Agent skills for Zed

FastAPI advanced patterns including lifespan, dependencies, middleware, and Pydantic settings.

Use when FastAPI async patterns for building high-performance APIs.

Create a Python FastAPI service that extracts structured data from images or documents using multiple LLM backends (Local Call…

Implements a robust Redis-based mechanism for gracefully stopping and managing AI agent workflows in real-time.

Provides comprehensive guidance for Fastify framework including routing, plugins, JSON schema validation, hooks, serialization, and…

Queries and analyzes top potential TikTok Shop creator rankings and performance data using the FastMoss intelligence API.

Queries and analyzes TikTok Shop creator showcase products, sales volume, GMV, and commission data using the FastMoss API.

Searches and analyzes TikTok Shop creators by nickname or keyword using FastMoss data via Wenmai standard API.

Use when the user asks to investigate, audit, trace, or explain how an existing feature, issue, module, workflow, API, config, or behavior…

When to activate: feature flags, feature toggles, gradual rollout, kill switch, LaunchDarkly, Unleash, A/B testing infrastructure, flag…

Framework-driven feature and initiative prioritization using RICE, ICE, or weighted scoring.

Write a game design document from a one-liner, rough draft, or feature discussion.

Generate a technical implementation plan from a game design document or a brief description.

Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

Build a structured PRD that connects problem, users, solution, and success criteria.

Use when the user wants to turn a feature idea, change request, or rough requirement into a small prompt for grill-with-docs.

Scores backlog items with RICE/WSJF/Kano and files GitHub issues for top candidates.

Analyzes competitor feature implementations and audits internal product capabilities to determine whether to build, adapt, or skip new…

Use when someone wants to know whether a change actually works and is not AI slop: "test this", "QA it", "write tests for the feature"…

Record a video walkthrough of a feature and add it to the PR description

Initialize federation on this node — generate keypair and configure peers