Skills directory

When the user wants to create or update their product marketing context document. Also use when the user mentions 'product context,' 'marketing context,' 'set up context,' 'positioning,' 'who is my target audience,' 'describe my product,' '

Find and label every LLM workflow in the repository so Caveman Cloud groups spend by workflow instead of one bucket. Use for "discover workflows" or breaking LLM spend down by workflow.

Use this skill when writing app code with InsForge or @insforge/sdk: database CRUD, auth, storage uploads/storage RLS, functions, OpenRouter AI, realtime, emails, Stripe or Razorpay payments, or pointing S3-compatible tooling (aws CLI, AWS

Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why

Use this skill whenever someone needs a backend, or a task touches InsForge backend or cloud infrastructure through the InsForge CLI: projects, SQL, migrations, RLS policies, functions, storage, backups, deployments, compute, secrets, confi

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complex

Build, debug, or review Cloudflare Agents SDK applications using the agents package.

Google Sheets: Read and write spreadsheets.

When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, or Facebook, or wants to do social listening and engagement triage. Also use when the user mentions 'LinkedIn post

Verify whether an image or video is authentic, original and correctly captioned — provenance checks, error level analysis, noise and JPEG compression analysis, clone and copy-move detection, lighting and shadow consistency, C2PA Content Cre

Investigator OPSEC — threat-model who might notice you, control your attribution surface across IP, ASN, browser and TLS fingerprint, timing and logged-in accounts, separate research identity from real identity, build and age a sockpuppet r

Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.

Delivers changes incrementally in thin, verifiable slices. Use when implementing any feature or change that touches more than one file, or when picking up the next task from a plan. Use when rolling a change out behind a feature flag, when

Generate and edit images with OpenAI GPT Image 2 (ChatGPT Images 2.0) on RunComfy. Documents GPT Image 2's strengths (embedded text, logos, multilingual typography, instruction precision), its 3 fixed sizes, edit-with-preservation language,

Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modif

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".

Read and write Google Docs.

Check and interpret data-breach exposure for an email, username, phone or name using Have I Been Pwned, the Pwned Passwords k-anonymity range API, DeHashed, IntelX and Snusbase. Use when checking breach or leak exposure, finding which servi

When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implemen

Search Remotion documentation

Build a complete non-photoreal narrated explainer or story video from ordered 10-second blocks: one narrator, one universal style key, one Seed Audio take and one Gemini Omni clip per block, then server-side assembly with explainer_video. U

When the user wants to find co-marketing partners, plan joint campaigns, or brainstorm partnership opportunities. Use when the user says 'co-marketing,' 'partner marketing,' 'joint campaign,' 'who should we partner with,' 'integration marke

Reverse image search across Yandex, Google Lens, Bing Visual Search, TinEye and Baidu to find where a picture came from and who published it first. Use when reverse image searching, identifying a photo, face, logo, product, uniform or build

Index and search code repositories, documentation, research papers, HuggingFace datasets, local folders, Slack workspaces, Google Drive, X (Twitter), and packages with Nia AI. Includes auth bootstrapping, Oracle autonomous research, GitHub

When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ROAS,' 'CPA,' 'ad campaign,' 'retargeting,'

Implement the result of /to-spec and /to-tickets in code.

Teaches agents to iteratively build websites using Stitch with an autonomous baton-passing loop pattern

Set up Clerk authentication in any project with the Clerk CLI and official framework quickstarts. Use when adding Clerk, initializing Clerk, scaffolding a new app with Clerk, or migrating an existing authentication system to Clerk.

Read-only repository explorer for cold-start orientation, broad cross-file localization, or when a direct search failed. Skip it when the exact file or symbol is already named. Returns path:line citations only; its reads stay out of main co

Use when diagnosing problems in an InsForge project — reactive failures (SDK error object, HTTP 4xx/5xx, gateway timeout 502/503/504, edge function failure or timeout, login/OAuth/auth errors, RLS denial, realtime channel issues, slow query

Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation. Use when asked to inspect or evaluate a Caveman optimization report. Needs explicit approval.

Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned. Use when asked to lower an agent's token cost, what caveman has saved, to trim a heavy CLA

Guide to Sonner, the React toast library — install and wire up the Toaster, pick the right toast() call, promise and loading toasts, updating, dismissing and persisting toasts, styling, theming and icons, positioning and multiple toasters.

Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.

Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing evidence-ranked hypotheses.

When the user wants to design, construct, or improve an offer — the thing they actually sell — including value framing, bonus stacking, guarantee design, scarcity/urgency, naming, and payment structure. Also use when the user mentions 'offe

Interacting with Mediabunny

Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.

Use when wiring an external auth provider (Clerk, Auth0, WorkOS, Kinde, Stytch, Better Auth) into InsForge for JWT-based RLS, or when adding the OKX x402 payment facilitator for onchain pay-per-use billing.

Build an animation from scratch, making the decisions in the order that determines whether it feels right — should it animate at all, what purpose, which tool, which properties, which curve and duration, how it interrupts, how it exits. Wri

Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.

Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings. Use when asked what Caveman found or where LLM spend goes.

Custom authentication flows and component appearance - hooks (useSignIn, useSignUp), themes, colors, fonts, CSS. Use for custom sign-in/sign-up flows, appearance styling, visual customization, branding.

Set up, repair, or migrate to Cloudflare Turnstile bot verification in an existing frontend and backend, including server-side Siteverify.

Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so the session stays logged in between runs

Verify that browser profiles are actually isolated from one another instead of assuming it - confirm each profile's timezone agrees with its own exit IP, that WebRTC exposes only the proxy, that canvas and WebGL hashes stay identical across

Remotion Map animation knowledge

Implement or troubleshoot Cloudflare Email Sending and Email Routing integrations and their delivery configuration.

编辑中文文章、评论和文档中的空话、重复及模板化表达，让文字更自然，同时保留事实、确定程度和作者声音。适用于润色已有文本，不用于判断作者身份或保证通过 AI 检测器。