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
9,019 results · page 57 of 301
- View details
childcare-comparisonSkillAI & models
Compare childcare options — nursery/daycare, childminder, nanny, family, or a mix — for your family's real needs, budget, and values. Use when asked to compare childcare options, nursery vs nanny, how to choose childcare, or find the right childcare. Produces a needs-and-values profile, a side-by-si
Ready to connect★ 1k
- View details
churn-analysisSkillAI & models
Produce a structured churn analysis that separates avoidable from unavoidable churn. Use when investigating why customers are leaving, identifying at-risk segments, calculating net revenue retention, or building a retention intervention plan. Produces a churn report with rate calculations, categoris
Ready to connect★ 1k
- View details
router-core/type-safetySkillAI & models
Full type inference philosophy (never cast, never annotate inferred values), Register module declaration, from narrowing on hooks and Link, strict:false for shared components, getRouteApi for code-split typed access, addChildren with object syntax for TS perf, LinkProps and ValidateLinkOptions type
Ready to connect★ 1k
- View details
start-core/execution-modelSkillAI & models
Isomorphic-by-default principle, environment boundary functions (createServerFn, createServerOnlyFn, createClientOnlyFn, createIsomorphicFn), ClientOnly component, useHydrated hook, import protection, dead code elimination, environment variable safety (VITE_ prefix, process.env).
Ready to connect★ 1k
- View details
loreSkillAI & models
SpecStory Lore - mine your SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more) into a persistent corpus, surface your reproducible workflows with corroborated evidence, and interactively forge the chosen ones into skills installed across all your agent harnesses. Us
Ready to connect★ 1k
- View details
workthreadsSkillAI & models
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shi
Ready to connect★ 1k
- View details
paper-dailySkillAI & models
Discover daily arXiv papers for LLM/Agent topics, rank candidates with keyword and institution filters, and prepare a small selected paper list for llm-paper-daily style workflows.
Ready to connect★ 1k
- View details
translate-docsSkillAI & models
Rules for the Chinese (docs/zh) tree — what is translated and what stays verbatim, by position on the page and by term. Read BEFORE translating, reviewing, or editing any docs/zh page or the translation prompts in tools/docs/translate.ts.
Ready to connect★ 1k
- View details
triageSkillAI & models
Classify untriaged issues (issues without the permanent triaged marker — open by default, closed backfills optional) via a GPT batch run, validate against the label taxonomy, and return a proposed-labels report plus an activity digest. Read-only — applying labels happens in the main conversation aft
Ready to connect★ 1k
- View details
jcp-stock-analysisSkillAI & models
Intelligent A-share stock analysis system using multi-agent collaboration to provide technical, fundamental, and risk analysis. Requires the Jiucaipan desktop app running with the OpenClaw service enabled.
Ready to connect★ 1k
- View details
thinking-model-combinationSkillAI & models
When one mental model leaves a material blind spot on a multi-domain or high-stakes problem, sequence complementary models with named roles and a conflict rule.
Ready to connect★ 1k
- View details
thinking-model-routerSkillAI & models
When unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).
Ready to connect★ 1k
- View details
harness-developmentSkillAI & models
Add, modify, or debug Centaur harness-server backends in crates/harness-server. Use when adding support for a new harness CLI, changing Codex App Server V2 normalization, investigating Claude Code/Amp/Codex streaming or steering behavior, removing Python/TypeScript harness normalizers, or differenti
Ready to connect★ 1k
- View details
oma-academic-writingSkillAI & models
Academic writing capability for publication-grade English prose.
Ready to connect★ 1k
- View details
oma-coordinationSkillAI & models
Guide for coordinating PM, Frontend, Backend, Mobile, and QA agents
Ready to connect★ 1k
- View details
oma-debugSkillAI & models
Bug diagnosis and fixing specialist - analyzes errors, identifies
Ready to connect★ 1k
- View details
oma-explanationSkillAI & models
Turn a code change (diff, PR, branch, commit range) into a rich,
Ready to connect★ 1k
- View details
oma-frontendSkillAI & models
Frontend specialist for React, Next.js, Angular, TypeScript with
Ready to connect★ 1k
- View details
oma-marketSkillAI & models
Market research skill for pain-point extraction, trend detection,
Ready to connect★ 1k
- View details
oma-mobileSkillAI & models
Mobile specialist for Flutter, React Native, and Swift native iOS
Ready to connect★ 1k
- View details
oma-orchestrationSkillAI & models
Automated multi-agent orchestration that spawns CLI subagents in
Ready to connect★ 1k
- View details
oma-recapSkillAI & models
Analyze conversation histories from multiple AI tools (Grok,
Ready to connect★ 1k
- View details
oma-refactorSkillAI & models
Behavior-preserving refactoring specialist - plans and executes
Ready to connect★ 1k
- View details
oma-scmSkillAI & models
"SCM (software configuration management) and Git: branching,
Ready to connect★ 1k
- View details
oma-skill-creationSkillAI & models
Create or update OMA skills in the SSL-lite human-readable format.
Ready to connect★ 1k
- View details
oma-tf-infraSkillAI & models
Infrastructure-as-code specialist for multi-cloud provisioning
Ready to connect★ 1k
- View details
oma-translationSkillAI & models
Context-aware translation and localization for UI strings,
Ready to connect★ 1k
- View details
oversized-skillSkillAI & models
A skill whose body deliberately exceeds the 500-line recommendation.
Ready to connect★ 1k
- View details
valid-skillSkillAI & models
A minimal, fully spec-conformant fixture skill used to exercise the happy path.
Ready to connect★ 1k
- View details
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.
54,764 of the 55,196 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.