Scan to join WeChat groupBrowse curated skills with source links, package snapshots, README assets and install signals in one calm, searchable catalog.
deepagents framework integration patterns for agent creation, planning, filesystem operations, and subagent orchestration. Current version 0.2.5 with LangGraph 1.0.2+
Atlas skill for Manus AI-inspired persistent planning. USE WHEN complex multi-step task, research project, extended implementation, OR need goal anchoring. Uses filesystem as memory with 3-file struct…
The unified AI agent for Polyprophet - combines deep analysis, precise execution, and atomic-level investigation. One agent, one skill, one mission.
Reforge neural dendrite patterns after catastrophic failure.
Plan LLM fine-tuning and evaluation experiments. Use when the user wants to design a new experiment, plan training runs, or create an experiment_summary.yaml file.
Design and optimize high-performance prompts based on Anthropic's Best Practices.
Create a structured summary of the article/transcript/report text, archive it in a thematic file (optional), and write it into U1's long-term memory (mem0-memory).
Build a rigorous world model with state, dynamics, uncertainty, and provenance. Use when creating digital twins, constructing system representations, building simulation foundations, or establishing b…
Molecular machine learning toolkit. Property prediction (ADMET, toxicity), GNNs (GCN, MPNN), MoleculeNet benchmarks, pretrained models, featurization, for drug discovery ML.
Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs.
Recommend who should do a task (Claude Code, Gemini, ChatGPT, Human, Taskmaster, MCPs) and generate handoff prompts.
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, dev…
Create new vision detector plugins following Bob The Skull's detector architecture. Use when adding new detectors like object detection, pose estimation, gesture recognition, or any computer vision de…
Create custom slash commands for popular AI agents (Claude Code, Codex, Gemini CLI). Use when user asks to create slash commands, custom commands, or reusable prompts for AI agent CLIs.
A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require effe…
Visualize FeedMob direct spend data as ASCII line charts. Use this skill when users request to view, display, chart, or visualize direct spend metrics for one or more click URL IDs. Trigger when users…
LLM-based deep iterative search and reasoning service. Proficient in handling complex problems, it automatically decomposes queries, conducts multi-round iterative retrieval, evaluates and verifies in…
Creates and manages multi-step AI workflows. Use when defining, implementing, or improving DeepWork jobs.
Run DEM lineament analysis to identify unmapped fault structures. Use when visually confirming orphan earthquake clusters, mapping fault extensions, or finding dark earthquake sources. Triggers on "DE…
Long-running design anthropologist that builds comprehensive visual databases from 500-1000 real-world examples, extracting color palettes, typography patterns, layout systems, and interaction design …
Audio loading patterns for R3F/Three.js. Use when adding sound effects.
Konsultant dietetyczny analizujący zakupy Pingo Doce. Używaj gdy użytkownik pyta o dietę, zdrowie, odżywianie, zakupy spożywcze, blind spots żywieniowe, lub chce porady dietetycznej. Automatycznie ana…
Build and maintain digital twins - virtual representations of physical systems that synchronize with real-world counterparts for monitoring, prediction, and optimization. Use when "digital twin, virtu…
DisCoPy categorical color streams via Hy with 3 parallel TAP streams