Agent skills

AI & Agents skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
4,965 found
4,0334,080 · page 85 / 104
metadata-version-present-passValidate a skill. Don't use for unrelated docs.luongnv89metadata-version-semver-failValidate a skill. Don't use for unrelated docs.luongnv89metadata-version-semver-passValidate a skill. Don't use for unrelated docs.luongnv89metallurgical-analysisSpecialized skill for metallic materials analysis and metallography including grain size measurement, phase quantification, and…a5c-aiwritesmetaphlan-profilerMetaPhlAn metagenomic profiling skill for species-level community compositiona5c-aiwritesmetaphor-automationAutomate Metaphor tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmetaverse-nft-model-releaseWenn es um Metaverse Nft Digital Fashion in fashion-law-moderecht geht: ordnet Sachverhalt, Norm, Beweislast, Gegenargumente und…Klotzkettemezmo-automationAutomate Mezmo tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmicro-experimentsUse when designing or auditing the evaluation of a MICRO paper — choosing the right instrument on the ladder from analytical…brycewang-stanfordmicrosoft-teams-automationAutomate Microsoft Teams tasks via Rube MCP (Composio): send messages, manage channels, create meetings, handle chats, and search…davepoonmicrosoft-teams-automationAutomate Microsoft Teams tasks via Rube MCP (Composio): send messages, manage channels, create meetings, handle chats, and search…sickn33microsoft-tenant-automationAutomate Microsoft Tenant tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmidjourney_prompt_generation根据用户提供的画面描述或关键词,生成包含详细描述段落和简化关键词列表的高质量Midjourney英文提示词,并附带标准参数。ECNU-ICALKmidjourney_stock_prompt_generatorGenerates MidJourney prompts optimized for stock photography sales using a specific structural formula, photorealistic…ECNU-ICALKmigrate-memoryMigrate legacy NanoClaw and Claude-native memory into the shared memory tree and provider-neutral standing instructions. Run…nanocoaimillers-lawApply Miller's Law — chunk information into groups of ~4 to work within working memory limits.Owl-ListenermindClaude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 filememvidminerstat-automationAutomate Minerstat tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmiro-automationAutomate Miro tasks via Rube MCP (Composio): boards, items, sticky notes, frames, sharing, connectors. Always search tools first…davepoonmiro-automationAutomate Miro tasks via Rube MCP (Composio): boards, items, sticky notes, frames, sharing, connectors. Always search tools first…sickn33missive-automationAutomate Missive tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQMistral AI AutomationAutomate Mistral AI operations -- manage files and libraries, upload documents for fine-tuning, batch processing, and OCR, track…ComposioHQmistral_ai-automationAutomate Mistral AI tasks via Rube MCP (Composio): completions, embeddings, fine-tuning, and model management. Always search…ComposioHQmitiq-error-mitigatorError mitigation skill using Mitiq for NISQ device noise reductiona5c-aiwritesmiturheber-mehrere-model-weights-nearshoreWenn es um Mehrere Entwickler und Miturheberschaft in Softwarerecht Deutschland/EU/International/USA geht: ordnet Sachverhalt…Klotzkettemixed-precision-trainerManage mixed precision trainer operations. Auto-activating skill for ML Training. Triggers on: mixed precision trainer, mixed…jeremylongshorewritesmixpanel-automationAutomate Mixpanel tasks via Rube MCP (Composio): events, segmentation, funnels, cohorts, user profiles, JQL queries. Always…davepoonmixpanel-automationAutomate Mixpanel tasks via Rube MCP (Composio): events, segmentation, funnels, cohorts, user profiles, JQL queries. Always…sickn33ml-engineerBuild production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature…sickn33ml-materials-predictorMachine learning skill for nanomaterial property prediction and discovery accelerationa5c-aiwritesmle-agent-guideIntelligent companion for ML engineering with arXiv integrationbrycewang-stanfordmlflow-tracking-setupConfigure mlflow tracking setup operations. Auto-activating skill for ML Training. Triggers on: mlflow tracking setup, mlflow…jeremylongshorewritesmlops-engineerBuild comprehensive ML pipelines, experiment tracking, and model registries with MLflow, Kubeflow, and modern MLOps tools.sickn33mne-eeg-toolUse this skill whenever any NeuroClaw modality skill (especially eeg-skill) needs to execute concrete MNE-Python operations for…BioTender-maxmnemosPersistent memory and learning-loop skills for AI coding agents using mnemos MCP tools. Use whenever mnemos_* MCP tools are…jeremylongshoremobicom-supplementaryUse when deciding what goes in the MobiCom 12-page double-column body versus references, optional appendices, and HotCRP fields —…brycewang-stanfordmobile-performanceApp startup, memory management, battery efficiency, network optimization, and profiling toolscosmicstack-labsmocean-automationAutomate Mocean tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmoco-automationAutomate Moco tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQmode-classificationUse before routing a /meta-agent request to choose single-agent-creator, team-builder, or agentlas-packager from the user's…agentlas-aiModel Attribution HeaderAlways begin responses with a specific attribution line identifying the model, provider, and version before addressing the main…ECNU-ICALKmodel-checker-interfaceInterface with multiple model checking tools for formal verificationa5c-aiwritesmodel-checkpoint-managerManage model checkpoint manager operations. Auto-activating skill for ML Training. Triggers on: model checkpoint manager, model…jeremylongshorewritesmodel-drift-detectorDetect model drift detector operations. Auto-activating skill for ML Deployment. Triggers on: model drift detector, model drift…jeremylongshorewritesmodel-evaluation-metricsBuild model evaluation metrics operations. Auto-activating skill for ML Training. Triggers on: model evaluation metrics, model…jeremylongshorewritesmodel-explainability-toolBuild model explainability tool operations. Auto-activating skill for ML Training. Triggers on: model explainability tool, model…jeremylongshorewritesmodel-export-helperAssist with model export helper operations. Auto-activating skill for ML Deployment. Triggers on: model export helper, model…jeremylongshorewritesmodel-pruning-helperAssist with model pruning helper operations. Auto-activating skill for ML Deployment. Triggers on: model pruning helper, model…jeremylongshorewrites
← Prev85 / 104Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going