llm-ai
5
token-formatter
Convert verbose docs/markdown/text into token-efficient formats. Use when user wants to reduce token count, compress content for LLM context, or optimize for AI consumption.
georgekhananaev
data-ai
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
llm-ai
5
text-summarizer
Generate extractive summaries from long text documents. Control summary length, extract key sentences, and process multiple documents.
dkyazzentwatwa
data-ai
llm-ai
5
voice-transcribe
Transcribe audio files using OpenAI's gpt-4o-mini-transcribe model with vocabulary hints and text replacements. Requires uv (https://docs.astral.sh/uv/).
clawdbot
data-ai
llm-ai
5
named-entity-extractor
Extract named entities (people, organizations, locations, dates) from text using NLP. Use for document analysis, information extraction, or data enrichment.
dkyazzentwatwa
data-ai
llm-ai
5
video-transcript-analyzer
Analyze customer interview transcripts (SRT or plain text) to generate thematic breakdowns with summary, quotes, topics, timestamps, and full transcript. Use when given video transcripts or asked to create chapter markers.
jeffvincent
data-ai
llm-ai
5
language-detector
Detect language of text with confidence scores, support for 50+ languages, and batch text classification.
dkyazzentwatwa
data-ai
llm-ai
5
assemblyai-transcribe
Transcribe audio/video with AssemblyAI (local upload or URL), plus subtitles + paragraph/sentence exports.
clawdbot
data-ai
llm-ai
5
openrouter-transcribe
Transcribe audio files via OpenRouter using audio-capable models (Gemini, GPT-4o-audio, etc).
clawdbot
data-ai
llm-ai
5
whisper-transcription
Audio transcription using local whisper.cpp server with CUDA acceleration. HTTP API for speech-to-text conversion.
lawless-m
data-ai
llm-ai
5
compaction-advisor
Provides context-aware compaction guidance with intelligent checkpointing. Monitors context during long tasks and suggests checkpoints before compaction interrupts your work.
vignesh07
data-ai
llm-ai
5
mcp-connector
Provides a Model Context Protocol (MCP) server interface to the skills library, allowing any MCP-compliant agent (e.g. Claude Desktop) to invoke Antigravity skills as native tools.
Sounder25
data-ai
llm-ai
5
advanced-memory-skill-creator
Use when planning, scaffolding, validating, or packaging Claude skills inside Advanced Memory MCP.
sandraschi
data-ai
llm-ai
5
design-system-context
Managing design tokens and system context for LLM-driven UI development. Covers loading, persisting, and optimizing design decisions within context windows.
HermeticOrmus
data-ai
llm-ai
5
rag-implementation
ベクトルデータベースとセマンティック検索を使用してLLMアプリケーションのためのRetrieval-Augmented Generation（RAG）システムを構築します。知識に基づいたAI、ドキュメントQ&Aシステムの構築、またはLLMと外部ナレッジベースの統合時に使用します。
amurata
data-ai
llm-ai
5
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Keywords: 创建技能, 技能开发, 构建claude技能, 技能设计, 技能模板, create skill, build skill, develop skill, skill creation, skill development, skill template, skill design, skill builder, skill generator, 技能生成器, 技能构建器
kay-ou
data-ai
llm-ai
5
field-agent-documentation
Comprehensive template and guidelines for documenting Field Agents including technical specifications, system prompts, tool specifications, user interactions, and standardized documentation structure
treasure-data
data-ai
llm-ai
5
speak
One-way TTS mode - Claude speaks aloud while user types. Use when user says: 'speak', 'read aloud', 'vocal on', 'lis-moi', 'parle-moi', or wants Claude to vocalize responses without responding vocally themselves. For bidirectional voice conversation (user speaks too), use /conversation instead.
alamparelli
data-ai
llm-ai
5
create-edit-agent-skill
Official skill generator for VS Code Agent Skills; scaffolds new skills with correct directory structure and validation, and is the upstream dependency for authoring or modifying any other skill in this repository.
crossxwill
data-ai
llm-ai
5
prompt-engineering
Apply prompting techniques when creating prompts, agents, commands, system instructions, or SKILL.md files. Use for XML tags, multishot examples, chain-of-thought, response prefilling, and Claude 4-specific patterns.
tstapler
data-ai
llm-ai
5
clearing-output
Prioritize brevity, directness, and clarity in all responses with minimal token usage.
WarrenZhu050413
data-ai
llm-ai
5
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
ingpoc
data-ai
llm-ai
5
claude-sdk-debugging
Comprehensive guide for debugging Claude Agent SDK errors, TypedDict contracts, and internal SDK processing issues
WarrenZhu050413
data-ai
llm-ai
5
interview-writer
AI 采访式内容创作系统。不是人写，也不是 AI 自动写，而是 AI 分析后采访人再按人的风格写。通过问答不断沉淀用户画像（观点、写作风格、思考逻辑），持续迭代演进。支持博客、社交媒体、观点文章等场景。
ArcBlock
data-ai