Agent skills

Other 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
21,420 found
4,2734,320 · page 90 / 447
QE Learning OptimizationTransfer learning, metrics optimization, and continuous improvement for AI-powered QE agents.majiayu000qiskitIBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads…majiayu000qiskitQiskit is the world's most popular open-source quantum computing framework with 13M+ downloads. Build quantum circuits, optimize…majiayu000qiskitIBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads…majiayu000qiskitIBM quantum computing framework. Use when targeting IBM Quantum hardware, working with Qiskit Runtime for production workloads…majiayu000qiskitQiskit is the world's most popular open-source quantum computing framework with 13M+ downloads. Build quantum circuits, optimize…majiayu000qraExtract Question-Reasoning-Answer pairs from text. Use --context for domain-focused extraction. Validates answers are grounded in…majiayu000writesqt-cmake-project-generatorGenerate CMake-based Qt project with proper module dependencies, cross-compilation support, and modern Qt6 configurationa5c-aiwritesQuantConnect ValidationQuantConnect walk-forward validation and Phase 5 robustness testing (project)majiayu000quantitative-managementUse when establishing measurement programs, analyzing metrics with statistical process control, setting baselines, or…majiayu000quantum-expertExpert-level quantum computing, Qiskit, quantum algorithms, and quantum informationmajiayu000writesquantum-guitarCoecke's Quantum Guitar: quantising guitar strings via qubit association, ZX-calculus notation, Moth Actias synth integrationmajiayu000query-graphGraphDB探索エージェント - RyuGraphデータベースを自然言語またはCypherで探索し、関連するコードや仕様書を返却。/query-graph [クエリ] で呼び出し。majiayu000question-resolverSystematically resolve questions - determine if answerable, gather evidencemajiayu000Questions Are Not InstructionsEnsures questions are answered literally before taking action. Triggers on user input containing '?' or patterns like 'why did…majiayu000quickLightweight analysis for straightforward decisions. Compresses research, evaluate, critique, and synthesize into a single pass…majiayu000quota-healthUse to analyze quota distribution, attainment fairness, and productivity signals.majiayu000qutipQuantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence…majiayu000qutipQuantum mechanics simulations and analysis using QuTiP (Quantum Toolbox in Python). Use when working with quantum systems…majiayu000QutipQuantum mechanics simulations and analysis using QuTiP (Quantum Toolbox in Python).majiayu000qutipQuantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence…majiayu000qutipQuantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence…majiayu000qwen-delegationDelegates tasks to Qwen CLI via delegation-core for Alibaba's models. Use when delegation-core selects Qwen or large-context…majiayu000qwen-image-2-proGenerate images with Alibaba Qwen-Image-2.0-Pro via inference.sh CLI. Professional text rendering, fine-grained realism, enhanced…majiayu000qwen_wsp_enhancementEnhance WSP protocols using Qwen strategic analysis and 0102 supervision. Use when enhancing WSPs, analyzing protocol gaps…majiayu000r-analystR statistical analysis for publication-ready sociology research. Guides you through phased workflows for DiD, IV, matching, panel…majiayu000r-econometricsRun IV, DiD, and RDD analyses in R with proper diagnosticsbrycewang-stanfordrahanpesun-estaminenRahanpesun ja terrorismin rahoittamisen estäminen Suomessa (laki 444/2017). Käytä tätä skilliä, kun organisaatio arvioi, onko se…akunikkolaralph-autonomous-devEnables autonomous development loops that run until all tasks pass. Use when the user says "until done", "keep going", "finish…majiayu000ralph-buildRun Ralph autonomous build loop. Use when user asks to "ralph build", "run build loop", or needs to process subtasks…majiayu000ralphRun RALPH autonomous development loop. Converts PRD markdown to prd.json and runs autonomous implementation.majiayu000writesralphRun RALPH autonomous development loop. Converts PRD markdown to prd.json and runs autonomous implementation.majiayu000writesralph-executionExecute Ralph loops. Use when: Running the autonomous loop, managing tasks, or handling backpressure. Not for: Designing new…majiayu000ralph-github-start-loopRuns autonomous loop fetching stories from GitHub Issues. Implements and closes issues as done. Triggers on "loop through my…majiayu000ralphConvert an ML PRD into prd.json for ML-Ralph. Use when you have an ML PRD and need prd.json. Triggers on: convert this prd, turn…majiayu000ralph-json-start-loopRuns the Ralph autonomous loop. Executes stories from prds/*.json using git worktrees.majiayu000setup-ralphSetup the Ralph autonomous AI coding loop - ships features while you sleepmajiayu000ralphQueue processing with fresh context per phase. Processes N tasks from the queue, spawning isolated subagents to prevent context…majiayu000writesralphAutonomous feature development - setup and execution. Triggers on: ralph, set up ralph, run ralph, run the loop, implement tasks.…majiayu000ralphRalph autonomous coding loop with MiniMax subagent delegation. Managed loop (not recursive) with progress tracking, completion…majiayu000ralph-runRun RALPH autonomous development loop to implement features from the PRD.majiayu000writesralph-runRun RALPH autonomous development loop to implement features from the PRD.majiayu000writesralph-specumUse only when the user explicitly invokes `$ralph-specum`, requests Ralph Specum in Codex, asks Ralph Specum to handle a named…majiayu000ralph-techniqueThe Ralph Wiggum technique for minimal, declarative prompts that enable loop-based autonomous execution.majiayu000ralph-wiggumLong-running iterative development loops with pacing control and verifiable progress. Use when tasks require multiple iterations…majiayu000ralph-wiggumSurgical Debugger & Code Optimizer. Autonomous root-cause investigation, persistence-loop fixing, and high-fidelity code…majiayu000writesralph-wiggumExecuta loops autonomos de desenvolvimento via tecnica Ralph Wiggum. Usar quando: (1) Iniciar loop Ralph na sessao atual, (2)…majiayu000ramanujan-expanderRamanujan graphs and Alon-Boppana spectral optimality for edge growth rules. Optimal expanders with λ₂ ≤ 2√(d-1) bound.majiayu000
← Prev90 / 447Next →
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