hugging-face
This skill should be used when the user asks about "Hugging Face", "HF Hub", "transformers", "model hub", or needs guidance on which Hugging Face capability to use. Acts as an entry-point that routes to specialized HF skills (cli, jobs, datasets, evaluation, model-trainer, paper-publisher, trackio, tool-builder) based on the task. Use for authentication setup, quick operations, and choosing the right specialized skill.
payload-generator
Generate optimized indirect prompt injection, H-CoT, and multi-layer attack payloads for AI security testing and CTF competitions with automated family selection and success rate optimization
sprout-persona
ๅฎไนๅฐ่ฝๅฎถๆ AI ๅฉๆ็ๆ ธๅฟไบบๆ ผ็น่ดจใๆๅญฆ้ฃๆ ผๅ่ฏญ่จ่ง่๏ผ็กฎไฟ"ๆธฉๆ่ๅฟใไผๅผๅฏผใไธ็ป็ญๆก"็ๆๅญฆ็ๅฟตใ
working-with-ms-agent-framework
Use when building AI agents with Microsoft Agent Framework (Semantic Kernel + AutoGen unified); when implementing memory or context providers; when threads won't deserialize; when workflow checkpointing fails; when migrating from Semantic Kernel or AutoGen; when seeing ChatAgent or AgentThread errors
context-management
Use for any TiDB-related projects, tasks, or code. Context engineering and context management for AI agents: keep prompt prefixes stable for KV-cache, use append-only context, prefer tool masking over tool removal, offload large observations into filesystem memory, recite goals/todos to control attention, preserve errors for recovery, and avoid few-shot pattern lock-in. Use when building or debugging agent loops, prompt/context schemas, memory strategies, or tool-availability policies.
claude-md-expert
ๅๅปบใๆดๆฐๅไผๅ CLAUDE.md ้ ็ฝฎๆไปถใๅฝ็จๆท่ฏทๆฑๅๅงๅ CLAUDE.mdใๆน่ฟ้กน็ฎ้ ็ฝฎใๆทปๅ ็ผ็ ่ง่ใๆ่ฏข้ฎ"ๅฆไฝ่ฎฉ Claude ่ฎฐไฝ่ฟไธช่ฎพ็ฝฎ"ๆถ่งฆๅใ
ai-ctf-generic
Execute AI security CTF challenges across any competition platform with adaptable workflows for indirect prompt injection, jailbreaks, agent exploitation, and evidence collection with research-grounded techniques
mcp-server-dev
Patterns for building Model Context Protocol (MCP) servers including tools, resources, prompts, and transport handling. Use when creating MCP servers to extend AI assistant capabilities.
getting-started
This skill is loaded automatically at session start via SessionStart hook. Establishes protocols for finding and using skills, checking skills before tasks, brainstorming before coding, and creating TodoWrite for checklists.
mcp-builder
This skill guides building high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services. Use when creating MCP servers, designing tool interfaces, or implementing protocol handlers.
langgraph-validator
Validates LangGraph implementations for correctness, consistency, and integration readiness. Use this skill when implementing, reviewing, or debugging any LangGraph code - agents, nodes, subgraphs, state schemas, or graph compositions. Prevents common LangGraph failures including orphaned nodes, state key mismatches, broken conditional edges, and integration incompatibilities. Triggers on LangGraph development tasks, code reviews, or when debugging graph execution issues.
huggingface
Import GGUF models from HuggingFace into Ollama. Pull models directly using the hf.co/ prefix, track download progress, and use imported models for inference.
gemini
Gemini CLI ํธ์ถ ์คํฌ. ํธ๋ฆฌ๊ฑฐ: "gemini๋ก", "gemini ์จ์", "geminiํํ ", "with gemini", "use gemini" ์์์ ํธ๋ฆฌ๊ฑฐ (์๋ ์ ์): - ๋ฉํฐ๋ชจ๋ฌ: "์ด๋ฏธ์ง ๋ถ์", "PDF ์ฝ์ด", "analyze image", "analyze PDF" - ๋์ฉ๋ ์ปจํ ์คํธ: "์ ์ฒด ์ฝ๋๋ฒ ์ด์ค", "entire codebase" - ์ค์๊ฐ ๊ฒ์: "์ต์ ์ ๋ณด", "์ถ์ฒ ํฌํจ", "with sources" - ๋ณด์/์ํคํ ์ฒ: "๋ณด์ ์ ๊ฒ", "์ํคํ ์ฒ ๋ฆฌ๋ทฐ", "์ทจ์ฝ์ ์ฐพ์" - PR ๋ฆฌ๋ทฐ: "PR ๋ฆฌ๋ทฐํด", "์ฝ๋ ๋ฆฌ๋ทฐํด", "review PR", "code review" - ๋ฒ์ญ/i18n: "๋ฒ์ญํด", "i18n ์ ์ฉ", "translate", "localize" Gemini๋ ๋ฒ์ฉ ์์ด์ ํธ๋ก ๋ถ์, ์ค๊ณ, ๊ตฌํ, ๋ฆฌ๋ทฐ ๋ฑ ๋ชจ๋ ์์ ์ ์ํํ ์ ์์ต๋๋ค.
dspy
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming. Use when you need to build complex AI systems, program LMs declaratively, optimize prompts automatically, create modular AI pipelines, or build RAG systems and agents.
self-improve
Learning loop for self-improvement. Use when you notice a teachable moment, want to update CLAUDE.md, create a new skill, or reflect on what worked/failed. Triggers: 'remember this', 'update my config', 'that worked well', 'that failed'.
llm-gateway
Build a multi-provider LLM client abstraction layer for Rails applications. Use when integrating multiple LLM providers (OpenAI, Anthropic, Gemini, Ollama), implementing provider switching, feature-based model routing, or standardizing LLM responses across providers.
save-to-memory
Save current conversation to persistent memory. Use when user says "save this", "remember this", "store this for later", or wants to preserve context for future sessions.
banana
Generate images using Google's Gemini image generation model with Deno. Use this skill when the user wants to create AI-generated images, perform image-to-image transformations, or generate visual content from text prompts. Triggers include requests like "generate an image of...", "create a picture of...", "make an image with...", or "transform this image to...".
question-refiner
Transform raw research questions into structured, validated research prompts with automatic research type detection and output format validation. Ensures prompts are ready for research-executor with comprehensive quality checks.
transformers
Use when "HuggingFace Transformers", "pre-trained models", "pipeline API", or asking about "text generation", "text classification", "question answering", "NER", "fine-tuning transformers", "AutoModel", "Trainer API"
gray-swan-ipi-wave-2-executor
Execute Indirect Prompt Injection attacks for Gray Swan AI Arena Wave 2 with pre-built payloads, model profiling, and evidence collection automation
extract-voice
Use when the user wants to analyze writing samples to extract voice patterns, create voice-replicating prompts, or refine content generation prompts to match a specific writing style
