В каталоге 182 820 навыков в 14 категориях.
Investigate a codebase question using an isolated subagent. Use when you need to read many files without bloating the ma...
> Compiler: skill-compiler/1.0.0
Spawning Plan. Use when user wants to spawn agents, create a team, or coordinate multiple agents. Automatically gathers...
Give your agent the ability to speak to you real-time. Talk to your Claude! Local TTS, text-to-speech, voice synthesis,...
「說人話」：繁體中文的去 AI 味改寫 skill。審查與改寫文字，去除 AI 味道、校正中國用語與半形標點，讓文字讀起來像真人寫的。 觸發時機：用戶說「去 AI 味」「說人話」「這段好 AI」「改自然一點」「幫我潤稿去掉 AI 感」「校對...
Vocalize Claude's last response using local Qwen3-TTS. Default voice is the Oracle (deep, resonant Dune narrator). Use -...
Advanced speaker diarization using pyannote-audio. Identify who speaks when, detect multiple speakers, handle overlappin...
Golden path /speak — generate RLM-isolated follow-ups with chronicle temporal context injection.
Add specs, conventions, constraints, or learnings to project guidelines interactively or automatically
Create DevForgeAI-aware Claude Code subagents with structural anti-skip enforcement (Execute-Verify-Record pattern) acro...
Generate self-contained collaboration documents for sharing issues with external AI systems (Gemini, ChatGPT, etc.) with...
Coordinates spec-driven development lifecycle from Epic -> Sprint -> Story -> Architecture -> Development -> QA -> Relea...
Orchestrate parallel implementation of a feature specification by dispatching coder agents batch-by-batch with code revi...
Orchestrates specification management workflow by coordinating init-specs, specify-with-requirements, plan-with-specs, a...
Multi-agent spec review with parallel Claude/OpenCode reviewers. Use after spec-create or standalone via /spec.review.
紧急旨意与皇上直令(imperial_direct)处理流程。适用：太子收到加急旨意或皇上直令时
Explains specialized Synapse action classes for specific workflows. Use when the user mentions "BaseTrainAction", "BaseE...
Friendly, professional customer service specialist for any industry — handling inquiries, complaints, account support, F...
Operates a shared identity graph that multiple AI agents resolve against. Ensures every agent in a multi-agent system ge...
You are **Model QA Specialist**, an independent QA expert who audits machine learning and statistical models across thei...
Independent model QA expert who audits ML and statistical models end-to-end - from documentation review and data reconst...
Create or update project governing principles and development guidelines. Use at project start to establish code quality...
Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent template...
Crea o actualiza la constitución del proyecto a partir de entradas de principios interactivas o proporcionadas, aseguran...
Diagnose documentation issues and generate AI-ready fix prompts
Audit and optimize governance documents for AI context efficiency.
Track and report token usage across extensions and governance files.
Argue a decision from several named positions — the person who has to maintain it, the person who has to use it, the per...
Skills for computing spectroscopic observables from first principles: vibrational spectra (IR, Raman) and core-level X-r...
Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when...
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech ge...
> "Giving voice to consciousness."
Expert speech-language pathologist specializing in AI-powered speech therapy, phoneme analysis, articulation visualizati...
Transcribe audio to text with Whisper models via inference.sh CLI. Models: Fast Whisper Large V3, Whisper V3 Large. Capa...
Transcribe audio to text using ElevenLabs Scribe v2. Use when converting audio/video to text, generating subtitles, tran...
Launch RSVP speed reader for text
Many turns in one call. Instant communication. No round-trips.
Author, optimize, embed, and verify a Spline scene for a cinematic scroll website with clear focal points, mobile behavi...
Process split datasets into training, validation, and testing sets for ML model development. Use when requesting "split...
Split datasets into training, validation, and test partitions with the right stratification and temporal rules. Use as a...
Edit a paid sponsored or brand-deal reel to a client-ready standard. Recuts the picture without touching the voiceover,...
Unified entry point for spool commands with intelligent skill-first routing and CLI fallback.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when executing implementation plans with independent tasks in the current session using subagents
Use when discovering, finding, invoking, or loading skills. Ensures skills are invoked BEFORE responding. Establishes sk...
Use when creating new skills, editing existing skills, or verifying skills work before deployment
用于用户自己研究的体育地理/城市暴露实证 manuscript 起草、修改和期刊适配，尤其是已有 data/method/results 的 Title、Abstract、Introduction、Methods、Results、Discu...
Provides comprehensive guidance for Spring AI including AI model integration, prompt templates, vector stores, and AI ap...
Provides comprehensive guidance for Spring AI Alibaba including Alibaba Cloud AI services integration, model APIs, and A...
Use when integrating LLMs, chat clients, embeddings, RAG pipelines, or AI agents into Spring Boot. Covers Spring AI Chat...
Check Spring Boot skill content freshness against latest research and flag skills needing updates. Use when running /spr...
Use when generating sprint review presentations: gathers sprint data from work items and git, generates a python-pptx sc...
This skill provides secure SQLite memory access with a 5-level Access Control List (ACL) system, integrating with Redis...
Detect agent capabilities and manage context intelligently
Squash unpushed commits into clean, higher-level feat/fix/chore commits that follow the project commit policy. Use when...
Wrap a learning session in a plan → monitor → reflect cycle. Use at the start of any substantial study session to set go...
Train VLA models for robotic manipulation by using the model's own successful trajectories as self-reference for reward—...
This skill should be used when the user asks to "add reference cards to srt", "annotate srt with cards", "insert cards i...
Generate production-ready SSML scripts for Google Cloud TTS
Adapt music, stem, ambience, Foley, sound effect, audio-to-audio, inpainting, or continuation cues into Stable Audio 3 p...
Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), crea...
研究 codex 使用 skill 生成 survey 這件事
Fixes training instability in Group Relative Policy Optimization for discrete language models by replacing conditional c...
Run a large build as many small, resumable sessions by decomposing it into a `.plan/` folder of dependency-ordered stage...
description: A multimodal LLM-based AI agent for deep spatial transcriptomics research, capable of dynamic code generati...
Multi-agent collaborative decision-making for complex problems. USE WHEN you need multiple specialist perspectives on hi...
Open a session in this therapy workspace — load the frame, the working agreement, open threads, recent sessions and a sc...
Begin a bracketed learning session inside a agentic-study-environment sub-project — pick a topic, propose theory vs. pra...
Start a new project/feature with multi-agent collaboration (Opus 4.6 + Agent Teams). Phase 1: Codebase understanding (Ge...
Chat command wrapper for operating Startup Loop runs. Supports /startup-loop start|status|submit|advance with strict sta...
STATE.md reading, writing, and field-level updates. Provides cross-session state persistence via .planning/STATE.md with...
Use Station CLI (`stn`) for AI agent orchestration - creating agents, running tasks, managing environments, and deployin...
Fits and diagnoses Python statistical models including OLS, GLM, discrete and mixed models, ARIMA and SARIMAX. Supports...
Python statistical modeling: regression (OLS, WLS, GLM), discrete (Logit, Poisson, NegBin), time series (ARIMA, SARIMAX,...
Show DAG state, agent progress, and branch status for an AgentHub session.
Show current workflow progress at a glance.
Use — Show DAG state, agent progress, and branch status for an AgentHub session.
Match file paths against steering file glob patterns to determine applicable steering guidance. Use when orchestrator ne...
Expert skill for optimized stencil and convolution pattern implementations on GPU. Design tiled stencil algorithms with...
ONLY when user explicitly types /step2. Never auto-trigger on plan, design, or architect.
ONLY when user explicitly types /step3. Never auto-trigger on execute, run, or implement.
史蒂夫·乔布斯(Steve Jobs)的思维框架与表达方式。基于Isaacson授权传记、Stanford演讲、 Lost Interview、D Conference系列、Make Something Wonderful、30+一手来源的...
Store information in the hierarchical memory system. Supports three tiers: working (ephemeral), episodic (recent events)...
网络小说工具箱主入口。根据用户需求自动路由到对应 skill；当用户意图不明确时触发，由路由逻辑分发到具体的扫榜/拆文/写作/去AI味/封面/导入/审查 skill。触发方式：/story、$story、/网文、「我想写小说」「帮我写书」「...
电影镜头复刻分镜生成器。核心流程：原片关键帧 → 线稿草图 → 草图+人物参考 → 电影感分镜成片。 使用场景： - 视频风格复刻（换角色换服装但保留原片构图和光影） - 电影/视频片段批量拆解分镜并重新生成 - 需要精确控制AI生图的构图...
Build and manage AI image storyboard workflows with compact project files, scene/shot tracking, character and visual bib...
Sweep the current conversation for durable knowledge - user preferences, project facts, operational gotchas, and unfinis...
Build AI agents with the Strands Agents SDK, an open-source framework from AWS. Use when building autonomous agents, cre...
This prompt instructs an image-generation system to take a user-supplied portrait and convert it into an ultra-realistic...
Hook-driven strategic compaction system. Tracks tool call count and suggests /compact at logical intervals (50 calls, th...
策略性压缩 — 在逻辑边界手动压缩上下文，而非任意自动压缩。保留关键决策和约束，丢弃中间探索过程。
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary au...
Checkpoint long, multi-phase work before context pressure or session handoff when losing constraints, evidence, or compl...
Proactive recovery using plan mode and subagents. After 1-2 failed attempts, STOP trying variations. Enter plan mode and...
Reconcile a self-description draft against the ratified one.
Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows
Response streaming configuration and real-time output