Agent Skills
Instruction packs that give your AI agent know-how — some work anywhere, some only with the tool they came with.
✦ Standalone skills3,373
Self-contained. Install one into any project and it works on its own — no other software needed.
🧰 Tool add-ons952
Come bundled with a specific tool and only work together with it — they teach your agent how to operate that tool.
✓ Official
48 companiesPublished by the companies themselves — pick one to see everything they ship.
openai5 skills
anthropics10 skills
google-gemini17 skills
microsoft92 skills
github8 skills
facebook4 skills
react1 skill
coinbase6 skills
stripe7 skills
shopify2 skills
cloudflare11 skills
vercel22 skills
vercel-labs63 skills
supabase4 skills
huggingface6 skills
pytorch2 skills
flutter3 skills
DataDog11 skills
getsentry89 skills
brave2 skills
googleworkspace95 skills
google-labs-code3 skills
genkit-ai9 skills
expo2 skills
n8n-io21 skills
sveltejs3 skills
nuxt1 skill
shadcn-ui2 skills
bitwarden2 skills
automattic14 skills
larksuite35 skills
browserbase1 skill
browser-use9 skills
apify2 skills
clickhouse8 skills
neondatabase11 skills
upstash10 skills
posthog165 skills
langfuse2 skills
resend3 skills
sanity-io24 skills
streamlit4 skills
remotion-dev3 skills
tldraw7 skills
apollographql1 skill
mastra-ai28 skills
triggerdotdev1 skill
mcp-use4 skillsposthog
6 tool add-ons
exploring-scouts
★ 35,336by posthog
How to explore and make sense of PostHog Signals scouts — the scheduled agents that scan a project and write reports into the Signals inbox. Use when a user wants to understand what scouts they have, how each one is behaving, and whether the fleet is actually working. Covers surveying the fleet and its schedules, reading recent scout runs and drilling into a single run's reasoning, inspecting the durable scratchpad memory the fleet has built up, tracing a run to the reports it wrote or edited, a
🧰 Not standalone — use together with posthog/posthog
kudos-storage
★ 35,336by posthog
The data model — the `kudos` table columns, the `kudos_id` dedupe/idempotency scheme, and the per-recipient `people/<handle>.md` profile memory. Load before any table-append or memory-write.
🧰 Not standalone — use together with posthog/posthog
runbook-memory
★ 35,336by posthog
🧰 Not standalone — use together with posthog/posthog
signals-scout-mcp-tool-calls
★ 35,336by posthog
Signals scout for PostHog MCP tool calls. Watches $mcp_tool_call telemetry for tools that need improvement — high, broad-reach failure rates, retry/hammering that betrays a confusing schema, slow or context-bloating responses — and files each validated tool-quality finding as a report in the inbox; otherwise writes durable memory and closes out empty. Adapts to which fields the project actually captures.
🧰 Not standalone — use together with posthog/posthog
optimizing-clickhouse-and-hogql-queries
★ 35,336by posthog
Workflow for optimizing ClickHouse and HogQL queries. Use when a HogQL query, query runner, insight, or report is too slow; when a hand-written ClickHouse query (via `sync_execute` or in a migration) is too slow; when ClickHouse times out or hits memory limits; when investigating a slow `system.query_log` row; or when reviewing a proposed HogQL printer change for performance. Covers extracting the ClickHouse SQL, common smells (`FROM ... FINAL`, `JSONExtract` over properties, missing skip indexe
🧰 Not standalone — use together with posthog/posthog
auditing-the-fleet
★ 35,336by posthog
The fleet-wide audit — sweep every agent, mine recent sessions for failures/anomalies, classify root causes, and branch a DRAFT proposal per fix (never freeze/promote); write a report to memory. Load when asked to audit all agents or what's underperforming.
🧰 Not standalone — use together with posthog/posthog