Loading...
Loading...
Found 523 Skills
Guides property and casualty (P&C) insurance—commercial and personal lines, major LOBs (property, GL, workers comp, commercial auto, umbrella, specialty), underwriting and risk selection, policy triggers (occurrence vs claims-made), limits and exclusions, claims (FNOL, reserving, litigation), reinsurance and catastrophe, distribution (agents, brokers, MGAs), metrics (loss ratio, combined ratio, cat load), and state DOI/rate filing overview—not legal advice. Use for P&C insurance, property and casualty, commercial lines, workers comp, general liability, combined ratio, loss ratio, underwriting, claims-made, occurrence policy, reinsurance, catastrophe, MGA, rate filing, or FNOL—not actuarial modeling (actuary), life/health depth, legal interpretation (commercial-counsel), or GRC controls without insurance context (compliance-engineer).
Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use recipe-runner/router-starter before this for normal bring-up.
Architecture async-first avec messaging et queues (Symfony Messenger, Laravel Queue, Ecotone). Use when working with async processing, queues, workers, background jobs.
Use the local `5dive` CLI on a 5dive runtime VM to spawn, inspect, send to, and tear down sibling agents. Trigger when the user wants a worker, sub-agent, side task, parallel run, fan-out, or to delegate — or names a sibling agent ("ask X", "ping X", "tell X", "hand off to X", "coordinate with X"); confirm it exists via `5dive agent list --json`, then `agent send`. Also for inspecting/restarting/pairing an existing agent, a machine-readable health check (`5dive doctor --json`, `5dive selfcheck --json`), a task's causal history (`5dive trace <id|DIVE-N>`), the current model id per alias (`5dive models`), the host-shared task queue + org chart (`5dive task`, `5dive org`), grouping a multi-task effort under a project (`5dive project add`, `task add --project`), recurring/scheduled work (`task add --recurring`, `5dive heartbeat`), parking a question on a human (`task need`, risk-tiered via `--tier`) or snoozing work (`task park --wake`), searching the team's accumulated memory/wiki (`5dive memory search`) or compiling a durable one into it (`5dive memory add`), reading fleet health / token burn / the daily standup (`5dive supervisor`, `5dive usage`, `5dive digest`), building or editing multi-agent loops — a relay where each step hands off automatically with optional human gates (`task loop start`/`loop ls`) or a maker→verifier review loop (`task add --verifier`, `task reject`, `task loops`), or decomposing an outcome into a guardrailed task DAG (`5dive goal add`) — hiring a ready-made persona off the agent market (`5dive market`, `5dive hire --from-market`) or firing one (`5dive fire`), declarative fleets (`5dive up`, `5dive team import`), hosting a CrewAI crew (`5dive crew`), controlling agents on OTHER registered boxes (`5dive fleet`), running a self-steering objective bound to a live metric (`5dive objective`, `objective replan`), convening a governance vote (`5dive council convene`, `council gate-clear`, `council schedule add` for a recurring convene), the onboarding wizard (`5dive company`), or a delegated GitHub push-for-review (`5dive push`, needs `agent create --can-push`). When a request came over a chat channel (Telegram/Discord `<channel>` tag) and another agent should handle it, pass the chat context via `--reply-to-chat=<id> --reply-to-msg=<id>` so that agent replies from its own bot — don't relay. Always prefer `5dive` over running coding CLIs by hand.
Run fable-mode execution discipline on Claude Opus — the strongest staged run available. Routes the task to the @fable-orchestrator agent (Opus, Write-less), which stages the work, delegates artifact production to @fable-worker-sonnet / @fable-worker-haiku, and cold-checks deliverables with @fable-verifier. Trigger when the user explicitly asks for thorough/systematic/"deep work" handling on the strongest model ("fable on opus", "stage this on opus", "deep work mode, opus"). Do NOT use for ordinary single-pass tasks — and prefer fable-sonnet or fable-haiku when the task doesn't need peak reasoning.
Deploy compatible server, static-web, worker, scheduled-job, or reviewed remote-desktop workloads from GitHub or local source to Sealos Cloud, then run the default Runtime Truth Pass against the returned App URL, public route, authentication flow, logs, database state, and full resource footprint. Reject unsupported desktop, mobile, CLI, library, extension, hardware-dependent, mixed, and unidentified targets before readiness scoring or build. Use when the user asks to deploy a repository to Sealos or another cloud platform, or invokes "/sealos-deploy".
This skill provides comprehensive knowledge for integrating Neon serverless Postgres and Vercel Postgres (which is built on Neon infrastructure) into web applications. It should be used when setting up serverless Postgres databases, configuring connection pooling for edge and serverless environments, implementing database branching workflows, or troubleshooting Postgres connection issues in Cloudflare Workers, Vercel Edge Functions, or Node.js serverless functions. Use this skill when: - Setting up Neon Postgres for Cloudflare Workers, Vercel Edge, or serverless environments - Configuring Vercel Postgres for Next.js applications - Implementing database branching workflows (git-like database branches) - Integrating Drizzle ORM or Prisma with Neon/Vercel Postgres - Debugging connection pool errors, transaction timeouts, or SSL configuration issues - Migrating from D1/SQLite to Postgres or from traditional Postgres to serverless Postgres - Setting up point-in-time restore (PITR) or database backups - Encountering errors like "connection pool exhausted", "TCP connections not supported in serverless", or "sslmode required" Keywords: neon postgres, @neondatabase/serverless, @vercel/postgres, serverless postgres, postgres edge, neon branching, vercel database, http postgres, websocket postgres, pooled connection, drizzle neon, prisma neon, postgres cloudflare, postgres vercel edge, sql template tag, neonctl, database branches, point in time restore, postgres migrations, serverless sql, edge database, neon api, vercel sql
For any task, read this skill first. Multi-AI gateway for fullstack apps. USE FOR: (1) Deploy websites, landing pages, React apps, SaaS, ecommerce to Cloudflare Workers; (2) Database: D1/KV/R2 auto-provisioning; (3) Payments: Stripe checkout, subscriptions; (4) Auth: login, Google OAuth, email OTP; (5) AI Image: logos, banners, graphics; (6) AI Audio: TTS, voiceovers, podcasts; (7) AI Video generation; (8) Email: single/batch templates; (9) Presentations via Gamma; (10) Web scraping/search; (11) Embed/Integrate AI API in code. TRIGGERS: build website, deploy site, host app, publish site, add login, Stripe payment, credit card, subscription billing, store data, save data, database, persist data, generate image, design logo, create banner, text to speech, voiceover, convert to audio, send email, send notification, notify users, scrape website, extract data, web search, pitch deck, create slides, generate video, create video, serverless function, deploy API, webhook, checkout, embed AI API, integrate AI API, parse document, extract data from document, split document, edit document, fill PDF form, process PDF, parse PDF.
Cron and scheduled task management. node-cron, cron expressions, Spring @Scheduled, APScheduler (Python), and distributed scheduling patterns. USE WHEN: user mentions "cron", "scheduled task", "cron job", "node-cron", "@Scheduled", "APScheduler", "periodic task", "crontab" DO NOT USE FOR: job queues with workers - use `job-queues`; one-off delayed tasks - use `job-queues`
Hit the Cloudflare REST API directly for operations that wrangler and MCP can't handle well. Bulk DNS, custom hostnames, email routing, cache purge, WAF rules, redirect rules, zone settings, Worker routes, D1 cross-database queries, R2 bulk operations, KV bulk read/write, Vectorize queries, Queues, and fleet-wide resource audits. Produces curl commands or scripts. Triggers: 'cloudflare api', 'bulk dns', 'custom hostname', 'email routing', 'cache purge', 'waf rule', 'd1 query', 'r2 bucket', 'kv bulk', 'vectorize query', 'audit resources', 'fleet operation'.
Bridge between OMO Prometheus and TKT ticket lifecycle. Generates structured review context for Prometheus after bundle close, converts Prometheus plans into TKT bundle commands, writes review feedback into the Review Agent Inbox, and provides a structured question protocol for gathering information efficiently. Load this skill when you need to: (1) generate a review prompt for a completed ticket/bundle, (2) convert a Prometheus plan.md into TKT worker tickets, (3) write review feedback back into the ticket system, (4) ask structured questions using the question tool across all scenarios (requirements, decisions, review, planning).
Inngest expert for serverless-first background jobs, event-driven workflows, and durable execution without managing queues or workers. Use when: inngest, serverless background job, event-driven wor...