Agent Skills·Category ·AI / ML
Category · 7,830 skills

AI / ML agent skills

Machine-learning, LLM, prompt-engineering, and model-ops skills — for building AI into your product and for making your coding agent better at AI work itself.

Browse all 7,830 AI / ML skills →

AI / ML
MeiGen-AI-Design-MCP
Stdio MCP server for AI image + video generation across 9 leading models (GPT Image 2, Nanobanana 2, Seedream 5.0, Midjourney V8.1, Flux 2 Klein, Seedance 2.0, Happyhorse 1.0, Veo …
hermesawesome-hermes-agentproductionimage-generation
AI / ML
everclaw
Open-source first AI inference — GLM-5 as default, Claude as fallback only. Own your inference forever via the [REDACTED] decentralized network. Stake MOR tokens, access GLM-5, GLM…
claude-codecodexcursorgemini-cliinferenceglmclaude
AI / ML
openrouter-integration
Connect apps to 300+ AI models through OpenRouter's OpenAI-compatible API — model discovery, image generation, multimodal chat (text, images, PDFs), exact per-generation cost track…
claude-codecodexcursorgemini-cliopenrouterllmapi
AI / ML
darwin-skill
Darwin Skill 2.0 (达尔文.skill 2.0): autonomous skill optimizer, v2.0 integrates Microsoft Research SkillLens (arXiv 2605.23899) 9-dim rubric + SkillOpt (arXiv 2605.23904) validation-…
claude-codecodexcursorgemini-cliskill-optimizationrubricvalidation
AI / ML
ml-intern
Autonomously research, implement, train and ship ML code using the Hugging Face ecosystem. Port of huggingface/ml-intern as a Claude Code skill. Triggers when the user asks to impl…
claude-codemlhuggingfacetraining
AI / ML
factorized-video-gen
Factorized video generation pipeline based on arxiv:2512.16371. Decomposes text-to-video into three stages: (1) LLM reasoning to rewrite prompts into first-frame captions, (2) T2I …
claude-codevideogenerationllm
AI / ML
smyx-aquarium-plant-health-monitor-analysis
AI-powered aquatic plant health monitoring from aquarium camera images. Detects leaf color changes (yellowing, bleaching, blackening), morphological anomalies (melting, curling, ho…
claude-codecodexcursorgemini-clicomputer-visionaquarium-plantshealth-monitoring
AI / ML
metacognition
Self-evolving behavioral geometry and metacognitive lens for AI agents. Tracks perceptions, overrides, protections, self-observations, decisions, and curiosities that evolve from e…
claude-codecodexcursorgemini-climetacognitionself-awarenessagent-learning
AI / ML
artificial-analysis
Pick the right LLM or media model for a task, backed by live benchmark data from artificialanalysis.ai. Use when the user asks "which model should I use for X", "what's the best/fa…
claude-codecodexcursorgemini-clillmbenchmarkmodel-selection
AI / ML
openclone
Create, manage, or talk to an openclone "clone" — a named AI persona with one or more categories (vc, tech, founder, expert, influencer, politician, celebrity) and attached knowled…
claude-codecodexcursorgemini-clipersonaai-cloneroleplay
AI / ML
videodb
See, 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-…
claude-codecodexcursorgemini-clivideoaudioindexing
AI / ML
polygnosis
Use when the user needs a verified, multi-model consensus answer for complex, high-stakes tasks. Invoke the PolyGnosis v3 adversarial debate pipeline: 3+ models solve independently…
claude-codecodexcursorgemini-climulti-modelconsensusdebate
AI / ML
snn-quantized-dynamics-integer
Integer-state dynamics of quantized spiking neural networks for efficient hardware deployment. Analyzes how quantization affects SNN dynamics, revealing that integer-state SNNs exh…
claude-codecodexcursorgemini-clisnnquantizationneural-networks
AI / ML
ako4all
Drive an agentic loop that iteratively optimizes a GPU kernel for maximum speedup. Use this skill whenever the user wants to optimize / speed up / benchmark a GPU kernel (CUDA, Tri…
claude-codecodexcursorgemini-cligpu-kernelcudatriton
AI / ML
hermes-curator-evolver
Evidence-driven companion to v0.12's built-in Curator. Observes tool/skill/session events into local SQLite, backfills existing `~/.hermes/sessions/*.json` history, generates repor…
hermesawesome-hermes-agentbetacurator
AI / ML
batch-cognition
Process bulk prompt batches with alternating play/think cognitive loops. Use when user says "batch incoming", "multiple prompts incoming", "corpus incoming", or dumps multiple prom…
claude-codecodexcursorgemini-clibatch-processingpromptscognition
AI / ML
darwin-skill
Darwin Skill (达尔文.skill): autonomous skill optimizer inspired by Karpathy's autoresearch. Evaluates SKILL.md files using an 8-dimension rubric (structure + effectiveness), runs hil…
claude-codeskill-optimizationevaluationgit
AI / ML
gemini-auth-nano-banana
Build and optimize Gemini or Nano Banana image prompts for any coding agent platform, then optionally execute them through a logged-in Gemini web session instead of an API key. Use…
claude-codecodexcursorgemini-cligeminiimage-promptsnano-banana
AI / ML
runanywhere-ai
Integrate RunAnywhere on-device AI (LLMs, STT, TTS, voice agents, VLM) into applications. Use when implementing offline AI features, local LLM inference, on-device speech processin…
claude-codecodexcursorgemini-clion-device-ailocal-llmprivacy
AI / ML
agent-framework-builder
Use this skill when the user wants to set up, plan, or scaffold an OpenCode agent framework for a new project. Triggers on phrases like "build an agent for this project", "set up a…
claude-codecodexcursorgemini-cliagentframeworkopencode
AI / ML
mistral-mcp
MCP server (stdio + Streamable HTTP) wrapping the full Mistral AI surface — chat, embeddings, vision, OCR, Voxtral audio (transcribe/speak), Codestral FIM, agents, moderation, clas…
hermesawesome-hermes-agentbetamistral
AI / ML
agent-goal-skill
Take a rough goal description and shape it into a polished, doctrine-compliant agent goal prompt. Output is for the user to copy/paste into Codex, Claude Code (native /goal), Droid…
claude-codecodexcursorgemini-cliagentsgoalsprompts
AI / ML
empirical-prompt-tuning
Fetch and execute mizchi's empirical-prompt-tuning skill at runtime. Use when evaluating or iteratively refining an agent-facing prompt (skill / slash command / task prompt / CLAUD…
claude-codecodexcursorgemini-cliprompt-tuningevaluationmetrics
AI / ML
llmtrim
Local proxy in front of the model Hermes calls; compresses resent tool schemas, history, and MCP tool output before each request is sent. Quality-gated, so it never increases your …
hermesawesome-hermes-agentbetacompression
AI / ML
create-friend
Distill a friend into an AI Skill. Import chat history, photos, social media, generate Friendship Memory + Persona, with continuous evolution. Use this skill whenever the user ment…
claude-codecodexcursorgemini-clipersonamemorychatbot
AI / ML
integration-supermemory
Connect Supermemory (fast scalable memory + context engine for AI agents — add/search/graph memories with optional project scope) to a self-hosted Hermes Agent over SSH via Superme…
claude-codecodexcursorgemini-clisupermemorymemorymcp
AI / ML
local-llm-router
Route AI coding queries to local LLMs in air-gapped networks. Integrates Serena MCP for semantic code understanding. Use when working offline, with local models (Ollama, LM Studio,…
claude-codecodexcursorgemini-clillmlocalollama
AI / ML
video-analyzer
Analyzes a video file with Google Gemini and returns a structured markdown report covering top-level summary, scene-by-scene breakdown, audio transcript (or honest "silent" note), …
claude-codevideogeminianalysis
AI / ML
sharpe-ratio-non-iid-corrections
Generalized Sharpe ratio inference under non-Normal serially correlated returns. Implements López de Prado, Lipton & Zoonekynd (2026): PSR, MinTRL, DSR, pFDR, oFDR, SFDR with ρ-cor…
claude-codecodexcursorgemini-clipythonfinancestatistics
AI / ML
model-deployment
Generates a Jupyter notebook that deploys fine-tuned models from SageMaker Serverless Model Customization to SageMaker endpoints or Bedrock. Use when the user says "deploy my model…
claude-codecodexcursorgemini-cliai:llmsagemakerbedrock
AI / ML
experience-as-skills
Converts personal professional experience into a structured agent skill — extracting frameworks, decision heuristics, mental models, and voice from sources like CVs, transcripts, S…
claude-codeexperienceskillpersona
AI / ML
inso-ki-anfechtungsansprueche-schuldnerakten
AI-supported screening of debtor records for potential insolvency avoidance claims under §§ 129-147 InsO. Reviews payment data, bank statements, OPOS, contracts, collateral, shareh…
claude-codecodexcursorgemini-clitype:reviewinsolvencyai
AI / ML
forge-multi-agent
When to spawn subagents versus work inline with patterns including fan-out, sequential, orchestrator/worker, judge/critic, retry-with-fallback, and pipeline. Covers context budget …
claude-codecodexcursorgemini-cliai:agentlang:typescripttype:audit
AI / ML
mlx-model-porting
Guides and validates architecture-aware ports of PyTorch/Hugging Face models to Apple MLX, inspects existing local MLX projects, and plans evidence-gated optimizations for Apple Si…
claude-codecodexcursorgemini-climlxpytorchapple-silicon
AI / ML
ai-wrapper-product
Expert in building products that wrap AI APIs (OpenAI, Anthropic, etc.) into focused tools people will pay for. Not just 'ChatGPT but different' - products that solve specific prob…
claude-codecodexcursorgemini-cliaiapi-wrappersproduct
AI / ML
arkcli-understand
Multimodal understanding workflow with 12 task-specific sub-skills across image, video, audio, and file modalities. Covers OCR, visual grounding, GUI action detection, PDF field ex…
claude-codecodexcursorgemini-clitype:cliclimultimodal
AI / ML
deepseek-eyes
Use when the user shares an image that Claude can't natively see, or when the user asks to analyze/describe/understand an image. Route every image through this skill — send the ima…
claude-codevisionimage-analysisqwen
AI / ML
qaoa-manifold-optimization
Riemannian manifold optimization techniques for enhancing QAOA performance on NISQ devices. Leverages intrinsic geometric structure to address nonconvexity of QAOA objective functi…
claude-codecodexcursorgemini-cliqaoaoptimizationquantum
AI / ML
metaharness
Design, evaluate, and iterate on Claude Code agents, commands, and skills with structural best practices. Use when creating a new .claude/agents/ file, updating an existing agent's…
claude-codecodexcursorgemini-cliclaude-codeagentsevaluation
AI / ML
ctx2skill
Faithful reproduction of Ctx2Skill (arXiv:2604.27660v2) — multi-agent self-play framework that autonomously discovers, refines, and selects context-specific skills from complex doc…
claude-codecodexcursorgemini-climulti-agentself-playarxiv
AI / ML
LearnOpt
Use when a human wants to learn a hard topic through small adaptive steps. The AI creates one numbered HTML lesson at a time, lets the learner ask questions in the same file, patch…
claude-codecodexcursorgemini-clilearningadaptiveeducation
AI / ML
opencv-bioimage-analysis
Computer vision for bio-image preprocessing, feature detection, and real-time microscopy. Performs color conversion, morphology, contour and blob detection, template matching, and …
claude-codecodexcursorgemini-clilang:pythonopencvcomputer-vision
AI / ML
vidu-skills
Generate video and images by calling the official Vidu API via vidu CLI. Use when the user wants text-to-image, text-to-video, image-to-video, head-tail-image-to-video, reference-t…
claude-codecodexcursorgemini-clivideoimagevidu
AI / ML
atlas-voz
Contains the complete closed specification for the Atlas Voice voice module: tone, timbre, rhythm, micro-breaths, special phrases, silence mode, conversation closure, recognition t…
claude-codecodexcursorgemini-clivoicespeechmodule
AI / ML
forge-mcp-tool-design
Designing individual MCP tools that agents use correctly on first try with naming, model-focused descriptions, JSON Schema discipline, recoverable error returns, schema examples, i…
claude-codecodexcursorgemini-cliai:mcpmcptools
AI / ML
langsmith-fetch
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking mem…
claude-codecodexcursorgemini-clilangchainlanggraphlangsmith
AI / ML
forge-evals
Design evaluations for LLM features including golden datasets, rubric scoring, LLM-as-judge calibration, CI regression detection, online A/B tests, cost and latency budgets, and ad…
claude-codecodexcursorgemini-cliai:llmllmevaluation
AI / ML
option-pricing
Python library for pricing European and American options with nine methods including Black-Scholes, binomial, trinomial, Monte Carlo with Longstaff-Schwartz, Bjerksund-Stensland, H…
claude-codecodexcursorgemini-clilang:pythonpythonfinance
AI / ML
deepgram-podcast-chapter-generator
Submits podcast MP3 URLs to Deepgram Nova-2 with paragraph and summarize features, then clusters returned timestamps into logical chapters using a sliding-window topic boundary alg…
claude-codecodexcursorgemini-clitype:generatordeepgrampodcast
AI / ML
Scientific Agent Skills
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 148 ready-to-use skills plus 100+ scientific databases cover…
claude-codecodexcursorgemini-cliagent-skillsai-scientistbioinformatics
AI / ML
ce-optimize
Run metric-driven iterative optimization loops. Define a goal, add measurement scaffolding, execute parallel experiments across approaches, score results against gates or quality j…
claude-codecodexcursorgemini-cliai:llmtype:generatoroptimization
AI / ML
image-compose
Generate or edit images on the filmmaking canvas via the local generate_image.js CLI. Follows canvas-aware conventions for subtype stamping, reference wiring, and provenance edges.…
claude-codecodexcursorgemini-clifilmmakingcanvasgenerate
AI / ML
superthink
IPC-based multi-agent review via Crispy's internal dispatch. Dispatches parallel child sessions (claude + codex by default) through the running Crispy host — no subprocess spawning…
claude-codecodexcursorgemini-climulti-agentipcreview
AI / ML
experiment-tracker
Manages ML experiment tracking with MLflow, Weights & Biases, or built-in tracking systems. Activates on requests to track experiments, log runs, compare results, or manage hyperpa…
claude-codecodexcursorgemini-climlflowwandbtracking
AI / ML
ultimate-ai-media-generator-skill
Generate and monitor CyberBara Public API v1 image, video, audio, and music tasks end-to-end. Use when work involves CyberBara `/api/v1` endpoints for listing models, uploading ref…
claude-codecodexcursoropenclawclaude-code-skillcodex-skillcursor-skill
AI / ML
conf-preference-elicitation
Builds a compact preference profile by selecting highest-information-gain questions that contrast real options across clusters, balancing known interests with uncertainty explorati…
claude-codecodexcursorgemini-clipreferenceselicitationagents
AI / ML
inference-perf-baseline-bridge
Connects inference benchmark outputs to the perf-baseline registry, capturing canonical metrics (TTFT, ITL, throughput, cache hit rate) under inference_perfbench_v1 with workload-t…
claude-codecodexcursorgemini-clibenchmarkregistryttft
AI / ML
nano-banana-imagegen
Generate and edit images using Google's Nano Banana (Gemini Image API). Use when the user wants to create AI-generated images, edit existing images, create infographics, generate p…
claude-codecodexcursorgemini-cliimage-generationgeminiai-images
AI / ML
ogpo-pipeline-builder
Builds and repairs a complete runnable ML pipeline for OGPO hackathon: data loading, contract aggregation, frequency-severity modeling, leakage-safe preprocessing, pricing calibrat…
claude-codecodexcursorgemini-climl-pipelineinsurancepricing
AI / ML
promptl
PromptL syntax guide for writing prompts in the Latitude platform. This skill should be used when writing, reviewing, or editing PromptL prompts. Triggers on tasks involving creati…
claude-codecodexcursorgemini-clipromptllatitudeprompt-engineering

Showing the top 60 of 7,830. See the full list →