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 197 of 300
- View details
write-triton-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-rope-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-sampling-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-silu-mul-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-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-vllm-custom-op-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
writing-agent-managed-skillsSkillAI & models
TraceDecay Dev: Use when creating, revising, validating, approving, installing, or auditing TraceDecay agent-managed automation skills and skill-writer drafts.
Ready to connect★ 77
- View details
adopt-projectSkillAI & models
Apply agent-starter patterns to an EXISTING project - audits the codebase, proposes components by invasiveness tier (hooks, skills, CLAUDE.md, lint configs, patterns), and applies only what the developer approves. Use when the user says adopt, retrofit, "apply agent-starter to this project", or want
Ready to connect★ 76
- View details
apac-transfersSkillAI & models
Guides management of cross-border data transfers under Asia-Pacific regulatory frameworks including APEC CBPR, ASEAN Model Contractual Clauses, Japan APPI supplementary rules, South Korea PIPA provisions, and Thailand/Singapore PDPA mechanisms. Keywords: APEC CBPR, ASEAN MCCs, APPI, PIPA, PDPA, APAC
Ready to connect★ 76
- View details
apec-cbpr-certSkillAI & models
Guides APEC Cross-Border Privacy Rules system certification process including self-assessment against the APEC Privacy Framework principles, accountability agent selection, intake questionnaire completion, certification decision, annual recertification, and Global CBPR Forum transition. Keywords: AP
Ready to connect★ 76
- View details
approvalSkillAI & models
Set the oma approval stance (`suggest`, `auto`, `full-auto`) with explicit risk guardrails.
Ready to connect★ 76
- View details
claude-plugin-converterSkillAI & models
Convert Claude Code plugins into self-contained Hermes plugins — discovery analysis then full conversion
Ready to connect★ 75
- View details
commit-push-prSkillAI & models
Full git workflow - creates branch, commits, pushes, and creates or updates a PR with summary and test plan.
Ready to connect★ 76
- View details
compliance-anthropicSkillAI & models
Navigate privacy regulations (GDPR, CCPA), review DPAs, and handle data subject requests. Use when reviewing data processing agreements, responding to data subject access or deletion requests, assessing cross-border data transfer requirements, or evaluating privacy compliance.
Ready to connect★ 76
- View details
consensusSkillAI & models
Compare multiple implementation options and converge on a decision with clear trade-offs.
Ready to connect★ 76
- View details
deep-initSkillAI & models
Initialize long-session context using a deep repository map, verification hooks, and risk hotspots.
Ready to connect★ 76
- View details
endpoint-probeSkillAI & models
Use when you need to discover an API's surface — poke a base URL to find its type (REST, GraphQL, SOAP, JSON-RPC), auth scheme, available endpoints, rate limits, and CORS policy. Also probes MCP servers (HTTP and stdio) to discover tools, resources, and prompts with full input schemas. Runs a Python
Ready to connect★ 75
- View details
entity-researchSkillAI & models
Deep background research on an entity — a company OR a person — into a cited dossier: identity & background, ownership & key management, adverse / negative media, public sanctions-list name-match signals, PEP indications from public research, and litigation / regulatory history. Use when the user sa
Ready to connect★ 75
- View details
- View details
- View details
ide-user-presetsSkillAI & models
Install or refresh an IDE's CMakeUserPresets.json from the checked-in template, substituting the scdv prefix so the `ide-scdv-reldbg` preset carries a real path. Use when setting an IDE up on a checkout, when an IDE cannot find Qt6 or pybind11, or after the template changes. Not a build step; agents
Ready to connect★ 76
- View details
input-token-analysisSkillAI & models
Use when input token spend needs explaining and fixing.
Ready to connect★ 75
- View details
input-token-overheadsSkillAI & models
Use when context window is filling up too fast or input token cost is too high. Audits overhead sources.
Ready to connect★ 75
- View details
intentSkillAI & models
Classifies user intent before execution begins and routes work to the correct oma phase.
Ready to connect★ 76
- View details
labor-arbitration-agentSkillAI & models
You are a **Labor Arbitration Agent** specializing in representing employees in China's labor dispute resolution system. You bridge the gap between wronged workers who cannot afford lawyers and the legal system that can deliver justice—at minimal cost and maximum effectiveness.
Ready to connect★ 76
- View details
loopSkillAI & models
Enforces a repeated execute-verify-fix loop until acceptance criteria pass or a blocking issue is clearly identified.
Ready to connect★ 76
- View details
media-analyzerSkillAI & models
Technique-focused media analysis. Detects rhetorical tools (loaded language, cherry-picking, source selection bias, framing, omission, emotional appeals, false balance) in articles and produces a structured analysis report. Identifies specific techniques and bias-signal intensity without labeling po
Ready to connect★ 75
- View details
miseSkillAI & models
Mise en place - setup and health check. Verifies Codex CLI and auth, installs the delegation profile, scaffolds AGENTS.md, and offers the routing policy. Re-run anytime, and after plugin updates to refresh the profile. Use when the user asks to set up sous-chef, or when another sous-chef skill fails
Ready to connect★ 76
- View details
modeSkillAI & models
Check or switch the oma operation mode/profile to adjust speed, depth, autonomy, or strict quality gating.
Ready to connect★ 76
- View details
notebooklm-modeSkillAI & models
Source-grounded research pipeline inspired by NotebookLM. Collect verbatim source extracts into a temporary workspace, then answer questions and create deliverables grounded in those sources. Two grounding modes: strict (vault-only) and augmented (vault + labeled [background] knowledge). Trigger whe
Ready to connect★ 75
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.