Loading...
Loading...
Found 2,684 Skills
Hypothesis-driven deep research swarm. Spawns specialist sub-agents to investigate a task across codebase patterns, web sources, MCP tools, installed skills, and project dependencies — with evidence grading and adversarial challenge. Activates on: research, investigate, discover, deep research, how should I, what's the best way, explore options, analyze approaches, scout, prior art, feasibility.
Advanced AI agent benchmark scenarios that push Vercel's cutting-edge platform features — Workflow DevKit, AI Gateway, MCP, Chat SDK, Queues, Flags, Sandbox, and multi-agent orchestration. Designed to stress-test skill injection for complex, multi-system builds.
Turn recent work into an engineering retro with shipped work, patterns, and momentum in one place. Use when asked to "weekly retro", "what did we ship", "engineering retrospective", "retro this sprint", or "team retro". Proactively suggest at the end of a work week or sprint. Requires One Horizon MCP.
Expert Coolify management skill for self-hosted infrastructure. Deploy, manage, provision, and debug services, handle environment variables, and automate workflows with or without MCP.
Add Arcjet Guard protection to AI agent tool calls, background jobs, queue workers, and other code paths where there is no HTTP request. Covers rate limiting, prompt injection detection, sensitive information blocking, and custom rules using `@arcjet/guard` (JS/TS) and `arcjet.guard` (Python). Use this skill whenever the user wants to protect tool calls, agent loops, MCP tool handlers, background workers, or any non-HTTP code from abuse — even if they describe it as "rate limit my tool calls," "block prompt injection in my agent," "add security to my MCP server," or "protect my queue worker" without mentioning Arcjet or Guard specifically. Uses the Arcjet CLI (`npx @arcjet/cli` or `brew install arcjet`) for authentication and site/key setup.
Use this skill when a user provides a torrent name or file name and wants to fix recognition issues, or asks to add/manage custom identifiers (自定义识别词). This skill generates identifier rules based on the WordsMatcher preprocessing logic, checks for duplicates against existing rules, and saves them via MCP tools. Because custom identifiers are global, generated rules must default to conservative, sample-specific regex patterns instead of broad matches unless the user explicitly wants global cleanup. Applicable scenarios include: 1) A torrent or file name is incorrectly recognized (wrong title, season, episode, etc.); 2) The user wants to block unwanted keywords from torrent names; 3) The user needs episode offset rules for series with non-standard numbering; 4) The user wants to force recognition of a specific media by TMDB/Douban ID.
Use when the user asks to create a demo video, product walkthrough, feature showcase, animated presentation, marketing video, or GIF from screenshots or scene descriptions. Orchestrates playwright, ffmpeg, and edge-tts MCPs to produce polished video content.
Diagnose landing page → conversion path problems for Google Ads traffic. Separates tracking failures from UX/path failures — the two most commonly confused sources of "low conversion rate." Pulls ad and campaign data via MCP, then reviews landing pages via browser or URL fetch to assess message match, load issues, form friction, and conversion path completeness. Produces a landing-review draft when problems are found.
Decision-grade entity research skill — produces a hypothesis-tested dossier on a specific company, person, nonprofit, or government org, not a generic profile. Forcing intake makes the user state their hypothesis upfront (what they already believe and want to verify or disprove) so the dossier tests it rather than confirms it. Output is an editable Word document (.docx) with verdict on the hypothesis, identity facts, 12-month activity timeline, network signals, reputation signals, red flags, 3-5 conversation hooks tied to specific findings, and source-provenance audit log. Uses WebSearch + WebFetch + free APIs (SEC EDGAR, GitHub, ProPublica Nonprofit Explorer) as workhorses; optional BYOK MCPs (LinkedIn, Crunchbase, Apollo, Pitchbook, SimilarWeb) enhance coverage. Triggers: 'research [company]', 'dossier on [person/company]', 'background check on [entity]', 'prep me for a meeting with [person/company]', 'due diligence on [company]', 'what should I know about [entity]', 'research [person] before I [meet/hire/invest]', 'competitor research on [company]', 'investor diligence [company]', 'interview prep for [company]'. Honors sensitivity exclusions for journalism + personal-vetting contexts.
Draft inbound and outbound RFQ emails for freight quotations. Inbound = a customer asks the forwarder for a quote; outbound = the forwarder asks a carrier or agent for a rate. Uses the practice profile for tone, sign-off, reference format, and lane-specific agent picks. Reads attached threads and dimensions when Gmail or Outlook MCP is connected. TRIGGER: RFQ, quote request, cerere de ofertă, ofertă freight, draft an RFQ, scrie un RFQ, write an RFQ email, email partener, email transportator, trimite la agent, send to carrier, rate request, freight quote email, cotație, request a rate, ask the agent. Also: "scrie un email la agentul din", "draft RFQ to", "cerere ofertă pe lane-ul", "trimite cerere rată la", "email către carrier pentru shipmentul de", "follow up on the quote", "chase the rate".
Search Mobbin for real app UI screenshots and visually analyze them. Required before calling the `search_screens` MCP tool — this skill defines how to plan searches, respond, and build HTML evidence boards when the screens are the answer. Use whenever the user asks about UI/UX design patterns, wants to see how other apps handle a screen or flow, needs design inspiration or references, asks to compare UI approaches across apps, mentions Mobbin, or whenever `search_screens` would be relevant. Trigger aggressively for any design-related question — even if screenshots aren't explicitly requested.
Garbage collection for your Claude Code configuration. Periodically scans ~/.claude (skills, memory, hooks, permissions, MCP servers, caches) for redundant, stale, orphaned, or low-value items, then walks the user through a confirm-each-deletion cleanup. Use when the user says "clean up my config", "config GC", "too many skills", "audit my setup", "my .claude is bloated", or asks for a periodic config review.