Loading...
Loading...
Found 9,262 Skills
Use the harem hierarchical code review system to output structured review conclusions based on the division of labor among the Empress, Four Consorts, and Nine Imperial Concubines
Generate cinematic film-style video prompts for Seedance 2.0 (Higgsfield). Use this skill when users want AI videos with cinematic, film-like, movie-quality, Hollywood-style, dramatic, or professional film-quality. Trigger words: cinematic, film-like, movie scene, dramatic lighting, depth of field, lens flare, anamorphic, letterbox, film noir, epic, stabilized camera, dolly shot, crane shot, or any cinematic video generation request. Use this skill even if users don't explicitly say "cinematic" but describe film aesthetics.
Use this skill first for ANY PixiJS v8 task; it routes to the right specialized skill for the job. Covers the full PixiJS surface: Application setup, the scene graph (Container, Sprite, Graphics, Text, Mesh, ParticleContainer, DOMContainer, GifSprite), rendering (WebGL/WebGPU/Canvas, render loop, custom shaders, filters, blend modes), assets, events, color, math, ticker, accessibility, performance, environments, migration from v7, and project scaffolding. Triggers on: pixi, pixi.js, pixijs, PixiJS, v8, Application, app.init, Sprite, Container, Graphics, Text, Mesh, ParticleContainer, DOMContainer, GifSprite, Assets, Ticker, renderer, WebGL, WebGPU, scene graph, filter, shader, blend mode, texture, BitmapText, create-pixi, how do I draw, how do I render, how do I animate in pixi.
This skill should be used when the user asks to start a new research project, import an existing code-plus-Markdown repository into Obsidian, or bind the current repository to a compact research knowledge base for future syncing.
Python software engineering guidelines from real PR review patterns. This skill should be used when writing, reviewing, or refactoring Python code — especially dataclasses, service interfaces, error handling, and type annotations. Triggers on tasks involving Python modules, API design, data modeling, type safety, exception handling, or refactoring for maintainability.
Bluedot platform help — bot-free AI note-taker with video recording, Chrome extension + desktop/mobile apps, Svix webhooks, screen recording with webcam overlay. Use when setting up Bluedot for a sales team, configuring Bluedot webhook integrations, syncing Bluedot meeting notes to HubSpot or Salesforce, troubleshooting Bluedot desktop app crashes or recording drops, choosing between Bluedot plans (Free/Basic/Pro/Business), comparing Bluedot vs Fathom or Fireflies for bot-free recording, or debugging Bluedot Chrome extension issues in managed IT environments. Do NOT use for comparing all note-takers (use /sales-note-taker) or reviewing a specific call for coaching (use /sales-call-review).
This skill must be used when initializing, maintaining, and executing by-harness workflows. It applies to scenarios where users mention by-harness, harness, initialization, continuous task decomposition, executing feat, plan/build/qa/fix, session_close, automatic resumption, runtime upgrade, or need to issue Java Gate, Distributed Java Gate, and three-tier frontend specifications to constrain model coding. This skill generates independent closed-loop scaffolding, sharded task storage, session closure tools, runtime upgrade tools, and issues Java hard rule gates, distributed Java coding contracts, three-tier frontend specifications, and BYAI HTML visual references; feature_list is only used as a legacy compatibility mirror.
Build, debug, or plan work with The Prompting Company through its API, MCP Server, CLI, or SDK entrypoints. Use when the user needs public routes, OpenAPI schema guidance, TypeScript SDK integration, CLI workflows, MCP setup, content APIs, app publishing APIs, public markdown access, simulations, visibility analytics, authentication, or API key scopes.
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval / pair classification), and `SparseEncoder` (SPLADE, sparse embedding model; for learned-sparse retrieval). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
让 agent zoom out，并给出更广的 context 或更高层 perspective。Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.
DeepEval evaluation workflow for AI agents and LLM applications. TRIGGER when the user wants to evaluate or improve an AI agent, tool-using workflow, multi-turn chatbot, RAG pipeline, or LLM app; add evals; generate datasets or goldens; use deepeval generate; use deepeval test run; add tracing or @observe; send results to Confident AI; monitor production; run online evals; inspect traces; or iterate on prompts, tools, retrieval, or agent behavior from eval failures. AI agents are the primary use case. Covers Python SDK, pytest eval suites, CLI generation, tracing, Confident AI reporting, and agent-driven improvement loops. DO NOT TRIGGER for unrelated generic pytest, non-AI test setup, or non-DeepEval observability work unless the user asks to compare or migrate to DeepEval.
Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl) and per-user profiles across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles". Adds the roast version when the user says "毒舌版", "roast 版", "再来个毒舌的", or similar.