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
55,543 results · page 52 of 1,852
- View details
writing-code-commentsSkillDatabases & data
Gates whether a code comment should exist and forces the ones that stay to explain why, not what. Use ALWAYS before writing or editing a comment in any language (Python, TypeScript, Go, Rust, SQL), and when reviewing a diff that adds comments. Removes the comment types that clutter the codebase: nar
Ready to connect★ 40k
- View details
writing-dataclassesSkillDev tools
House rules for Python dataclasses in PostHog: when to reach for one instead of a tuple or `dict[str, Any]`, which decorator to use (`@frozen` from `posthog.dataclasses`), how to name, construct, consume and evolve them, how to keep secrets out of `repr`, and when a function should accept a dataclas
Ready to connect★ 40k
- View details
writing-evalsSkillCloud & infra
Teaches how to write and run evals on the `products/posthog_ai/eval_harness/` harness — sandboxed agent suites that execute the real coding agent in a Docker or Modal sandbox against a seeded Hedgebox project, and one-shot suites that score a single in-process model invocation per case. Use when add
Ready to connect★ 40k
- View details
writing-kea-logicsSkillFiles & storage
Guide for writing or reviewing PostHog kea logic files (`*Logic.ts` / `*Logic.tsx`). Use when creating a new logic, adding actions/reducers/selectors/listeners/loaders/forms/router bindings, choosing between reducer vs selector vs cache, deciding between listeners and `kea-subscriptions`, wiring Rea
Ready to connect★ 40k
- View details
writing-pr-descriptionsSkillDev tools
Shapes a PR body into something a reviewer understands at a glance. Use ALWAYS before writing or editing a PR description, before `gh pr create` or `gh pr edit --body`, and when asked to improve an existing description. Puts the effect a person sees in the first line and the mechanism under it, rout
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
writing-ui-componentsSkillFiles & storage
Structure and abstraction rules for PostHog UI code — any React component or frontend file under `frontend/src/` or `products/*/frontend/`. Use ALWAYS before creating, moving, splitting, or restructuring a component or frontend file, extracting a shared/generic component, promoting a component to `l
Ready to connect★ 40k
- View details
writing-user-facing-copySkillCommunication
Sets the voice and word choices for any text a person reads in PostHog: UI labels, buttons, tooltips, empty and error states, notifications, in-app messages, onboarding, docs, and support replies. Use ALWAYS before writing or editing user-facing copy, and whenever a code change adds or changes a str
Ready to connect★ 40k
- View details
avoid-ai-writingSkillDocs & knowledge
Lets your agent audit and rewrite text so it reads less like AI-generated writing.
Ready to connect★ 40k
- View details
before-you-buildSkillAI & models
Lets your agent review a product or feature idea for demand, positioning, monetization, and trust risks before you build it.
Ready to connect★ 40k
- View details
checkpoint-promotionSkillAI & models
Gates fine-tuned model checkpoints with drift budgets, paired comparisons, and forgetting checks before promotion.
Ready to connect★ 40k
- View details
dataset-curationSkillDatabases & data
Lets your agent prepare, format, and validate datasets for fine-tuning language models.
Ready to connect★ 40k
- View details
defi-protocol-templatesSkillCommerce & finance
Gives your agent ready-made code templates for building DeFi features like staking, token swaps, governance, and flash loans.
Ready to connect★ 40k
- View details
eval-harness-firstSkillAI & models
Guides your agent to build an evaluation harness with golden sets, graders, judge calibration, and baselines before fine-tuning.
Ready to connect★ 40k
- View details
file-conversionSkillFiles & storage
Lets your agent convert files between formats, like PDF to Word, MP4 to MP3, or CSV to JSON.
Ready to connect★ 40k
- View details
finetuning-method-selectionSkillAI & models
Helps your agent decide whether to fine-tune a model and pick the right method and base model.
Ready to connect★ 40k
- View details
grpo-rlvr-trainingSkillProductivity
Guides your agent through GRPO training for tasks where success can be automatically checked, like math or code.
Ready to connect★ 40k
- View details
hermes-tweetSkillMonitoring & ops
Lets your agent research X/Twitter accounts, read timelines, and analyze tweets with gated posting actions.
Ready to connect★ 40k
- View details
incident-runbook-templatesSkillDatabases & data
Lets your agent create incident response runbooks with step-by-step procedures, escalation paths, and recovery actions.
Ready to connect★ 40k
- View details
langchain-architectureSkillDocs & knowledge
Guides your agent in designing LLM apps with LangChain and LangGraph for agents, memory, and tool integration.
Ready to connect★ 40k
- View details
lora-qlora-recipesSkillAI & models
Guides your agent to set up LoRA and QLoRA fine-tuning configs with best-practice settings.
Ready to connect★ 40k
- View details
pptx-deck-contextSkillDocs & knowledge
Prepares the narrative, sources, and design context your agent needs to build an editable PowerPoint deck.
Ready to connect★ 40k
- View details
pptx-quality-gatesSkillDocs & knowledge
Lets your agent check and fix PowerPoint files for layout problems, accessibility, editability, and file integrity.
Ready to connect★ 40k
- View details
pptx-reference-deck-analysisSkillDocs & knowledge
Lets your agent inspect PowerPoint files to analyze their structure, themes, fonts, and layouts without changing them.
Ready to connect★ 40k
- View details
pptx-slide-specificationSkillDocs & knowledge
Lets your agent write and fix JSON specifications that define editable PowerPoint slide layouts.
Ready to connect★ 40k
- View details
pptx-visual-assetsSkillDocs & knowledge
Lets your agent add approved icons, images, diagrams, and infographics to PowerPoint decks.
Ready to connect★ 40k
- View details
preference-optimizationSkillAI & models
Lets your agent fine-tune a model using feedback data with methods like DPO or ORPO.
Ready to connect★ 40k
- View details
prompt-engineering-patternsSkillMedia
Helps your agent write, improve, and debug prompts using patterns like chain-of-thought and few-shot examples.
Ready to connect★ 40k
- View details
protect-mcp-setupSkillCommerce & finance
Lets your agent set up policy rules and signed receipts that record and control what tool actions it takes.
Ready to connect★ 40k
- View details
python-anti-patternsSkillAI & models
Lets your agent review Python code against a checklist of common anti-patterns and bad practices.
Ready to connect★ 40k
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.
55,111 of the 55,543 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.