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
9,028 results · page 298 of 301
- View details
fleet-rolesSkillAI & models
The role catalogue and the descending-model rule for a multi-session fleet - which roles exist at each tier, what each owns, which model tier each runs on, and when a role should be its own session versus a subagent. Use when standing up a fleet, deciding who owns an activity, choosing a model for a
Ready to connect
- View details
football-prediction-skillSkillAI & models
Generate explainable China Sports Lottery football predictions with event-time snapshots, T-24h/T-6h/T-90m/closing model horizons, separate directional and value states, strict reference/target market isolation, sourced pre-match intelligence, hierarchical Dixon-Coles probabilities, multi-window mod
Ready to connect
- View details
frameworkSkillAI & models
Quick-reference mental model for the Tesseron TypeScript SDK — core abstractions (app, action, resource, handler, ActionContext, transport, session, gateway), canonical imports per consumer package (`@tesseron/web`, `/server`, `/react`, `/core`, `/mcp`), and the minimum-viable-app template. Load whe
Ready to connect
- View details
- View details
gitworfkflowsSkillAI & models
Git workflows including branching strategies, commits, merging, rebasing, and GitHub collaboration. Activate for git commands, version control, PRs, and repository management.
Ready to connect
- View details
harness-expertSkillAI & models
Expert-level Harness template types, runtime inputs, expression language, pipeline patterns (CI/CD, GitOps, Canary, Blue-Green), versioning, and step configurations
Ready to connect
- View details
hook-policy-engineSkillAI & models
Hook policy engine with 8 installable packs for safety, verification, context recovery, and teammate quality gates
Ready to connect
- View details
- View details
humanize-chineseSkillAI & models
A complete toolkit for removing the AI tone from Chinese text (works out of the box, zero API keys — the agent with this skill installed IS the LLM itself). Six workflows: ① De-AI at generation time — when writing Chinese, follow this skill's writing guidelines so the first draft already has no AI t
Ready to connect
- View details
icon-forgeSkillAI & models
Generate brand icons as SVG and produce all platform assets including favicon package (ICO, SVG with dark mode, apple-touch-icon), PWA manifest icons, and mobile app icons. Use when user runs /icon-forge, requests "brand icon", "favicon generation", "app icon", or "svg logo" for a project.
Ready to connect
- View details
- View details
kr-patent-dependent-claim-draftingSkillAI & models
Skill for drafting Korean patent dependent claims, system claims, program claims, and additional independent claims (claims 2–N). Takes a paper (or invention materials) and the finalized claim 1 as input, and drafts claims 2 through N from the perspective of a patent attorney well-versed in KIPO cla
Ready to connect
- View details
lead-qualifySkillAI & models
Score a lead or opportunity against an ideal-customer-profile fit check. Trigger when the user pastes a lead/company and asks "is this a fit", "should I pursue", or to qualify/score a lead against the ICP.
Ready to connect
- View details
listing-stale-branchesSkillAI & models
Lists local and remote git branches that are candidates for cleanup — merged but not deleted, and inactive branches with no commits in a configurable period (default 3 months). Use when user mentions "stale branches", "old branches", "branch cleanup", "prune branches", "dead branches", "unused branc
Ready to connect
- View details
llmintegrationSkillAI & models
LLM integration patterns for Claude, GPT, Gemini, and Ollama. Activate for AI API integration, prompt engineering, token management, extended thinking, and multi-model orchestration.
Ready to connect
- View details
local-ai-filmSkillAI & models
Produce AI short films (atmosphere pieces / mood pieces / trailers / vlogs / narrative films with dialogue) using local or cloud models. Directing hub entry point: manages go/no-go decisions, anti-homogenization, pitfall avoidance, execution workflow, and final post-production assembly. Trigger scen
Ready to connect
- View details
lsp-integrationSkillAI & models
LSP server detection, installation, and Claude Code integration — auto-invoke when setting up a new project, running /cc-setup, or configuring IDE tooling
Ready to connect
- View details
lyraSkillAI & models
Transform vague inputs into precision-optimized AI prompts for Claude, ChatGPT, Gemini, or other LLMs. Use when user mentions "optimize prompt", "improve prompt", "lyra", "prompt engineering", or needs help crafting effective AI prompts.
Ready to connect
- View details
- View details
- View details
- View details
onboarding-handoffSkillAI & models
Run the Won→onboarding handoff — the seam most teams drop. Trigger when a deal is marked won/closed-won, when the user says "we won X", "hand this off to onboarding", "kick off the new customer", or "onboarding checklist".
Ready to connect
- View details
onescience-knowledge-harvesterSkillAI & models
OneScience skill for automatically filling knowledge gaps. When a user describes missing knowledge in a domain (e.g., "lacking knowledge of saffron gene-derived reasoning"), it automatically runs: literature search → knowledge extraction → card generation → writing to onescience-primitives, so subse
Ready to connect
- View details
onescience-primitive-distillerSkillAI & models
OneScience primitive distillation execution skill. Used to distill scientific-agent-skills, third-party research tools, databases, services, datasets, output formats, or workflow documentation into onescience-primitives asset packages, and to determine whether resource, expert, or executor implement
Ready to connect
- View details
pattern-captureSkillAI & models
This skill should be used when the user asks to 'find repeated feedback', 'what do I keep correcting', 'capture this pattern', 'DRY my prompting', 'stop repeating myself', 'turn this into a check', 'automate this correction', or when the same type of feedback has been given 3+ times across sessions.
Ready to connect
- View details
plugin-catalogSkillAI & models
Domain knowledge for the cowork marketplace seed catalog, including all 17 items mapped to 16 installed plugins with their agents, skills, and commands
Ready to connect
- View details
plugin-packagingSkillAI & models
Knowledge for exporting marketplace items as Cowork-compatible plugin ZIPs for distribution via Claude Desktop private marketplaces
Ready to connect
- View details
product-signalSkillAI & models
Route post-sale and field signals into product's roadmap queue, and write the buyer-facing line for anything shipped. Trigger when the user says "what should product hear", "triage the roadmap signals", "route this to product", "feature request", or "what does this feature mean for the buyer".
Ready to connect
- View details
project-scaffoldingSkillAI & models
Project type detection matrix, template recommendations per project type, post-scaffolding checklist, Harness integration patterns, and testing recommendations
Ready to connect
- View details
qbr-prepSkillAI & models
Turn a customer's recent calls, adoption signal, and roadmap status into a QBR brief that leads with the outcome they bought. Trigger when a quarterly business review is coming up, before a renewal or value-review call, or when the user says "QBR prep", "build the QBR", "quarterly review for X", or
Ready to connect
Popular skills lists
- Best Claude skills for what are
- Best Claude skills for awesome
- Best Claude skills for github
- Best Claude skills for how to use
- Best Claude skills for anthropic
- Best Claude skills for grill me
- Best Claude skills for how to create
- Best Claude skills for caveman
- Best Claude skills for humanizer
- Best Claude skills for remotion
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.
55,483 of the 55,914 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.