Scan to join WeChat grouppersonjakexiaoNo key required
azure-speech-to-text-rest-py
Azure Speech to Text REST API for short audio (Python). Use for simple speech recognition of audio files up to 60 seconds without the Speech SDK.
download11deployed_code—star3
Skill Directory
AI Skill Directory
Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
personjakexiaoNo key required
langchain-architecture
Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM w...
download11deployed_code—star2
personjakexiaoNo key required
mental-health-analyzer
Analyze mental health data, identify psychological patterns, assess mental health status, and provide personalized mental health advice. Supports associative analysis with other health data such as sl…
download11deployed_code—star2
personjakexiaoNo key required
audio-cog
AI audio generation powered by CellCog. Text-to-speech, voice synthesis, voiceovers, podcast audio, narration, music generation, background music, sound design. Professional audio creation with AI.
download11deployed_code—star0
personjakexiaoNo key required
smart-model-switching
-
download11deployed_code—star0
personjakexiaoNo key required
ai-cost-check
Calculate AI feature costs and challenge if you actually need it. Invokes ai-cost-analyzer agent for detailed economics modeling.
download11deployed_code—star13
personjakexiaoNo key required
calibrate
Post-launch AI feature calibration workflow. Document error patterns, review eval performance, and decide on agency promotion. Based on CC/CD framework for continuous calibration of AI products.
download11deployed_code—star13
personjakexiaoNo key required
veo-prompt-director
Generates structured Google Veo 3.1 video prompts by collecting user input for subject, action, style, cinematography, and audio. Guides users through the Universal Prompt Formula to produce camera-re…
download11deployed_code—star7
personjakexiaoNo key required
crewai
Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (s...
download11deployed_code—star3
personjakexiaoNo key required
matplotlib
Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export …
download11deployed_code—star2
personjakexiaoNo key required
voice-ai-development
Expert in building voice AI applications - from real-time voice agents to voice-enabled apps. Covers OpenAI Realtime API, Vapi for voice agents, Deepgram for transcription, ElevenLabs for synthesis...
download11deployed_code—star2
personjakexiaoNo key required
deepread
AI-native OCR platform that turns documents into high-accuracy data in minutes. Using multi-model consensus, DeepRead achieves 95%+ accuracy and flags only uncertain fields for review—reducing manual …
download11deployed_code—star0
personjakexiaoNo key required
the-ultimate-guide-to-writing-effective-ai-prompts-65c2a3a3
write a simple prompt like “Write an email to [contact] welcoming them to the company,” but you can add more context with a persona in order to get a better result
download11deployed_code—star0
personjakexiaoNo key required
ai-health-check
Pre-launch health check that blocks you from shipping broken AI features. Grades 6 dimensions (model selection, data quality, cost, monitoring, failure UX, optimization).
download11deployed_code—star13
personjakexiaoNo key required
build-judge
Build an LLM-as-Judge evaluator for one specific failure mode. Binary pass/fail only. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness) and cannot be checke…
download11deployed_code—star13
personjakexiaoNo key required
ai-dev-workflow
The entire AI development process is threaded together by documentation. It covers Domain-Driven Design (DDD) and the setting of AI development standards (Agent norms). Use when (1) the user asks to o…
download11deployed_code—star0
personjakexiaoNo key required
gemini-api-integration
Use when integrating Google Gemini API into projects. Covers model selection, multimodal inputs, streaming, function calling, and production best practices.
download11deployed_code—star2
personjakexiaoNo key required
memory-systems
Design short-term, long-term, and graph-based memory architectures
download11deployed_code—star2
personjakexiaoNo key required
tiktok-automation
Automate TikTok tasks via Rube MCP (Composio): upload/publish videos, post photos, manage content, and view user profiles/stats. Always search tools first for current schemas.
download11deployed_code—star3
personjakexiaoNo key required
docs-cog
Deep reasoning. Accurate data. Beautiful design. The three things every great document needs — and most AI gets wrong. #1 on DeepResearch Bench (Feb 2026), powered by SOTA search models, and state-of-…
download11deployed_code—star0
personjakexiaoNo key required
llm-context
USE FOR RAG/LLM grounding. Returns pre-extracted web content (text, tables, code) optimized for LLMs. GET + POST. Adjust max_tokens/count based on complexity. Supports Goggles, local/POI. For AI answe…
download11deployed_code—star73
personjakexiaoNo key required
agency-ladder
Plan the v1→v2→v3 agency progression for AI features. Walk through mapping how autonomy increases over time, define promotion criteria, and generate artifacts for stakeholder alignment. Based on CC/CD…
download11deployed_code—star13
personjakexiaoNo key required
ai_quick_chat
Sends a short prompt to OpenRouter-compatible LLM for capability verification.
download11deployed_code—star0
personjakexiaoNo key required
td-task-management
Task management for AI agents across context windows. Use when agents need to track work, log progress, hand off state, and maintain context across sessions. Includes workflows for single-issue focus,…
download11deployed_code—star1