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.
Filter by category
55,257 results · page 162 of 1,842
- View details
stacked-chart-visualizationSkillDev tools
Lets your agent turn categorical percentage data into stacked bar charts showing how compositions change over time or across categories.
Ready to connect★ 6k
- View details
statistical-distribution-and-outlier-analysisSkillDev tools
Lets your agent analyze number distributions, spot outliers, and create box plot and histogram reports.
Ready to connect★ 6k
- View details
text-normalization-and-large-file-processingSkillFiles & storage
Lets your agent clean and normalize Excel files, like removing odd prefixes or extracting Chinese characters.
Ready to connect★ 6k
- View details
time-series-and-categorical-analysisSkillMonitoring & ops
Lets your agent analyze trends and make predictions from time-series or categorical data with visual reports.
Ready to connect★ 6k
- View details
top-value-coloringSkillMonitoring & ops
Lets your agent highlight top values in Excel sheets and export them with formatting.
Ready to connect★ 6k
- View details
trend-analysisSkillDev tools
Lets your agent analyze data trends, forecast future values, and create comparison charts.
Ready to connect★ 6k
- View details
word-analysisSkillFiles & storage
Lets your agent read Word documents, extracting text, tables, formatting, and image captions.
Ready to connect★ 6k
- View details
humanizeSkillDev tools
Lets your agent rewrite Korean AI-generated text so it reads like natural human writing.
Ready to connect★ 6k
- View details
humanize-koreanSkillAI & models
Lets your agent rewrite AI-generated Korean text so it reads like natural human writing.
Ready to connect★ 6k
- View details
humanize-redoSkillDev tools
Lets your agent re-run a previous Korean text humanization pass with targeted fixes for specific categories, paragraphs, or intensity.
Ready to connect★ 6k
- View details
lieflat-chartsSkillDev tools
Lets your agent generate HTML charts and publishable reports from ready-made chart and report templates.
Ready to connect★ 6k
- View details
apitestSkillDev tools
Lets your agent test local APIs by running chained curl commands and running test suites in parallel.
Ready to connect★ 6k
- View details
archSkillDev tools
Lets your agent answer questions about the FlexPrice codebase layout, dependencies, and key flows.
Ready to connect★ 6k
- View details
composeSkillCloud & infra
Lets your agent set up and run FlexPrice development services with Docker Compose shortcuts and view logs.
Ready to connect★ 6k
- View details
context-syncSkillFiles & storage
Lets your agent update AGENTS.md context files so they match the current codebase.
Ready to connect★ 6k
- View details
devenvSkillCloud & infra
Sets up your dev environment by mixing local Docker services with shared cloud credentials from .env files.
Ready to connect★ 6k
- View details
ghSkillDev tools
Lets your agent manage GitHub pull requests, checks, and issues for FlexPrice repos using the gh CLI.
Ready to connect★ 6k
- View details
godevSkillDev tools
Lets your agent format, vet, and run tests including race tests on Go code.
Ready to connect★ 6k
- View details
openapiSkillDev tools
Lets your agent generate Swagger specs and SDKs, and merge API definition files.
Ready to connect★ 6k
- View details
bashSkillDev tools
Teaches your agent how to use the shell effectively when running commands.
Ready to connect★ 6k
- View details
text-to-lottieSkillDev tools
Lets your agent create and edit Lottie JSON animations like loaders, icons, and UI effects.
Ready to connect★ 5k
- View details
codex-with-chatgptSkillDev tools
Lets your agent use ChatGPT on the web to plan and review its Codex coding work while it keeps writing the code.
Ready to connect★ 5k
- View details
get-prompt-from-imageSkillMedia
Lets your agent look at an image and write a prompt that recreates it with an image generator.
Ready to connect★ 5k
- View details
agentic-workflowsSkillMedia
Lets your agent route GitHub workflow design, create, debug, and upgrade requests to the right prompts.
Ready to connect★ 5k
- View details
analyzing-dotnet-performanceSkillDocs & knowledge
Scans your .NET code for about 50 common performance problems and suggests fixes.
Ready to connect★ 5k
- View details
android-tombstone-symbolicationSkillFiles & storage
Turns cryptic Android crash backtraces from .NET apps into readable function names and source file locations.
Ready to connect★ 5k
- View details
apple-crash-symbolicationSkillFiles & storage
Lets your agent turn cryptic .NET app crash logs from iPhones and Macs into readable function names and line numbers.
Ready to connect★ 5k
- View details
assertion-qualitySkillDev tools
Lets your agent grade how meaningful your test assertions are and spot weak or trivial checks.
Ready to connect★ 5k
- View details
author-componentSkillFiles & storage
Lets your agent write and review Blazor UI components (.razor files) following correct patterns.
Ready to connect★ 5k
- View details
authoring-github-workflowsSkillFiles & storage
Helps your agent write and fix GitHub Actions workflow files so they load and run without errors.
Ready to connect★ 5k
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.
54,826 of the 55,257 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.