries, validation ├── Dockerfile # Minimal container ├── cost-model.yaml # From cost analysis └── README.md # Ops runbook ``` **Hardening applied automatically:** 1. **Add timeouts** — wrap every LLM call: `timeout=30` (or pipeline config value) 2. **Add retry wrapper** — exponential backoff on 429, 502, 503 3. **Add structured output validation** — Pydantic (Python) or Zod (TypeScript) schema enforcement 4. **Add token budget enforcement** — `max_tokens` from pipeline config enforced at call site 5. **Add cost cap guard** — abort if estimated cost exceeds `warn_above_usd` 6. **Remove dev logging** — strip verbose debug output **Framework removal (if detected):** - Check if LangChain/LangGraph calls are load-bearing - If replaceable: rewrite the relevant section without the dependency - If not replaceable: flag with ⚠ and note in README ### Step 3: Generate Dockerfile ```dockerfile FROM python:3.12-slim WORKDIR /app COPY requirements.txt . RUN pip install --no-cache-dir -r requirements.txt COPY prod/ . CMD ["python", "src/pipeline.py"] ``` Or TypeScript equivalent with Node 22. ### Step 4: Generate Ops Runbook (prod/README.md) Sections: - Overview (pipeline name, pattern, what it does) - Start / Stop - Health check command - Rollback procedure - Monitoring (what to watch: latency, error rate, cost) - Eval re-run instructions ### Step 5: Final Report ``` Productionization Complete: pipelines/<name>/prod/ ✓ Prompts hardened ✓ Retry + timeout wrapper added ✓ Pydantic output validation added ✓ Dockerfile generated ✓ Ops runbook written Removed: langchain dependency (replaced with direct anthropic SDK call) Deploy: docker build -t <name>:latest . && docker run <name>:latest Cost model: prod/cost-model.yaml (~$9/mo at 100k calls) ``` ## References - @$AIWG_ROOT/agentic/code/addons/nlp-prod/README.md — nlp-prod addon overview - @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/vague-discretion.md — Concrete readiness thresholds (pass rate ≥85%, eval within 7 days) - @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/human-authorization.md — Confirm with user when ✗ items found before generating prod artifacts - @$AIWG_ROOT/docs/cli-reference.md — CLI reference for aiwg nlp commands
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.