FastAPI Best Architecture (fba) project development guide. Provide complete architecture specifications, coding styles, and plugin development guidance.
分析 JSON Schema 生成测试数据的 Python 脚本
Designs intuitive Python library APIs following principles of simplicity, consistency, and discoverability. Handles API evolution, deprecation, breaking changes, and error handling. Use when designing new library APIs, reviewing existing APIs for improvements, or managing API versioning and deprecations.
IDA Pro reverse-engineering skill for Codex, Claude Code, and OpenCode. Use when a user needs live IDA or Hex-Rays analysis through the local ida-pro-skill CLI and installed IDA bridge, especially for instance discovery, metadata, cursor or selection context, entrypoints, functions, callers, imports, strings, xrefs, pseudocode, globals, structs, renames, comments, byte patches, function creation, or explicit IDAPython, including WSL-to-Windows IDA setups.
Guides using and contributing to LLMaps: Python library for interactive web maps (MapLibre, single HTML). Use when building maps with llmaps (pip or repo), when editing the llmaps repo, or when the user mentions llmaps, MapLibre, or map generation.
Write code using Agora SDKs (agora.io) for real-time communication. Covers RTC (video/voice, live streaming, screen sharing), RTM/signaling, Conversational AI voice agents, Cloud Recording, Server Gateway, and token generation. Use for Agora, RTC, RTM, video calling, voice calling, screen sharing, recording, tokens, signaling, or ConvoAI requests across Web, React, Next.js, iOS, Android, Go, and Python. Triggers include agora-rtc-sdk-ng, agora-rtc-react, agora-rtm, agora-agent-server-sdk, AgoraVoiceAI, AgoraClient, useConversationalAI, useTranscript, useAgentState, Cloud Recording, Server Gateway, and Agora authentication.
在 MergeMeet 專案中建立或修改 API 路由時使用此 skill。它強制執行「禁止尾隨斜線」標準以防止 404 錯誤。適用於處理 FastAPI 路由、修復 404 錯誤或審查 API 端點定義時。
Auto-activate for alembic/, alembic.ini, advanced_alchemy imports. Expert knowledge for Advanced Alchemy / SQLAlchemy ORM patterns. Produces ORM models with audit trails, repository/service patterns, and Alembic migrations. Use when: defining models with UUIDAuditBase, building repositories and services, configuring SQLAlchemy plugins for Litestar/FastAPI/Flask/Sanic, creating DTOs, running Alembic migrations, using custom types (EncryptedString, FileObject, PasswordHash, DateTimeUTC), composing filters and pagination, choosing base classes and mixins, configuring dogpile.cache query caching, setting up read/write replica routing, or managing file storage with obstore/fsspec backends. Not for raw SQLAlchemy without Advanced Alchemy abstractions.
Verify and install project tooling before feature development. Detects language (Node/TS, Python, Rust, Go), installs linter, formatter, type checker, dead code detection, pre-commit hooks, test framework, and standardized scripts. Idempotent — tracks state in .tooling-state.json. Use when starting a new project, when /develop Phase 4c runs, or when the user says "bootstrap", "setup tooling", "install dev tools", "quality gates".
Security audit of Python source code (.py, setup.py, pyproject.toml) for security vulnerabilities using Bandit AST analysis. (1) Detects exec/eval code execution, pickle/yaml deserialization, subprocess shell injection, SQL injection, hardcoded credentials, weak cryptography, OWASP Top 10 Python issues. Use for Python security audits, Django/Flask apps, malicious Python code triage, CI/CD pipelines. NOT use for dependency/package audits (use guarddog), non-Python code (use graudit), shell scripts (use shellcheck). For mixed Python projects, combine with graudit -d secrets for comprehensive coverage.
Help developers write code that interacts with Alkahest escrow contracts using the TypeScript, Rust, or Python SDK
This skill should be used when the user asks to "create api endpoint", "django ninja", "django api", "add endpoint", "rest api django", "ninja router", "api schemas", or mentions API development, endpoint organization, or Pydantic schemas in Django projects. Provides Django Ninja patterns with 1-endpoint-per-file organization. --- # Django Ninja API Development Opinionated Django Ninja patterns with single-endpoint-per-file organization. ## Core Principles 1. **One endpoint = one file** - Each endpoint lives in its own file 2. **Logical grouping** - Endpoints grouped in subpackages by domain 3. **Router per group** - Each group has its own router 4. **Schemas in separate package** - Pydantic models in `schemas/` 5. **Services for logic** - Business logic in services, not endpoints ## API Structure ``` myapp/ ├── api/ │ ├── __init__.py # Main NinjaAPI instance │ ├── users/ │ │ ├── __init__.py # Router: users_router │ │ ├── list.py # GET /users/ │ │ ├── detail.py # GET /users/{id} │ │ ├── create.py # POST /users/ │ │ ├── update.py # PUT /users/{id} │ │ └── delete.py # DELETE /users/{id} │ ├── products/ │ │ ├── __init__.py │ │ ├── list.py │ │ ├── detail.py │ │ └── search.py │ └── auth/ │ ├── __init__.py │ ├── login.py │ ├── logout.py │ └── refresh.py └── schemas/ ├── __init__.py ├── user.py # UserIn, UserOut, UserPatch ├── product.py └── common.py # Pagination, errors ``` ## Main API Setup In `api/__init__.py`: ```python from ninja import NinjaAPI from ninja.security import HttpBearer from .users import router as users_router from .products import router as products_router from .auth import router as auth_router class AuthBearer(HttpBearer): def authenticate(self, request, token): # Token validation logic from ..services.auth import AuthService return AuthService.validate_token(token) api = NinjaAPI( title="My API",
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
