--- title: Best Action-Taking Skills slug: best-action-taking-skills type: collection canonical: https://top-agent-skills.com/collections/best-action-taking-skills skills: 62 rubric: 1.0 updated: 2026-09-30 --- # Best Action-Taking Skills 62 Skills perform real side effects — firebase-hosting deploys, playwright-cli drives a browser, stripe-projects touches payment objects, resend-email sends mail that reaches actual inboxes. Read this page as a risk register as much as a ranking: every entry here can change state outside your machine, most need an API key with real scope, and the ones marked as requiring an MCP server will do nothing at all until that server is configured. 62 Skills, ranked by composite score (https://top-agent-skills.com/about/methodology). ## The picks ### 1. hostinger-api-mcp-skills — score 63/100 (verified-org) The jobs, not the endpoints: migrate a live site, connect the domain, keep WordPress patched. - Best for: Moving an existing site onto Hostinger and running it afterwards — migration, custom domain with SSL, WordPress updates, and an account-wide health audit. - Not ideal for: Anyone not on Hostinger, and anyone wanting a reference for the raw API — these skills drive the MCP server toward an outcome; hostinger-agent-skills is the endpoint-level knowledge base. - Publisher: Hostinger · MIT - Verified on: claude-code, codex ```bash npx skills add hostinger/api-mcp-server --skill deploy-to-hosting --yes ``` Full entry: https://top-agent-skills.com/skill/hostinger-api-mcp-skills (https://top-agent-skills.com/skill/hostinger-api-mcp-skills.md) ### 2. firebase-hosting-basics — score 61/100 (verified-org) Firebase-authored. Init, configure, and one-step deploy to Firebase Hosting / App Hosting. - Best for: Web apps already in the Google/Firebase ecosystem (Firestore, Auth) that want the agent to handle hosting setup and the deploy step without leaving chat. - Not ideal for: Static-only sites with no Firebase dependency — a generic static host (Pages, Netlify) is simpler and avoids the Firebase project requirement. - Publisher: Firebase (Google) · Apache-2.0 - Verified on: claude-code, cursor, codex, gemini-cli, antigravity ```bash claude plugin marketplace add firebase/agent-skills ``` Full entry: https://top-agent-skills.com/skill/firebase-hosting (https://top-agent-skills.com/skill/firebase-hosting.md) ### 3. playwright-cli — score 60/100 (verified-org) Microsoft's first-party Playwright skill, invoked through the CLI — the reference implementation for driving a real browser, with no credentials required. - Best for: Driving a real browser from the agent and working with an existing Playwright suite — navigation, assertions, tracing, video, request mocking, and test generation. - Not ideal for: Hosted scraping at scale. It drives a local browser, so rate limiting and anti-bot handling are your problem — reach for a hosted extraction skill when the target fights back. - Publisher: Microsoft · Apache-2.0 - Verified on: claude-code ```bash playwright-cli install --skills ``` Full entry: https://top-agent-skills.com/skill/playwright-cli (https://top-agent-skills.com/skill/playwright-cli.md) ### 4. stripe-projects — score 59/100 (verified-org) Provision a Postgres, Redis, auth, or LLM provider through the Stripe Projects catalog rather than signing up by hand. - Best for: Letting an agent provision and wire up cloud services (DB, cache, auth, email, model providers) with credentials returned inline. - Not ideal for: Teams that must provision through their own IaC (Terraform, Pulumi) or a locked-down cloud account. - Publisher: Stripe · MIT - Verified on: claude-code, cursor, gemini-cli ```bash /plugin marketplace add stripe/ai ``` Full entry: https://top-agent-skills.com/skill/stripe-projects (https://top-agent-skills.com/skill/stripe-projects.md) ### 5. resend — score 59/100 (verified-org) Resend's own API skill: send transactional and batch email, handle inbound webhooks, and manage domains, templates, and keys. - Best for: Wiring Resend into an app — transactional sends, batch sends, inbound webhook handling, and domain/template/key management. - Not ideal for: Non-Resend providers (SendGrid, Postmark, SES) — the SDK calls and webhook signatures are Resend-specific. - Publisher: Resend · MIT - Verified on: claude-code, cursor, codex ```bash npx skills add resend/resend-skills ``` Full entry: https://top-agent-skills.com/skill/resend-email (https://top-agent-skills.com/skill/resend-email.md) ### 6. agent-email-inbox — score 59/100 (verified-org) Give an agent a webhook-driven inbox with the sender-allowlist and content-filtering patterns that block prompt injection from inbound email. Full entry: https://top-agent-skills.com/skill/agent-email-inbox (https://top-agent-skills.com/skill/agent-email-inbox.md) ### 7. zeabur-agent-skills — score 59/100 (verified-org) Deploy and register the domain in the same session — Zeabur is its own registrar, so both are one CLI. Full entry: https://top-agent-skills.com/skill/zeabur-agent-skills (https://top-agent-skills.com/skill/zeabur-agent-skills.md) ### 8. browser — score 58/100 (verified-org) Local browser with no credentials, or a hosted Browserbase session with CAPTCHA solving and residential proxies when the target is protected. Full entry: https://top-agent-skills.com/skill/browserbase-browser (https://top-agent-skills.com/skill/browserbase-browser.md) ### 9. ui-test — score 58/100 (verified-org) Diff-aware adversarial QA: it reads the git diff and tests only what changed, across correctness, accessibility, layout and UX. Full entry: https://top-agent-skills.com/skill/browserbase-ui-test (https://top-agent-skills.com/skill/browserbase-ui-test.md) ### 10. stripe-directory — score 57/100 (verified-org) Find vendors and partners for a job-to-be-done — and, where supported, let the agent purchase and consume the service. Full entry: https://top-agent-skills.com/skill/stripe-directory (https://top-agent-skills.com/skill/stripe-directory.md) ### 11. create-payment-credential — score 57/100 (verified-org) Stripe's answer to agentic checkout: one-time payment credentials so an agent can buy without ever seeing the underlying card. Full entry: https://top-agent-skills.com/skill/stripe-link-checkout (https://top-agent-skills.com/skill/stripe-link-checkout.md) ### 12. chrome-devtools — score 57/100 (verified-org) Chrome's own team, giving agents the DevTools protocol: drive it, inspect it, debug it. Full entry: https://top-agent-skills.com/skill/chrome-devtools (https://top-agent-skills.com/skill/chrome-devtools.md) ### 13. dbhub — score 56/100 (verified-org) One skill across Postgres, MySQL, SQL Server, MariaDB and SQLite — and its actual job is forcing explore-before-query on real schemas. Full entry: https://top-agent-skills.com/skill/dbhub (https://top-agent-skills.com/skill/dbhub.md) ### 14. azure-ai-contentunderstanding-py — score 56/100 (verified-org) Multimodal extraction across documents, images, audio and video through one Azure client — Microsoft-authored, with an explicit trigger list. Full entry: https://top-agent-skills.com/skill/azure-content-understanding (https://top-agent-skills.com/skill/azure-content-understanding.md) ### 15. azure-ai-translation-document-py — score 56/100 (verified-org) Batch document translation that preserves layout — the part that breaks when you translate a PDF by extracting text and re-flowing it. Full entry: https://top-agent-skills.com/skill/azure-document-translation (https://top-agent-skills.com/skill/azure-document-translation.md) ### 16. text-to-speech — score 56/100 (verified-org) Vendor-official voiceover generation across 70+ languages, from the company that defined the category. Ships with evals, which almost no skill does. Full entry: https://top-agent-skills.com/skill/elevenlabs-text-to-speech (https://top-agent-skills.com/skill/elevenlabs-text-to-speech.md) ### 17. speech-to-text — score 56/100 (verified-org) Transcription and subtitle generation as a first-class skill — the media job agents are asked for most and could not previously do well. Full entry: https://top-agent-skills.com/skill/elevenlabs-speech-to-text (https://top-agent-skills.com/skill/elevenlabs-speech-to-text.md) ### 18. dubbing — score 56/100 (verified-org) Localise video while keeping the original speaker's voice — and correct the transcript before regenerating, rather than accepting the first pass. Full entry: https://top-agent-skills.com/skill/elevenlabs-dubbing (https://top-agent-skills.com/skill/elevenlabs-dubbing.md) ### 19. hostinger-agent-skills — score 56/100 (verified-org) The registrar half of the stack: buy the domain, set the DNS, stand up the site — from one plugin. Full entry: https://top-agent-skills.com/skill/hostinger-agent-skills (https://top-agent-skills.com/skill/hostinger-agent-skills.md) ### 20. composio — score 55/100 (verified-org) 1,000+ SaaS integrations as one skill. OAuth lifecycle, scoped credentials, structured actions. Full entry: https://top-agent-skills.com/skill/composio (https://top-agent-skills.com/skill/composio.md) ### 21. dodo-payments-skills — score 54/100 (verified-org) The deepest MoR skill coverage after Stripe: 17 skills from checkout to go-live. Full entry: https://top-agent-skills.com/skill/dodo-payments-skills (https://top-agent-skills.com/skill/dodo-payments-skills.md) ### 22. loops-skills — score 54/100 (verified-org) SaaS email as skills: Loops API, CLI, LMX markup, deliverability practice. Full entry: https://top-agent-skills.com/skill/loops-skills (https://top-agent-skills.com/skill/loops-skills.md) ### 23. paddle-agent-skills — score 53/100 (verified-org) Paddle's own integration playbook: ten skills for Checkout, webhooks, pricing pages, and subscription lifecycle on the merchant-of-record platform. Full entry: https://top-agent-skills.com/skill/paddle-agent-skills (https://top-agent-skills.com/skill/paddle-agent-skills.md) ### 24. box — score 53/100 (verified-org) Box as an agent surface, plus the contract-review workflows nothing else in the catalog covers. Full entry: https://top-agent-skills.com/skill/box-for-ai (https://top-agent-skills.com/skill/box-for-ai.md) ### 25. use-runway-api — score 53/100 (verified-org) Generative video from the vendor developers name first, as a skill set rather than an SDK crawl. Full entry: https://top-agent-skills.com/skill/runway-api (https://top-agent-skills.com/skill/runway-api.md) ### 26. hubspot-agent-skills — score 52/100 (verified-org) First-party HubSpot CRM operations for agents: lookups, deals, quote-to-cash, reporting. Full entry: https://top-agent-skills.com/skill/hubspot-agent-skills (https://top-agent-skills.com/skill/hubspot-agent-skills.md) ### 27. gtm-eng-skills — score 52/100 (verified-org) Waterfall enrichment as a procedure, not a single provider call. Full entry: https://top-agent-skills.com/skill/gtm-eng-skills (https://top-agent-skills.com/skill/gtm-eng-skills.md) ### 28. stripe-payments — score 51/100 (verified-org) Stripe done right. Checkout, subscriptions, webhooks, idempotency, metered billing. Full entry: https://top-agent-skills.com/skill/stripe-payments (https://top-agent-skills.com/skill/stripe-payments.md) ### 29. shopify-storefront — score 51/100 (verified-org) Shopify Storefront API: cart, checkout, metafields, customer accounts, Hydrogen patterns. Full entry: https://top-agent-skills.com/skill/shopify-storefront (https://top-agent-skills.com/skill/shopify-storefront.md) ### 30. railway-skills — score 51/100 (verified-org) All of Railway in one skill: provision, deploy, debug — listed in the official plugin marketplace. Full entry: https://top-agent-skills.com/skill/railway-skills (https://top-agent-skills.com/skill/railway-skills.md) ### 31. webapp-testing — score 50/100 (official-anthropic) Test local webapps with Playwright. Generation, run, report — end-to-end. Full entry: https://top-agent-skills.com/skill/webapp-testing (https://top-agent-skills.com/skill/webapp-testing.md) ### 32. semgrep — score 50/100 (verified-org) Semgrep's own scanning skill: run the industry-standard SAST engine across 30+ languages, and author custom rules for your codebase's patterns. Full entry: https://top-agent-skills.com/skill/semgrep-scan (https://top-agent-skills.com/skill/semgrep-scan.md) ### 33. scan-secrets — score 50/100 (verified-org) GitGuardian's own secret-detection skill — scans history, images and packages, and ships a written remediation doctrine rather than just a list of hits. Full entry: https://top-agent-skills.com/skill/gitguardian-secret-scanning (https://top-agent-skills.com/skill/gitguardian-secret-scanning.md) ### 34. postmark-skills — score 50/100 (verified-org) Transactional email the Postmark way: send, inbound, templates, webhooks. Full entry: https://top-agent-skills.com/skill/postmark-skills (https://top-agent-skills.com/skill/postmark-skills.md) ### 35. verify — score 50/100 (official-anthropic) Real feature verification — run the app, drive it, prove it works. Full entry: https://top-agent-skills.com/skill/verify (https://top-agent-skills.com/skill/verify.md) ### 36. firecrawl — score 49/100 (verified-org) Web scraping, search, and browser automation built to be agent-friendly. Full entry: https://top-agent-skills.com/skill/firecrawl (https://top-agent-skills.com/skill/firecrawl.md) ### 37. notion-api-skill — score 49/100 (verified-org) Notion API: page/database CRUD, block hierarchies, rich text, schema sync. Full entry: https://top-agent-skills.com/skill/notion-api-skill (https://top-agent-skills.com/skill/notion-api-skill.md) ### 38. vercel-deploy-claimable — score 49/100 (verified-org) Ship to a live Vercel URL from chat — auto-detects the framework, returns a claim link. Full entry: https://top-agent-skills.com/skill/vercel-deploy-claimable (https://top-agent-skills.com/skill/vercel-deploy-claimable.md) ### 39. weaviate — score 49/100 (verified-org) The vector-database skill that ships executable scripts rather than prose — the agent runs the query instead of describing it. Full entry: https://top-agent-skills.com/skill/weaviate-skill (https://top-agent-skills.com/skill/weaviate-skill.md) ### 40. norman-finance — score 49/100 (verified-org) The ledger, not the checkout: categorise, reconcile, invoice, file. Full entry: https://top-agent-skills.com/skill/norman-finance (https://top-agent-skills.com/skill/norman-finance.md) ### 41. shannon — score 48/100 (verified-org) Real exploits, no false positives. 96.15% exploit success across 50+ vuln types. Full entry: https://top-agent-skills.com/skill/shannon (https://top-agent-skills.com/skill/shannon.md) ### 42. snyk-fix — score 48/100 (verified-org) The remediation half of security work: scan, fix, validate the fix, open the PR. Batch mode handles a whole backlog of CVEs in one pass. Full entry: https://top-agent-skills.com/skill/snyk-fix (https://top-agent-skills.com/skill/snyk-fix.md) ### 43. brightdata — score 48/100 (verified-org) The anti-bot problem, handled: proxies, SERP, and structured extraction at scale. Full entry: https://top-agent-skills.com/skill/brightdata-skills (https://top-agent-skills.com/skill/brightdata-skills.md) ### 44. zotero-skills — score 48/100 (community) Programmatic access to the reference manager academia actually uses. Full entry: https://top-agent-skills.com/skill/zotero-skills (https://top-agent-skills.com/skill/zotero-skills.md) ### 45. run — score 48/100 (official-anthropic) One-command app launch tailored to your project type. Full entry: https://top-agent-skills.com/skill/run (https://top-agent-skills.com/skill/run.md) ### 46. loop — score 48/100 (official-anthropic) Recurring task runner. Self-paced or interval-based. Full entry: https://top-agent-skills.com/skill/loop (https://top-agent-skills.com/skill/loop.md) ### 47. schedule — score 48/100 (official-anthropic) Cron for remote Claude Code agents. Set it and forget it. Full entry: https://top-agent-skills.com/skill/schedule (https://top-agent-skills.com/skill/schedule.md) ### 48. agent-browser — score 47/100 (verified-org) Deterministic web control. ref-based clicks/fills, no flaky selectors, parallel sessions. Full entry: https://top-agent-skills.com/skill/agent-browser (https://top-agent-skills.com/skill/agent-browser.md) ### 49. claude-healthcare — score 47/100 (official-anthropic) FHIR to prior-auth to ICD-10 coding: the official payer/provider/pharma toolkit. Full entry: https://top-agent-skills.com/skill/claude-healthcare (https://top-agent-skills.com/skill/claude-healthcare.md) ### 50. paypal-ai-toolkit — score 47/100 (verified-org) The largest payment processor, first-party: checkout to disputes to payouts. Full entry: https://top-agent-skills.com/skill/paypal-ai-toolkit (https://top-agent-skills.com/skill/paypal-ai-toolkit.md) ### 51. netlify-deploy — score 46/100 (verified-org) Netlify-authored deploy flow. Auth, site linking, Deploy Previews, production promotes. Full entry: https://top-agent-skills.com/skill/netlify-deploy (https://top-agent-skills.com/skill/netlify-deploy.md) ### 52. cloudflare — score 46/100 (verified-org) Cloudflare-authored. Workers and Pages deploys, Wrangler config, KV/D1/R2 from chat. Full entry: https://top-agent-skills.com/skill/cloudflare-platform (https://top-agent-skills.com/skill/cloudflare-platform.md) ### 53. canva — score 46/100 (verified-org) Brand-checked design output at volume — the production half of design work. Full entry: https://top-agent-skills.com/skill/canva-skills (https://top-agent-skills.com/skill/canva-skills.md) ### 54. github-pages — score 45/100 (community) Repo-to-live-URL on GitHub Pages: Actions workflow, custom domain, Jekyll, troubleshoot. Full entry: https://top-agent-skills.com/skill/github-pages-deploy (https://top-agent-skills.com/skill/github-pages-deploy.md) ### 55. apify — score 45/100 (verified-org) Run the marketplace's scrapers, or turn your own scraper into a deployable Actor. Full entry: https://top-agent-skills.com/skill/apify-skills (https://top-agent-skills.com/skill/apify-skills.md) ### 56. render-deploy — score 44/100 (verified-org) Deploy, debug, and scale on Render: Blueprint generation with validation built in. Full entry: https://top-agent-skills.com/skill/render-deploy (https://top-agent-skills.com/skill/render-deploy.md) ### 57. browser-use — score 43/100 (community) Headless browser as an agent tool. Navigate JS-heavy pages, fill forms, extract content. Full entry: https://top-agent-skills.com/skill/browser-use (https://top-agent-skills.com/skill/browser-use.md) ### 58. hubspot-admin-skills — score 42/100 (community) A HubSpot admin in a plugin: audits, dedup, scoring, lifecycle hygiene — 37 skills deep. Full entry: https://top-agent-skills.com/skill/hubspot-admin-skills (https://top-agent-skills.com/skill/hubspot-admin-skills.md) ### 59. ios-simulator-skill — score 41/100 (community) Drive the iOS Simulator from the agent loop. Build and test iOS apps. Full entry: https://top-agent-skills.com/skill/ios-simulator-skill (https://top-agent-skills.com/skill/ios-simulator-skill.md) ### 60. playwright-skill — score 40/100 (community) Playwright patterns: clicks, fills, waits, retries. The do-it-right defaults. Full entry: https://top-agent-skills.com/skill/playwright-skill (https://top-agent-skills.com/skill/playwright-skill.md) ### 61. ffuf-web-fuzzing — score 36/100 (community) ffuf web fuzzing for authorized pentests. Common modes, payloads, and gotchas. Full entry: https://top-agent-skills.com/skill/ffuf-web-fuzzing (https://top-agent-skills.com/skill/ffuf-web-fuzzing.md) ### 62. lemonsqueezy-claude-skills — score 36/100 (community) Operate a Lemon Squeezy store from the agent: customer lookup, refunds, discount codes, receipts, and a sales dashboard — six support-and-revops skills. Full entry: https://top-agent-skills.com/skill/lemonsqueezy-skills (https://top-agent-skills.com/skill/lemonsqueezy-skills.md) --- _Top Agent Skills. Machine-readable twin of https://top-agent-skills.com/collections/best-action-taking-skills._