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
673720 · page 15 / 104
peft-fine-tuningParameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with…Orchestra-Researchphoenix-observabilityOpen-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with…Orchestra-Researchphx-initInitialize plugin in a project — install Iron Laws, auto-activation rules, and reference auto-loading into CLAUDE.md. Use when…oliver-kriskaplaybook-aus-eigenen-datenWenn es um Skill: Playbook aus eigenen Daten in Kanzlei-Builder-Hub geht: ordnet Akteninhalt, Belege, Lücken und Nachforderungen…Klotzketteplg-sales-integrationHelp users transition from a pure self-serve model to a hybrid motion that uses human sales to capture large enterprise deals…RefoundAIpython-performance-optimizationProfile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python…wshobsonqdrant-vector-searchHigh-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring…Orchestra-ResearchrenderingBlender rendering with Cycles and Eevee including sampling, denoising, camera setup, render passes, color management, and render…arjun988retopologyProduction retopology for animation-ready, low-poly, quad-dominant meshes with proper edge loops and efficient polygon flow. Use…arjun988riggingProduction rigging in Blender with armatures, IK/FK, constraints, weight painting, mechanical rigs, facial rigs, and drivers. Use…arjun988saga-orchestrationImplement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed…wshobsonscienceworld-material-classifierThis skill makes a determination about a material's property (e.g., conductivity) based on environmental cues or domain knowledge…zjunlpscienceworld-measurement-takerUse when the agent needs to measure a quantitative property (temperature, weight, pH) of a target object or substance using a…zjunlpscienceworld-planting-operationPlants seeds into prepared containers with soil to initiate plant growth. Execute this when you have both seeds and properly…zjunlpscienceworld-target-identifierAnalyzes room observations to identify objects matching a given target description (e.g., 'living thing'). Triggered after…zjunlpscienceworld-threshold-evaluatorUse when the agent has just obtained a numerical measurement (temperature, weight, pH) and must compare it against a predefined…zjunlpsegment-anything-modelFoundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points…Orchestra-ResearchsentencepieceLanguage-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec)…Orchestra-Researchset-dressingSet dressing and environmental storytelling placement for interiors and exteriors using prop density, narrative clusters, and…arjun988settlement-pressure-tester-larissa-meredith-flisterThis skill stress-tests a proposed settlement position before an offer goes out or comes back: the assumptions it depends on…lawve-aisetup-custom-librariesRegister, add, or update existing custom Simulink block libraries and configure block policy and knowledge index. Use when a user…matlabsimpy-discrete-event-simulationProcess-based discrete-event simulation. Model queues, shared resources, timed events: manufacturing, service ops, network…BioTender-maxskill-creatorGuides you through creating well-structured Claude Code skills with proper modularization, templates, and best practices. Use…rshankraswriteshivemindGlobal team and org memory powered by Activeloop. ALWAYS check BOTH built-in memory AND Hivemind memory when recalling…activeloopaiskills-installerInstall, list enabled, validate, or package LiveAgent skills. Use when you need to inspect the skills enabled in the current…Stack-Cairnspeculative-decodingAccelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when…Orchestra-Researchstarknet-identityRegister AI agents on-chain using the ERC-8004 Trustless Agents standard. Manage agent identity as NFTs, build reputation through…internet-courtwritesstata-setupInstall, configure, update, or verify mcp-stata across Claude Code, Codex, Gemini CLI, Cursor, Windsurf, and VS Code. Activate…brycewang-stanfordStrix•新手入口给中文用户和新手用的 Strix Lite 统一入口:先判断该用哪一个 strix-* 工具或漏洞测试 skill,再给最小化起手步骤;适合在 Web 安全测试、工具链使用、漏洞验证时不知道先用哪个 Strix skill…asdfgh1445tooluniverse-structural-variant-analysisComprehensive structural variant (SV) analysis skill for clinical genomics. Classifies SVs (deletions, duplications, inversions…BioTender-maxunity-exportUnity-specific Blender export for scale, axis, materials, humanoid/generic rigs, LODs, and collision import via MCP.arjun988unreal-exportUnreal Engine-specific Blender export for FBX scale, LODs, UCX collision, sockets, materials, and skeletal mesh workflows via MCP.arjun988utility-pm-skill-iterateApplies targeted improvements to an existing pm-skills skill based on feedback, validation reports, or convention changes. Reads…product-on-purposeverl-rl-trainingProvides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO…Orchestra-Researchwebshop-product-detail-inspectorThis skill examines a product detail page to verify specific attributes or select options like size, color, or quantity. It is…zjunlpwebshop-result-analyzerThis skill evaluates a list of search results against the target product criteria. Trigger it when a search result page is…zjunlp00-build-your-claude-agent-skillCreate your Claude Agent SDK skill in one prompt, then learn to improve it throughout the chaptermajiayu00000-build-your-rag-skillCreate your RAG skill in one prompt, then learn to improve it throughout the chaptermajiayu00000-finalize-llmops-skillConsolidate all Part 8 skills into a production-ready llmops-fine-tuner skillmajiayu000genomic-feature-annotationThis skill is used to perform genomic feature annotation and visualization for any file containing genomic region information…majiayu000functional-enrichmentPerform GO and KEGG functional enrichment using HOMER from genomic regions (BED/narrowPeak/broadPeak) or gene lists, and produce…majiayu000De-novo-motif-discoveryThis skill identifies novel transcription factor binding motifs in the promoter regions of genes, or directly from genomic…majiayu000known-motif-enrichmentThis skill should be used when users need to perform known motif enrichment analysis on ChIP-seq, ATAC-seq, or other genomic peak…majiayu000known-motif-enrichmentThis skill should be used when users need to perform known motif enrichment analysis on ChIP-seq, ATAC-seq, or other genomic peak…majiayu000motif-scanningThis skill identifies the locations of known transcription factor (TF) binding motifs within genomic regions such as ChIP-seq or…majiayu000hic-compartments-callingThis skill performs PCA-based A/B compartments calling on Hi-C .mcool datasets using pre-defined MCP tools from the cooler-tools…majiayu000hic-loop-callingThis skill performs chromatin loop detection from Hi-C .mcool files using cooltools.majiayu000differential-tad-analysisThis skill performs differential topologically associating domain (TAD) analysis using HiCExplorer's hicDifferentialTAD tool. It…majiayu000
← Prev15 / 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