18 skills found
kyegomez / OpenMythosA theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
majiayu000 / issue-size-estimationIssue粒度判定とコード行数見積もりの基準、サイズラベル、分割判定ロジックを定義
NeuralBlitz / infinite-recommender-systems-measurementThis skill enables measurement in the domain of recommender-systems (data-science). It represents intermediate-level expertise and is designed for production use in research, industry, and educational contexts.
Leonxlnx / taste-skillTaste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
hassan-alnator / vibe-eyesAutomated visual testing framework for Claude and MCP-compatible clients. Generate unit tests, run E2E browser automation, perform visual regression testing, and extract text with OCR - all through natural language commands.
kitlau86 / agent-vision-mcpAn MCP server that gives non-vision LLMs the ability to "see" images. Plug in any OpenAI-compatible vision API (Gemini, Qwen-VL, OpenAI, or self-hosted) and your text-only model — like DeepSeek in Claude Code — can analyze screenshots, OCR text, read charts, and more.
ProjectLiminality / DreamTalkA programmatic animation library extending the ancient modality of SandTalk into the digital domain
NeuralBlitz / data-mining-interpretation-fundamentalThis skill enables interpretation in the domain of data-mining (data-science). It represents fundamental-level expertise and is designed for production use in research, industry, and educational contexts. Use this skill when you need to perform interpretation operations related to data-mining.
htdt / godogenAutonomous game development for Godot, Bevy, and Babylon.js with Claude Code and Codex
Guilhem-Bonnet / godot-evidence-loopBoucle de preuve Godot via le serveur MCP Fennara : ancrer chaque claim sur des diagnostics éditeur, screenshots, contexte scène et logs runtime réels
GunaTeja777 / DesiSketch-Illustrations-AI-Hand-Drawn-Diagram-Generator-Agent-SkillTranslate judgments, workflows, system states, and metaphors in articles into clean, hand-drawn, absurd, and minimalist body illustrations Skill
sakamoto-family-smile / videodbSee, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips.
dioptx / mcp-atom-of-thoughtsMCP server for structured AI reasoning — decompose problems into atomic thoughts with dependency graphs, confidence tracking, and interactive D3.js visualization
NeuralBlitz / semi-supervised-optogenetics-testingThis skill enables testing in the domain of optogenetics (neuroscience). It represents intermediate-level expertise and is designed for production use in research, industry, and educational contexts. Use this skill when you need to perform testing operations related to optogenetics.
Huaizz-shawen / navigate-toOpenclaw + rosclaw + visual feedback
huang-sh / pytorch-fsdpAn open-source, model-agnostic AI workbench for scientific discovery.
S0ulFood / second-opinionAI design thinking framework with four roles (Strategist, Researcher, Executor, Critic) for Claude Code. Domain-agnostic.
sageox / ox-decisionThe hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines, and teammates.
