Top Agent Skills

DreamLIP: Language-Image Pre-training with Long Captions

Flamingo: A Visual Language Model for Few-Shot Learning

Emu2: Generative Multimodal Models are In-Context Learners

3D-LLM: Injecting the 3D World into Large Language Models

Multimodal Few-Shot Learning with Frozen Language Models

NLVR2: A Visual Reasoning Benchmark for Natural Language

PUA Shot — compact all-in-one PUA reference for explicit injection into sub-agents or short sessions. Strong flavor, same evidence-first behavior.

Preparation guideline for organizing a patent application in Canada with CIPO

Help a user set up Telegram for Dojo Dojo. Default to Personal private bots (recommended). Group setup is advanced for teams/observers/demos.

Preparation guideline for organizing a US provisional patent application with the USPTO

Production-grade Playwright testing toolkit. Use when the user mentions Playwright tests, end-to-end testing, browser automation, fixing flaky tests, test migration, CI/CD testing, or test suites. Generate tests, fix flaky failures, migrate from Cypress/Selenium, sync with TestRail, run on BrowserStack. 55 templates, 3 agents, smart reporting.

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation.

Analyze a problem, plan the fix, execute with verification. Use when tackling a non-trivial bug, feature, or refactor that needs structured approach.

Semantic-search personal knowledge (memory, plans, handoffs, skills, Codex rules) via the local RAG index at ~/.claude/rag-index/. Use when a query is fuzzy or cross-file ("how did we fix X", "what did we decide about Y", "which skill handles Z"). Complements grep (exact) and Serena (code symbols). If the user asks a recall question that doesn't map to a specific known file, reach here first.

spec-ship

Inspect current CI state, identify the first real blocker, separate required failures from noise, and monitor until checks settle. Use when checks are failing, flaky, or blocking a merge.

Git-level WIP safety net. Stashes uncommitted work, tags, and pushes to remote

Onboard a new brand — configure API keys, connect integrations, analyze website, generate brand context files

Bring an existing brand's setup up to date with the latest plugin version — detects gaps since the user last ran brand-setup and fills them interactively.

Daily inbound freelance-job discovery across the markets and platforms the brand chose — scrapes job posts via Claude in Chrome (Freelancer.com API where available), scores each for service fit, deduplicates, and drops matches into a Notion opportunities DB. Runs daily on cron schedule.

Daily customer health scoring across the active book of business. Pulls usage signals from PostHog and subscription state from Stripe, scores each active customer per the brand's customer-success playbook, updates the Notion customer DB, and Slack-alerts on at-risk transitions. Runs daily on cron schedule.

Plan a weekly social media content calendar for any active brand — Static Mode (14 posts across LinkedIn, Facebook, Instagram) or YouTube-First Mode (one weekly video + platform clips), selected by brand.md Content Strategy. Runs weekly on Sunday cron schedule.

Publishing to LinkedIn, Facebook, Instagram, Twitter/X via Zernio for any active brand

Report the brand's organic performance from fb.ai — Search Console clicks/impressions/positions plus AI-engine visibility (whether ChatGPT, Perplexity and friends cite the brand). All traffic-monitor tools are free, so there is no quota gate. Run weekly or monthly.

Turn fb.ai article briefs into published articles — check the destination is connected, price the batch (1.0 quota per article), generate, optionally route through human approval, then publish to the connected CMS/social platform. Also owns the publishing calendar and fb.ai's daily autopilot automations. Run on demand, after seo-researcher.

Daily automated content production — generate copy and images from Notion Social Calendar, publish to Zernio API, update Notion, notify Slack. Runs daily on cron schedule.

Prepare the demo video for a freelance bid — captures a clean screenshot of the gig's published n8n workflow via Claude in Chrome, builds a shot-by-shot recording script pairing the VSL narration with on-screen actions, and hands the founder tool-agnostic recording instructions (Loom/Tella/any recorder). The Demo phase of the Inbound Gig Engine. The founder records the video themselves.

Send personalized cold email sequences via Gmail (self-managed loop), track replies, schedule follow-ups, and route booked meetings to Calendly. Runs daily on cron schedule.

Generate a branded sales proposal from a CRM deal record — packaged as a Gamma deck (or Google Doc fallback) with embedded Stripe payment link, emailed to the prospect via Gmail draft. On-demand per deal.

Build the proof-of-concept automation that backs a freelance bid — turns a drafted gig's solution shape into a real, validated n8n workflow via the n8n Cloud MCP (SDK flow), publishes it, and writes the live workflow URL back onto the gig's Notion row. The Prove phase of the Inbound Gig Engine.

Compose a monthly investor update — pull financials from Xero, MRR/churn from Stripe, product KPIs from PostHog, customer wins from Notion CRM, prior-update context from investors.md. Drafts in founder's voice, redacts per investors.md OMIT rules, packages as a branded Gamma deck (Google Doc fallback), and dispatches a Gmail cover note per investor (or BCC list) linking to the deck. Monthly cron (5th of month for prior month) or on-demand.

Jenkins CLI for controllers. Use when users need to manage jobs, pipelines, config.xml, runs, logs, artifacts, credentials, nodes, or queues in Jenkins. Triggers include "jenkins", "jk", "pipeline", "build", "job create", "job config", "config.xml", "run logs", "jenkins credentials", "jenkins node".

Build and troubleshoot Box integrations for uploads, folders, folder listings, downloads and previews, shared links, collaborations, search, metadata, event-driven automations, and Box AI retrieval flows. Use when Codex needs to add Box APIs or SDKs to an app, wire Box-backed document workflows, organize or share content, react to new files, or fetch Box content for search, summarization, extraction, or question-answering.

Search Hex projects and ask Hex Threads questions. Use when the user explicitly references Hex, Hex projects, Hex dashboards, Hex data apps, Hex Threads, or asks to search an existing Hex workspace asset.

Use before writing any implementation code — enforces RED-GREEN-REFACTOR cycle.

Initialize team config for a project. Creates .agenteam/config.yaml (or legacy agenteam.yaml) and generates .codex/agents/*.toml.

Use when a val sends email, receives email, or is triggered by an incoming email. Covers email-type vals (the Email handler shape, attachment limits, the assigned val email address) and sending mail via std/email.

Use when a val needs to require login with a Val Town account — gating routes behind authentication, identifying the current user, building user-specific dashboards. Covers std/oauth's `oauthMiddleware` and `getOAuthUserData`, the auto-managed `/auth/*` routes, and session behavior. For third-party OAuth providers (Google, GitHub, etc.) see the `third-party-integrations` skill instead.

Manage Gmail inbox triage, mailbox search, thread summaries, action extraction, reply drafting, and email forwarding through connected Gmail data. Use when the user wants to inspect a mailbox or thread, search email with Gmail query syntax, summarize messages, extract decisions and follow-ups, prepare replies or forwarded messages, or organize messages with explicit confirmation before send, archive, delete, or label actions.

Use when the user wants to use the UCP CLI to find, compare, buy, or track products from online merchants, or to set up and troubleshoot the local UCP profile required for merchant-scoped operations. Covers global catalog search ("find me X under $Y"), named-merchant transactions ("buy this from Z.com"), order tracking, `ucp profile init`, `ucp doctor`, carts, checkout, orders, and UCP setup/help. Falls back to merchant-hosted handoff when direct in-protocol checkout isn't available.

Build and review Wix CLI app extensions — dashboard pages, modals, plugins, menu plugins, custom element widgets, Editor React components, site plugins, embedded scripts, backend APIs, backend events, service plugins, data collections, and App Market readiness. Use when building ANY feature or extension for a Wix CLI app or preparing a Wix app for App Market review. Triggers on: add, build, create, implement, help me, dashboard, widget, plugin, backend, API, event, collection, embedded script, service plugin, Editor React component, checkout, shipping, tax, discount, SPI, CMS, schema, tracking, popup, admin panel, menu item, modal, validate, test, verify, register extension, App Market, app review, submission readiness.

Use after design approval for milestone plans with executable acceptance.

Use when all plan tasks are done and green to review, archive planning artifacts, and ask how to finish.

AI-native publishing system: autonomous multi-phase workflows from ideation to export. Fiction, non-fiction, and technical books. Trigger: /velith or book-related requests.

Use when comparing products.

Register a deferred decision in the debt registry. Trigger by judgment, not a marker scan, whenever a future reader would ask "why this way?": an unmade decision, stub, loosened type, bypassed check, swallowed error, a default picked "for now", or a TODO/FIXME/HACK/XXX marker. Trigger immediately whenever you defer work, or when the user invokes $add. Over-register freely; the developer drops with "drop A", "drop A,C", or "drop all".

Use for bugs, unexpected behavior, regressions, or failing tests you did not write.

Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.

Vercel AI SDK expert guidance. Use when building AI-powered features — chat interfaces, text generation, structured output, tool calling, agents, MCP integration, streaming, embeddings, reranking, image generation, or working with any LLM provider.

Use when calling REST APIs.

Show available Archcore commands and how to use them. Use when onboarding, exploring what skills are available, or when you're not sure which command to run.

Quick project status report synthesized from state files, artifacts, and git activity. No agent dispatch (<2s).

Comprehensive SEO analysis for any website or business type. Full site audits, single-page analysis, technical SEO (crawlability, indexability, Core Web Vitals with INP), schema markup, content quality (E-E-A-T), image optimization, sitemap analysis, and GEO for AI Overviews/ChatGPT/Perplexity. Industry detection for SaaS, e-commerce, local, publishers, agencies. Triggers on: SEO, audit, schema, Core Web Vitals, sitemap, E-E-A-T, AI Overviews, GEO, technical SEO, content quality, page speed, structured data.

Use for standard or complex new work before coding or planning. Also handles vague goals — clarifies before designing.

Use when building any val with a user interface — dashboards, web apps, landing pages, forms, admin tools, anything users see in a browser. Covers JSX/React conventions, Twind/Tailwind styling, React version pinning, the view-source link requirement, and what to avoid (template-string HTML, external assets).

Wix business solution management recipes — REST API operations for configuring and managing Wix business solutions. Routes to: stores, bookings, get-paid, CMS, contacts, forms, media, app-installation, pricing-plans, restaurants, rich-content, sites, blog, calendar, domains, site-properties, ecommerce.

Full specialist analysis via parallel agent dispatch. Researcher, Architect, and PM produce a prioritized report of what to build next (30-60s).

Regenerate .codex/agents/*.toml from agenteam.yaml and plugin defaults.

Use when the user asks to release, version, tag, or publish.

Use when creating a new val and choosing which starter to fork. Covers the catalog of official starter templates, which project shape each one fits, and when forking an existing val is the better starting point.