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
8,700 results · page 7 of 290
- View details
modeling-warehouse-foundationsSkillAI & models
Shared foundations for building reusable data models in PostHog, on either of two stacks: PostHog-native data-warehouse views / materialized views (HogQL, via the view-* MCP tools), or an external dbt project (sources.yml + staging/marts + schema tests) run against your own or PostHog's managed ware
Ready to connect★ 40k
- View details
scanning-experiments-with-replay-visionSkillAI & models
Provisions a Replay Vision scanner scoped to one experiment's exposed sessions: sets `experiment_targeting` so the API derives the person-scoped exposure filter server-side, templates a prompt that stays comparable across variants, sizes credit spend against the experiment's own population, and crea
Ready to connect★ 40k
- View details
setting-up-devboxSkillAI & models
Guide a PostHog engineer through spinning up, connecting to, running commands on, and mirroring local code to a remote devbox (a Coder workspace running the full PostHog stack). Use when asked to set up a devbox, start or connect to a devbox, configure remote dev, get gh CLI / Claude Code authed on
Ready to connect★ 40k
- View details
setup-web-testsSkillAI & models
Set up Python test environment in Claude Code for web where flox is unavailable. Use when you need to run backend tests and `uv sync` fails due to Python version mismatch.
Ready to connect★ 40k
- View details
writing-skillsSkillAI & models
Guide for writing PostHog agent skills — job-to-be-done templates that teach agents how to use MCP tools to achieve a goal. Use when adding new product functionality that agents should know how to work with, creating a new skill, or updating existing skills in products/*/skills/.
Ready to connect★ 40k
- View details
agent-skill-stackSkillAI & models
Helps your agent find and pick the smallest set of skills needed to complete a multi-step task.
Ready to connect★ 39k
- View details
agentic-evalSkillAI & models
Gives your agent patterns for grading and improving its own outputs, like self-critique loops and rubric-based evaluation.
Ready to connect★ 39k
- View details
ai-team-orchestrationSkillAI & models
Lets your agent set up and run a small multi-agent team to plan, implement, and QA coding work.
Ready to connect★ 39k
- View details
arize-experimentSkillAI & models
Lets your agent create, run, and compare Arize experiments to evaluate model performance.
Ready to connect★ 39k
- View details
arize-prompt-optimizationSkillAI & models
Lets your agent improve and debug AI prompts using real performance data from your app.
Ready to connect★ 39k
- View details
arize-traceSkillAI & models
Lets your agent download and inspect Arize traces and spans to debug what an LLM app is doing.
Ready to connect★ 39k
- View details
audit-integritySkillAI & models
Adds quality checks to your agent's security audits, forcing honest self-review and retries until findings meet a high bar.
Ready to connect★ 39k
- View details
breakdown-feature-implementationSkillAI & models
Lets your agent create a detailed plan for implementing a feature step by step.
Ready to connect★ 39k
- View details
breakdown-planSkillAI & models
Turns a project idea into a structured plan with epics, features, stories, tests, dependencies, and priorities.
Ready to connect★ 39k
- View details
cli-masterySkillAI & models
Trains you on GitHub Copilot CLI with guided lessons, quizzes, and a reference on its commands and features.
Ready to connect★ 39k
- View details
code-exemplars-blueprint-generatorSkillAI & models
Generates prompts that help your agent scan a codebase and pick out high-quality code examples in many languages.
Ready to connect★ 39k
- View details
competitor-ad-intelligenceSkillAI & models
Lets your agent analyze a competitor's paid ads and break down their ad strategy and angles.
Ready to connect★ 39k
- View details
copilot-sdkSkillAI & models
Lets your agent build apps that embed GitHub Copilot agents with custom tools and streaming responses.
Ready to connect★ 39k
- View details
declarative-agentsSkillAI & models
Helps you build Microsoft 365 Copilot custom agents with guided workflows and templates.
Ready to connect★ 39k
- View details
diagnoseSkillAI & models
Lets your agent scan an AI workflow across quality dimensions and produce a scored report with prioritized fixes.
Ready to connect★ 39k
- View details
dotnet-mcp-builderSkillAI & models
Helps your agent build MCP servers in C#/.NET using the current 2.x libraries and correct setup defaults.
Ready to connect★ 39k
- View details
dotnet-upgradeSkillAI & models
Lets your agent analyze a .NET project and perform a framework upgrade.
Ready to connect★ 39k
- View details
improveSkillAI & models
Lets your agent audit a codebase and produce prioritized improvement plans for other agents to execute.
Ready to connect★ 34k
- View details
gws-modelarmorSkillAI & models
Lets your agent check user-generated content against Google's safety filters before using it.
Ready to connect★ 31k
- View details
gws-modelarmor-create-templateSkillAI & models
Lets your agent create a new Google Model Armor template for AI safety settings.
Ready to connect★ 31k
- View details
gws-modelarmor-sanitize-promptSkillAI & models
Lets your agent check a user prompt against Google Model Armor safety rules before sending it to a model.
Ready to connect★ 31k
- View details
gws-modelarmor-sanitize-responseSkillAI & models
Lets your agent check an AI model's response against a Model Armor safety template before using it.
Ready to connect★ 31k
- View details
add-atomic-chat-toolSkillAI & models
Lets your agent chat with AI models running locally on your computer through the Atomic Chat desktop app.
Ready to connect★ 31k
- View details
add-codexSkillAI & models
Lets your agent use OpenAI's Codex as an alternative AI model provider for planning and running tasks.
Ready to connect★ 31k
- View details
add-ollama-toolSkillAI & models
Lets your agent run and chat with AI models running locally on your machine.
Ready to connect★ 31k
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.
52,524 of the 52,958 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.