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 6 of 290
- View details
pylabrobotSkillAI & models
Lets your agent write and review lab automation protocols and liquid-handling plans using PyLabRobot, with offline simulation.
Ready to connect★ 45k
- View details
pymatgenSkillAI & models
Lets your agent analyze, validate, and convert crystal structures and computed materials data using pymatgen.
Ready to connect★ 45k
- View details
pymcSkillAI & models
Lets your agent build Bayesian statistical models and run simulations to estimate uncertainty in data.
Ready to connect★ 45k
- View details
pyzoteroSkillAI & models
Lets your agent manage your Zotero reference library: search, add, edit, and organize citations and collections.
Ready to connect★ 45k
- View details
qiskitSkillAI & models
Lets your agent build, simulate, and run quantum circuits using Qiskit and IBM quantum computers.
Ready to connect★ 45k
- View details
qutipSkillAI & models
Lets your agent simulate quantum systems, including dynamics, steady states, spectra, and phase-space analyses.
Ready to connect★ 45k
- View details
relsa-severity-assessmentSkillAI & models
Lets your agent assess severity and predict humane endpoints in lab animal studies from welfare data.
Ready to connect★ 45k
- View details
research-grantsSkillAI & models
Lets your agent draft research grant proposals for agencies like NSF, NIH, and DARPA with agency-specific formatting.
Ready to connect★ 45k
- View details
rowanSkillAI & models
Rowan is a cloud-native molecular modeling and medicinal-chemistry workflow platform with a Python API. Use for pKa and macropKa prediction, conformer and tautomer ensembles, docking and analogue docking, protein-ligand cofolding, MSA generation, molecular dynamics, permeability, descriptor workflow
Ready to connect★ 45k
- View details
scholar-evaluationSkillAI & models
Lets your agent review scholarly works with traceable feedback and audit research-assessment rubrics.
Ready to connect★ 45k
- View details
scientific-writingSkillAI & models
Lets your agent draft, revise, and check scientific manuscripts with evidence citations and reporting guidelines.
Ready to connect★ 45k
- View details
scikit-learnSkillAI & models
Lets your agent build and evaluate machine learning models in Python using scikit-learn.
Ready to connect★ 45k
- View details
scveloSkillAI & models
Lets your agent estimate how single cells change state over time from RNA sequencing data.
Ready to connect★ 45k
- View details
scvi-toolsSkillAI & models
Lets your agent build deep generative models for single-cell biology data, including batch correction and multimodal integration.
Ready to connect★ 45k
- View details
seabornSkillAI & models
Lets your agent create statistical charts like box plots, heatmaps, and pair plots from pandas data.
Ready to connect★ 45k
- View details
shapSkillAI & models
Lets your agent explain machine-learning predictions by computing and visualizing SHAP feature attributions.
Ready to connect★ 45k
- View details
stable-baselines3SkillAI & models
Lets your agent train and test reinforcement learning models using standard algorithms like PPO and DQN.
Ready to connect★ 45k
- View details
statistical-analysisSkillAI & models
Lets your agent run guided statistical analysis with test selection, assumption checks, and APA-formatted reporting.
Ready to connect★ 45k
- View details
statistical-powerSkillAI & models
Lets your agent calculate sample sizes and statistical power when planning a study.
Ready to connect★ 45k
- View details
resume-builderSkillAI & models
Lets your agent ask you questions and build a resume as JSON you can import into Reactive Resume.
Ready to connect★ 42k
- View details
auditing-llm-gateway-paritySkillAI & models
Audits services/llm-gateway against PostHog/ai-gateway and updates services/llm-gateway/PARITY.md from current implementation evidence. Use when either gateway changes auth, attribution, billing, endpoints, providers, models, routing, or metadata; when reviewing a Python gateway change; or when aske
Ready to connect★ 40k
- View details
authoring-data-quality-checksSkillAI & models
Adds and runs data quality checks (dbt-test style assertions) on a project's warehouse tables and saved-query views: not-null, uniqueness, accepted values, referential integrity, row-count bounds, freshness, and custom HogQL. Use when asked to test a model, validate a view, check for nulls or duplic
Ready to connect★ 40k
- View details
autoresolving-pr-conflictsSkillAI & models
Operating procedure for the conflict-autoresolver agent: sweep open PostHog/posthog PRs that conflict with master, resolve the trivial conflicts (generated artifacts deterministically, source conflicts with judgment), land one merge commit on the PR head, and flag everything else for a human. Use wh
Ready to connect★ 40k
- View details
exploring-ai-failuresSkillAI & models
Find where an AI/LLM application is failing in production and surface the failure patterns, working from real traces. Use when someone wants to understand what's going wrong with an AI feature, find and categorize failure modes, triage errors, or investigate quality issues (wrong answers, ignored in
Ready to connect★ 40k
- View details
exploring-llm-costsSkillAI & models
Investigate LLM spend in PostHog — total cost over time, cost by model, provider, user, trace, or custom dimension, token and cache-hit economics, and cost regressions. Use when the user asks "how much are we spending on LLMs?", "which model / user / feature is most expensive?", "why did cost spike?
Ready to connect★ 40k
- View details
fixing-flaky-testsSkillAI & models
Guides an agent through reproducing, root-causing, fixing, and validating flaky tests in the PostHog monorepo. Use when a test fails intermittently in CI but passes on rerun or locally, when `hogli ci:insights` or the debugging-ci-failures skill classifies a failure as a flaky test, when given a Git
Ready to connect★ 40k
- View details
ingestion-pipeline-doctor-nodejsSkillAI & models
Ingestion pipeline architecture overview and convention reference. Use when you need a quick orientation to the pipeline framework or want to know which doctor agent to use for a specific concern.
Ready to connect★ 40k
- View details
isolating-product-facade-contractsSkillAI & models
Plan and execute product isolation migrations to a facade plus contract layer in PostHog, following the Visual review architecture. Use when a product still exposes internals (models/logic/views) across boundaries and needs migration toward contracts.py + facade/api.py + presentation separation, wit
Ready to connect★ 40k
- View details
migrating-llm-gateway-callersSkillAI & models
Migrates an LLM caller from services/llm-gateway to PostHog/ai-gateway. Use when adding a gateway caller, converting an existing Python gateway integration, adopting shared Go-capable client builders, changing gateway URLs or headers for a caller, or removing a Python fallback. Inventories the calle
Ready to connect★ 40k
- View details
modeling-dimension-tablesSkillAI & models
Build reusable dimension / lookup tables for a star schema — country/region, timezone, currency, date, plan/product, and other descriptive attributes — on either PostHog data-warehouse views (HogQL) or an external dbt project. Use when the user wants to model dimension tables, lookup tables, a star
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.
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.