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: Monitoring & ops
2,353 results · page 2 of 79
- View details
omni-resilienceSkillMonitoring & ops
Lets your agent check provider health, latency metrics, circuit-breaker states, and budget alerts in real time.
Ready to connect★ 64k
- View details
omni-version-managerSkillMonitoring & ops
Lets your agent start, stop, restart, update, and monitor local services and view their logs.
Ready to connect★ 64k
- View details
pricingSkillMonitoring & ops
Lets your agent apply marketing practices like copywriting, SEO, and growth analysis to your projects.
Ready to connect★ 49k
- View details
agentix-ceoSkillMonitoring & ops
Lets your agent use Agentix collaboration skills to work with other AI agents.
Ready to connect
- View details
sales-funnel-blueprintSkillMonitoring & ops
Lets your agent build and follow a step-by-step sales funnel plan for your product or service.
Ready to connect
- View details
pixijs-mathSkillMonitoring & ops
Lets your agent work with PixiJS coordinates, matrices, shapes, and hit testing math.
Ready to connect★ 48k
- View details
007SkillMonitoring & ops
Lets your agent run security audits, threat modeling, and code reviews to find and fix vulnerabilities.
Ready to connect★ 46k
- View details
ab-test-setupSkillMonitoring & ops
Guides your agent through setting up A/B tests with required checks for hypothesis, metrics, and readiness.
Ready to connect★ 46k
- View details
agent-qa-debug-fixSkillMonitoring & ops
Lets your agent debug and fix failed QA runs using logs and evidence, then verify the fixes work.
Ready to connect★ 46k
- View details
agent-qa-result-triageSkillMonitoring & ops
Lets your agent sort and analyze failed QA test runs, grouping them by failure type with suggested fixes.
Ready to connect★ 46k
- View details
application-performance-performance-optimizationSkillMonitoring & ops
Lets your agent analyze and tune application speed using profiling and observability data.
Ready to connect★ 46k
- View details
dnanexus-integrationSkillMonitoring & ops
Lets your agent run and monitor genomics jobs on DNAnexus, moving data and automating projects with the dx CLI.
Ready to connect★ 45k
- View details
medchemSkillMonitoring & ops
Lets your agent screen chemical compounds for drug-likeness, structural alerts, and complexity using standard medchem rules.
Ready to connect★ 45k
- View details
neuropixels-analysisSkillMonitoring & ops
Lets your agent analyze Neuropixels brain recordings, from loading raw data to spike sorting and quality checks.
Ready to connect★ 45k
- View details
pkpd-modelingSkillMonitoring & ops
Lets your agent run pharmacokinetic and pharmacodynamic modelling, from non-compartmental analysis to dose prediction.
Ready to connect★ 45k
- View details
pytorch-lightningSkillMonitoring & ops
Lets your agent write and run PyTorch training code organized for multi-GPU and distributed deep learning.
Ready to connect★ 45k
- View details
scientific-brainstormingSkillMonitoring & ops
Lets your agent run structured scientific brainstorming with independent idea generation, critique, and decision logs.
Ready to connect★ 45k
- View details
scikit-bioSkillMonitoring & ops
Lets your agent analyze biological sequence data, build phylogenetic trees, and compute diversity metrics for microbiome studies.
Ready to connect★ 45k
- View details
scikit-survivalSkillMonitoring & ops
Lets your agent build and evaluate survival models that handle censored or competing-risk time-to-event data.
Ready to connect★ 45k
- View details
simpySkillMonitoring & ops
Lets your agent build, run, and analyze discrete-event simulations with events, resources, and reproducible results.
Ready to connect★ 45k
- View details
statsmodelsSkillMonitoring & ops
Lets your agent run statistical models like regression, time series, and mixed models with detailed diagnostics in Python.
Ready to connect★ 45k
- View details
adding-activity-loggingSkillMonitoring & ops
Adds or changes activity logging (the audit trail) for a Django model in PostHog. Use when a model's writes must show in the Activity side panel or the advanced activity logs, when adding ModelActivityMixin, an ActivityScope, a model_activity_signal receiver, an activity describer, or field exclusio
Ready to connect★ 40k
- View details
analyzing-expensive-usersSkillMonitoring & ops
Analyze the most expensive users in AI observability and explain why they cost so much. Use when the user asks about top spenders, expensive users, per-user LLM cost, user-level cost drivers, or patterns behind high AI observability spend.
Ready to connect★ 40k
- View details
analyzing-experiment-precompute-canarySkillMonitoring & ops
Analyze the experiment precompute result-consistency canary across prod-US and prod-EU, deep-dive any issues, and produce an actionable report. Sweeps the canary's Prometheus health gauges in both regions, and when anything is unhealthy pulls the structured divergence/failure logs from Loki to recon
Ready to connect★ 40k
- View details
announcing-behavior-changesSkillMonitoring & ops
Decides whether a behavior-changing fix needs an in-app notice, then builds one that reaches only the affected users and can be removed later. Use when a change alters what an existing user sees without them doing anything — a metric moves, a chart shifts, a count drops, a date range resolves differ
Ready to connect★ 40k
- View details
building-a-dashboardSkillMonitoring & ops
Build a new dashboard, or update an existing one, from a set of insights — the same job the in-app assistant does with its upsert-dashboard tool, but over MCP. Use when a user asks to create a dashboard, put several metrics/charts together on one page, assemble a dashboard for a topic (product analy
Ready to connect★ 40k
- View details
creating-online-evaluationsSkillMonitoring & ops
Author continuously-running online evaluations in PostHog AI observability, grounded in real failure modes you've identified. Use when the user wants evaluations that automatically score new generations or whole traces going forward — "create an eval to catch X", "continuously check that responses d
Ready to connect★ 40k
- View details
exploring-llm-clustersSkillMonitoring & ops
Investigate AI observability clusters — understand usage patterns in AI/LLM traffic, compare cluster behavior, compute cost/latency metrics, and drill into individual traces within clusters.
Ready to connect★ 40k
- View details
instrumenting-first-party-metricsSkillMonitoring & ops
How to instrument PostHog's own Metrics product from PostHog-owned code — record counters, gauges, and histograms that land in posthog.metrics, the same way customers do. Use when adding application metrics in this monorepo (web, Celery, Temporal), when asked to push or ship metrics into posthog met
Ready to connect★ 40k
- View details
modeling-activation-metricsSkillMonitoring & ops
Build reusable activation models — an activation-rate metric and a per-user/per-account activated flag — on either PostHog data-warehouse views (HogQL) or an external dbt project. Use when the user wants to define, model, or measure activation, the "aha moment", onboarding success, or which early ac
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.