发现 Skills

Post to X (Twitter) using the HTTP Browser API. Supports tweets, replies, threads, and media uploads without API costs.

Integrated judgment for in-depth research; used when multiple sub_reports are complete and a synthesis.md needs to be produced to clarify the main-line judgments, strength of evidence, cross-dimensional consensus, key conflicts, explanations for conflicts, uncertainties, and answers to the original question. It is intended to “think through the conclusions first” and not to directly write the final report.

PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.

Implement reliable data backup and recovery strategies with automated scheduling, encryption, rotation policies, and disaster recovery testing. Covers database backups, file system snapshots, and cloud storage patterns. Triggers on backup strategy, disaster recovery, or data protection requests.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. Use this toolkit when Claude needs to fill a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Build production RAG systems with LangChain orchestration and Qdrant vector store. Covers 8 RAG architectures (Simple, HyDE, CRAG, Self-RAG, Agentic), document processing, semantic chunking, retrieval chains, and evaluation with LangSmith/RAGAS. Use when implementing RAG pipelines, semantic search, or AI knowledge systems. NOT for simple keyword search.

Async REPL Protocol

Provides comprehensive guidance for Django framework including models, views, templates, forms, admin, REST framework, and deployment. Use when the user asks about Django, needs to create Django applications, implement models and views, or build Django REST APIs.

Provides comprehensive guidance for FastAPI framework including routing, request validation, dependency injection, async operations, OpenAPI documentation, and database integration. Use when the user asks about FastAPI, needs to create FastAPI applications, implement REST APIs, or build high-performance Python web services.

Provides comprehensive guidance for Runway ML including AI video generation, image editing, and creative AI tools. Use when the user asks about Runway ML, needs to generate AI videos, edit images with AI, or work with creative AI tools.

Methodological framework for analyzing production failures and preventing recurrences.

Improves CLAUDE.md by analyzing conversation patterns. Use when Claude keeps repeating a mistake, when teaching a new preference, or when consolidating guidance from repeated instructions. Captures recurring corrections and style preferences into project instructions.

Targeted API penetration testing using a GTFO-first approach: find the highest-impact vulnerability fast, prove it with a PoC, and move on. Covers five attack families: AuthN/AuthZ, BOLA/IDOR, Input Validation, SSRF, and Business Logic. Each family is a loadable module with specific test cases, payloads, and PoC templates. Trigger when user mentions "API pentest", "API security test", "test this API", "find vulnerabilities in this endpoint", "BOLA", "IDOR", "broken auth", "injection test", "SSRF", "business logic flaw", "API attack", or shares API docs, Swagger/OpenAPI specs, Postman collections, or curl commands.

Skill for defining terminology and data structures used throughout the project. Covers domain terminology, entities, relationships, and schema design. Use proactively when starting a new project or when data structures are unclear. Triggers: schema, terminology, data model, entity Do NOT use for: UI-only changes, deployment, or when schema is already defined.

Test quality validation through mutation testing, assessing test suite effectiveness by introducing code mutations and measuring kill rate. Use when evaluating test quality, identifying weak tests, or proving tests actually catch bugs.

Project N.E.K.O. 胶囊化 UI、品牌蓝视觉系统规范

为您的项目生成创意域名想法，并检查多个顶级域名（.com、.io、.dev、.ai 等）的可用性。节省数小时的头脑风暴和手动检查时间。

Reviews pull requests with code analysis and terminal smoke testing. Applies when examining code changes, running CLI tests, or when 'PR review', 'code review', 'terminal screenshot', 'visual test' is mentioned.

Establish performance baselines and detect regressions using flamegraph analysis. Use when optimizing performance-critical code, investigating performance issues, or before creating commits with performance-sensitive changes.

Workflow 1.5: a bridge between idea discovery and the auto-review loop. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPUs, and collects initial results. Use this when the user asks to implement experiments, to bridge a plan to execution (e.g., “deploy the plan” or “from plan to running experiments”), or already has an experiment plan ready to execute.

CRITICAL / MANDATORY. The ONLY acceptable workflow. Enforces strict Feature Branch -> Preview -> Merge protocol. You MUST follow this for every change.

Admin authentication and authorization system reference — login flow, JWT, TOTP, sessions, RBAC

Write clean, maintainable Go code following Clean Architecture, dependency injection, and ChecklistApplication patterns. Use when writing new Go code, refactoring, or implementing features.

Help users define AI product strategy. Use when someone is building an AI product, deciding where to apply AI in their product, planning an AI roadmap, evaluating build vs buy for AI capabilities, or figuring out how to integrate AI into existing products.