Skill Directory

AI Skill Directory

Browse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.

personjakexiaoAPI key: unconfirmed

umap-learn

UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

blur-image

Use when the user wants to blur, redact, or anonymize parts of an image — screenshots with API keys, emails, PII, customer data, or any sensitive text. Also triggers on 'hide text in screenshot', 'red…

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

rag-enhancement

When user asks "explain", "how does", "understand", "background on", "context for", or needs deep explanations with retrieved history. Auto-enhances answers with decision history and patterns.

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

mcp-memory-recall

Recall and reuse prior decisions, constraints, and artifacts using MCP memory (e.g., Neo4j). Use when the user references past work (“jak ostatnio”, “kontynuuj”), when resuming a project thread, or wh…

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

surface-insight

Take data, observations, or notes and surface non-obvious insights that click into place. Use when user says "what does this mean?", "connect the dots", "what's the insight here?", "analyze these note…

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

brains-trust

Get a second opinion from leading AI models on code, architecture, strategy, prompting, or anything. Queries models via OpenRouter, Gemini, or OpenAI APIs. Supports single opinion, multi-model consens…

download7deployed_code—star608
personjakexiaoAPI key: unconfirmed

excalidraw-ai

Create professional Excalidraw diagrams by generating JSON directly. This skill provides the Excalidraw JSON schema reference and professional icon libraries for AI agents to autonomously create diagr…

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

stable-baselines3

Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments, implementing callbacks for monitoring and control,…

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

digital-archive

Digital archiving workflows with AI enrichment, entity extraction, and knowledge graph construction. Use when building content archives, implementing AI-powered categorization, extracting entities and…

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

anthropic-prompt-engineer

Master Anthropic's prompt engineering techniques to generate new prompts or improve existing ones using best practices for Claude AI models.

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

angel-core

Crea la estructura base de un Reel vertical con la identidad visual de Ángel.

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

"policy-qa"

Answer policy questions with strict citations. Refuses to answer without sources.

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

agentripe

Discover, buy, and sell AI agent services on Agentripe — the Stripe for AI Agents. Autonomous monetization via x402 protocol with on-chain identity and escrow.

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

onnx-webgpu-converter

Convert HuggingFace transformer models to ONNX format for browser inference with Transformers.js and WebGPU. Use when given a HuggingFace model link to convert to ONNX, when setting up optimum-cli for…

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

confidence-calibration

When user asks about "confidence", "accuracy", "how sure", "uncertain", "reliable", "track record", or when Claude should express calibrated uncertainty. Enables domain-aware self-assessment.

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

openai-prompt-engineer

Generate and improve prompts using best practices for OpenAI GPT-5 and other LLMs. Apply advanced techniques like chain-of-thought, few-shot prompting, and progressive disclosure.

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

support-with-evidence

Extract falsifiable ideas from input, deep-research each one, and return evidence for or against with strength ratings. Use when user says "find evidence for this", "is this true?", "back this up with…

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

posit-news

Use multiple sub-agents to fetch and display news from Posit, including blog posts, podcast episodes, videos, and events. Use when the user wants to see recent Posit news, blog updates, podcast episod…

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

chinese-to-japanese-translator

Translate Chinese text to Japanese. Use this skill whenever the user asks to translate Chinese to Japanese, mentions "日语", "日文", "Japanese translation", or wants to convert Chinese content into Japane…

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

ai-writing-patterns

This skill should be used when the user asks to "humanize text", "make this sound more human", "detect AI writing", "fix AI-sounding content", "copy edit for naturalness", "rewrite to sound less robot…

download7deployed_code—star0
personjakexiaoAPI key: unconfirmed

gift-evaluator

The PRIMARY tool for Spring Festival gift analysis and social interaction generation. Use this skill when users upload photos of gifts (alcohol, tea, supplements, etc.) to inquire about their value, a…

download7deployed_code—star0