Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: AI & models
8,992 results · page 196 of 300
- View details
zoom-mcp/revenue-acceleratorSkillAI & models
Zoom Revenue Accelerator MCP server guidance for conversation transcripts and analysis, scorecards, deals, customer accounts/contacts, indicators, teams, and users. Use when an AI agent needs read-oriented ZRA sales intelligence through the dedicated MCP endpoint.
Ready to connect★ 78
- View details
avoid-warp-divergenceSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
choose-launch-configurationSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
choose-tile-size-and-work-partitioningSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
debug-cuda-kernel-correctnessSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
debug-quantized-kernel-accuracySkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
evaluating-hook-hintsSkillAI & models
TraceDecay Dev: Use when auditing, testing, debugging, or improving TraceDecay hook hint behavior, especially Codex/Claude/Cursor hint injection, verbosity, repetition, dedupe, token efficiency, real transcript examples, synthetic scenarios, or `src/hooks/tool_hints*` changes.
Ready to connect★ 77
- View details
fuse-elementwise-opsSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
handle-boundary-conditionsSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
optimize-prefill-vs-decode-kernelsSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
optimize-triton-block-parametersSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
port-cuda-kernel-to-hipSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
port-cuda-kernel-to-tritonSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
using-the-cliSkillAI & models
Use when MCP is intentionally absent or unavailable, a host or subagent has shell access without MCP, or a tracedecay MCP call fails, times out, or disconnects.
Ready to connect★ 77
- View details
write-backend-agnostic-kernel-planSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-cuda-gemm-kernelSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-cuda-layernorm-kernelSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-cuda-reduction-kernelSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-cuda-softmax-kernelSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-fp8-kernelSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-int8-quantized-kernelSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-kernel-test-planSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-numerically-stable-kernelSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-tensorrt-plugin-integration-planSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-triton-attention-kernelSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-triton-dequant-kernelSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-triton-fused-add-rmsnorm-kernelSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-triton-gemm-kernelSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-triton-kv-cache-append-kernelSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
- View details
write-triton-layernorm-kernelSkillAI & models
Open source skill library for AI coding agents to write, optimize, and debug high performance compute kernels across CUDA, Triton, and quantized workloads.
Ready to connect★ 77
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
54,624 of the 55,055 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.