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

multi-perspective-analysis

Analyze propositions from multiple expert perspectives. Dynamically generates 4-6 relevant expert roles, then performs validation, comprehensive analysis, or debate-style examination. Use when user wa…

download11deployed_code—star3
personjakexiaoAPI key: unconfirmed

ring:gandalf-webhook

Send tasks to Gandalf (AI team member) via webhook and get responses back. Publish to Alfarrábio, send Slack notifications, ask for business context, and more.

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

caffe-cifar-10

Guidance for building Caffe from source and training CIFAR-10 models. This skill applies when tasks involve compiling Caffe deep learning framework, configuring Makefile.config, preparing CIFAR-10 dat…

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

hf-model-inference

Guidance for setting up HuggingFace model inference services with Flask APIs. This skill applies when downloading HuggingFace models, creating inference endpoints, or building ML model serving APIs. U…

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

repomix-prompt-packet

Use when creating AI-optimized repository snapshots paired with sophisticated prompts for LLM consumption. Combines repomix configuration selection with prompt engineering to generate complete "prompt…

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

flow-capture

Capture streams of consciousness, tangential thoughts, and hyperfocus output. Extract signal from noise. Use when ideas are flowing faster than they can be organized, or when returning to raw notes/th…

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

Fine-Tuning Strategies

Adapt pre-trained foundation models to specific tasks/domains by continuing training on targeted data

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

natural-selection

Design systems that improve through variation, selection pressure, and inheritance of successful traits over generations

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

unbrowse-browser

Route website tasks through the Unbrowse-backed browser path instead of legacy pixel automation.

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

drawing-diagrams

Generate Mermaid diagrams from context and open them in mermaid.live in the browser. Use when the user asks for a diagram, visualization, flowchart, sequence diagram, ER diagram, or any visual represe…

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

bn-fit-modify

Guide for Bayesian Network tasks involving structure learning, parameter fitting, intervention, and sampling. This skill should be used when working with pgmpy or similar libraries to recover DAG stru…

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

model-extraction-relu-logits

Guidance for extracting weight matrices from black-box ReLU neural networks using only input-output queries. This skill applies when tasked with recovering internal parameters (weights, biases) of a n…

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

pattern-resonance

Surface patterns across data, notes, code, and thoughts. Reveal what is already sensed but not yet articulated. Use when feeling "something here" but unable to pinpoint it, or when reviewing accumulat…

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

Computational Mechanics

Identifies the minimal computational structure required to predict a system's behavior from limited observations

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

ml-batch-processing

Batch processing decouples prediction from real-time requests by pre-computing predictions on scheduled intervals

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

online-learning

Online learning updates models continuously as new data arrives, one sample at a time or in mini-batches, without retraining from scratch

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

readgzh

ReadGZH API Key (sk_live_...). Get one free at https://readgzh.site/dashboard. Without a key, the public endpoint is used (rate-limited).

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

chess-best-move

Guide for analyzing chess board images to find the best move(s). This skill should be used when tasks involve analyzing chess positions from images, detecting piece positions, identifying winning move…

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

extract-moves-from-video

This skill provides guidance for extracting text commands, moves, or typed input from video recordings using OCR. It applies when extracting gameplay commands (e.g., Zork), terminal sessions, or any t…

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

path-tracing

Guidance for implementing path tracers and ray tracers to reconstruct or generate images. This skill applies when tasks involve writing C/C++ ray tracing code, reconstructing images from reference ima…

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

idea-hoffman

Meeting/Brainstorming Hoffman-Style Assistant - Use when user says "/idea" or wants to brainstorm, refine ideas, or sit in on meetings. Implements Reid Hoffman's agent orchestration - parallel analysi…

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

Data Network Effects

Product becomes smarter and more valuable as it collects more usage data from users, leveraging machine learning to create indirect value

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

ml-streaming-inference

Streaming inference processes predictions on events as they arrive in real-time data streams with sub-second latency

download11deployed_code—star0
personjakexiaoAPI key: unconfirmed

streaming-inference

Process unbounded data streams with sub-100ms predictions when real-time ML inference is required

download11deployed_code—star0