Claude Skills by naveedharri

Iterative newsletter writing workflow for Ben Van Sprundel's audience. Use when Ben wants to write a newsletter from research, an insight, an idea, or a YouTube video transcript. This is a CREATIVE, STEP-BY-STEP process. Never output a complete newsletter immediately. Each step requires suggestions, user decision, then progression to next step. Pairs with /research upstream and /image downstream. Triggers: newsletter, write newsletter, email content, repurpose video, insight to newsletter.

Run deep, internet-enabled research on any topic to gather the raw material for content. First step of the content pipeline that feeds /linkedin and /newsletter. Automates prompt enhancement through clarifying questions, saves parameters for reproducibility, and executes web-enabled deep research via the OpenAI Deep Research API. Use when the user asks to research a topic, gather sources, investigate a subject, or build the foundation for a post or newsletter.

Generate on-brand visuals and infographics for LinkedIn posts and newsletters using Nano Banana MCP (Gemini AI image generation). Final step of the content pipeline. Follows a guided flow: analyze the content, suggest visualizable concepts, propose visualization approaches, then generate on-brand visuals. USE THIS SKILL WHEN user says \"create a visual\", \"make a visual\", \"generate an infographic\", or wants a graphic to go with a post or newsletter.

Puts a running Open WebUI or Odysseus on a shareable public URL through an ngrok tunnel, so a teammate can sign in and use the local models without installing anything. Use when the user says "share Open WebUI with my team", "share Odysseus with my team", "let my colleague use my local AI", "expose Open WebUI", "share localhost:8080", "share localhost:7860", "give someone access to my models", "set up an ngrok tunnel", "make my local AI reachable from another machine", or asks how to let some...

Installs and wires up Open WebUI end to end, so a non-technical user gets a working local AI chat in the browser instead of setup instructions. Use when the user says "install Open WebUI", "set up Open WebUI", "get Open WebUI running", "connect Open WebUI to Ollama", "Open WebUI shows no models", "localhost:8080 refused to connect", "does not support tools", or asks for help finishing a local AI setup. Installs Ollama if missing, pulls a model that fits, starts the server, connects them, and ...

The one command that takes someone from nothing to a working local AI setup: scans their machine, asks what they want it for, recommends a model and an app, asks Open WebUI or Odysseus when the pick is browser-based, then installs it with their approval. Use when the user says \"set up local AI\", \"help me run AI on my own computer\", \"I want to run AI locally\", \"get me started with local LLMs\", \"run AI offline\", \"private AI on my machine\", \"local AI setup\", or asks how to start wi...

Asks a few plain questions about the work, then names the one desktop app to run local AI models in, from LM Studio, Goose, Open WebUI, AnythingLLM, OpenWork or Odysseus. Use when the user asks "which app should I use for local AI", "LM Studio or Ollama", "what is the best local AI interface", "do I need Open WebUI", "Open WebUI or Odysseus", "which one supports MCP", "which supports skills", "pick a harness for me", or is comparing local AI desktop apps. Names one tool and states what it can...

Runs an open model in the cloud two ways, and makes the user choose with real numbers. Route A is OVHcloud AI Endpoints, an EU-owned per-token API with zero idle cost, for spiky usage and EU jurisdiction. Route B rents one single-tenant RunPod GPU pod in a region the user picks, serving the model on vLLM behind a generated API key, with Open WebUI behind its own login and a URL Claude Code can use directly, for sustained use, unlisted models, or single tenancy. Use when the user says "rent a ...

Scans the user's actual hardware and tells them exactly which local AI models they can run, by name, with expected speed. Use when the user asks "what models can my computer run", "can I run a local LLM", "how much VRAM do I have", "which model should I download", "is my Mac good enough for local AI", "scan my machine", or shares hardware specs and asks what fits. Reads real memory and GPU rather than asking the user to know their own specs. Never installs anything. Requires Claude Code with ...

Build Anthropic Managed Agents through a non-technical conversation. The skill asks the user what kind of agent they want, which connectors and abilities it should have, and then silently translates that into Anthropic's Managed Agents REST API: creates the Agent, Environment, Vault and credentials, attaches MCP servers and Skills, opens a Session, and sends a first message. Hides the developer details. USE THIS SKILL WHEN user says \"agent builder\", \"build an agent\", \"create an agent\", ...

Build a BenAI-branded HTML page in the neo-brutalist instant-ui design language (cream background, near-black ink, 3px hard borders, 6px zero-blur shadows, a blue/green/amber gradient stripe, system font plus SF Mono, weight-900 headings). Use for any BenAI landing page, offer, sales, or pricing page, onboarding or intake form, partner page, case study, playbook, toolkit, or internal doc that must look like it came off the same line as the BenAI Champion Offer assets. Reproduces that visual l...

Build an image-first social carousel from an asset already filed in the Marketing OS, export it as a PDF, and record it back as a real channel asset. Brand palette, typography, the logo pointer and the never-black-background rule all resolve from Context/brand/brand-kit.md. Source is a filed newsletter edition, published pillar asset, or pipeline brief, so it provably says what the parent said. Fans out parallel readers over the OS before planning, renders every slide with Higgsfield, QAs eve...

Build, rebuild, and deploy the Marketing OS control center: a self-contained single-page dashboard rendered from the OS files, eleven pages in six nav groups (Core, Calendar, Content, Campaigns, Funnel, Performance, Learnings, Audience, Intelligence, Team, System). Interviews the user on first build to decide which pages earn a place, then reads the OS, assembles one inline JSON data block, swaps it into the fixed page shell, verifies the page opens with no external requests, deploys to a liv...

Run a market intelligence brief against the Marketing OS, score every find, and turn the ones that clear the bar into scored ideas in the backlog. The watchlist, competitor roster, lookback window and connectors all come from the OS, and what counts as a signal comes from the positioning file, so the brief reports the translation gap rather than generic AI news. Fans out one agent per stream in a single batch across official sources, practitioners, the competitor roster, search demand and the...

Write a newsletter edition from the Marketing OS, gated step by step, then file it as a real asset. Reads the ICP, voice register, offer and live price, measured patterns and swipe file from the OS, never from bundled copies. Sources from a pillar asset, the values doc, a community post or a raw idea. Fans out five parallel readers over the OS before the first gate, and verifies the draft with independent agents against the voice register and offer facts. Seven gates with options at each; the...

Answer an open question the Marketing OS already wrote down, then promote it to a finding. Takes its queue from the OS itself: files with status open-question in Intelligence/research/, open questions and untested beliefs in Analytics/what-works.md, and ideas with no established pain. Fans out one agent per stream in a single batch across papers, forums, the web and creators, with an effort floor, distinct sources and full-text reads, fact-checks every hard claim with a verifier prompted to r...

Create and manage the Marketing OS routines as scheduled tasks: ten of them in two groups: five operating routines (morning performance sweep, content pipeline sync, campaign sync, dashboard, monthly report) and five intelligence and review routines (market scan, customer intel, competitor radar, pipeline hygiene, quarterly report). Probes every connector first and reports exactly what each routine loses without it, so nothing gets scheduled against a dead integration. Gives the operator the ...

Set up a Marketing OS: a markdown second brain that becomes the single source of truth every marketing skill reads, plus the routines that keep it current and a control-center dashboard on top. Interview-driven and idempotent, safe to re-run. Builds seven knowledge folders (Context, Channels, Campaigns, Offers, Analytics, Team, Intelligence) plus Routines, writes the Context layer that ends skills carrying their own stale copies of the ICP and offer and voice, scaffolds one folder per publish...

Build and schedule a personalized Operator prompt that runs the user's second brain on a recurring cadence. The skill is invoked from inside the vault folder locally — it reads `Context/` and `CLAUDE.md` first to infer org, team, brand voice, and paths, then asks ONLY the gaps it can't determine (cadence, connectors, DM recipient, budgets, signature). Fills `references/operator-prompt-template.md`, writes the rendered prompt locally, then invokes the `schedule` skill to wire up the recurring ...

Framework-driven audit and optimizer for any markdown vault. Applies 10 frameworks covering CLAUDE.md quality, wiki structure, compression, context rot, memory, progressive disclosure, hygiene, cross-file synthesis, architecture and discoverability, plus F10 Claude 5 rule rewriting. F9 walks the real discovery chain (root CLAUDE.md, routing, folder index, file) and audits routing tables against folder reality. F10 rewrites rules written for older Claude models into judgment plus the reason, a...

Turn a task you just finished into a small, reliable, single-purpose skill by reverse-engineering the process from the conversation you already had. Also improves or audits an existing skill. Use this AFTER you have done a piece of knowledge work in a chat (research, a draft, an analysis, a prep doc) and want to lock the process in as a skill. Triggers include "build a skill from this", "turn this into a skill", "make a skill out of what we just did", "skill-ify this", "build a skill", "impro...

Explain a topic like I'm a 5 year old. Use when the user types /eli5 [topic] or asks for a dead-simple picture explainer of how something works.

Interview the user one question at a time before starting a big or fuzzy task, then write the brief and execute it. Use when the user says "interview me", "brief me", "help me brief this", "I don't know where to start", or hands over a large task with obvious gaps in the request. Based on the interview pattern Anthropic recommends in the Claude Fable 5 field guide.

Start a clean Claude session with only the context the next task needs, instead of /compact. Captures the goal of your next session, points to the right files (never copies them), and outputs a self-contained prompt to paste into a fresh chat. Use when: "refresh", "refresh context", "fresh start", "my chat got sloppy", "start a new chat with context", "hand off this session", outputs degrading, drifting off task. Three levels: lite (quick reset), full (default handoff), ultra (full briefing)....

Audit a CLAUDE.md or skill file for rules written for older Claude models and rewrite them for the Claude 5 generation. Finds one-sided rules, bare prohibitions, retired instructions, and aggressive language, then rewrites each into judgment plus the reason, or flags it for deletion. Use when the user says "rewrite my rules", "audit my CLAUDE.md", "fix my claude md", "rule rewriter", "my skills feel too strict", or after upgrading to a Claude 5 model.

Generate SEO-optimized competitor comparison and alternatives pages. Covers "X vs Y" layouts, "alternatives to X" pages, feature matrices, schema markup, and conversion optimization. Use when user says "comparison page", "vs page", "alternatives page", "competitor comparison", "X vs Y", "best tools", or "competitor content".

Content quality and E-E-A-T analysis with AI citation readiness assessment. Use when user says "content quality", "E-E-A-T", "content analysis", "readability check", "thin content", "content audit", "AI citation", or "GEO content".

Optimize content for AI Overviews, ChatGPT web search, Perplexity, and other AI-powered search experiences. GEO analysis including brand mention signals, AI crawler accessibility, llms.txt compliance, passage-level citability scoring, and platform-specific optimization. Use when user says "AI Overviews", "GEO", "AI search", "LLM optimization", "Perplexity", "AI citations", "ChatGPT search", "AI visibility", or "llms.txt".

Hreflang and international SEO audit, validation, and generation. Detects common mistakes, validates language/region codes, and generates correct hreflang implementations for HTML, HTTP headers, and XML sitemaps. Use when user says "hreflang", "i18n SEO", "international SEO", "multi-language", "multi-region", "language tags", or "hreflang validation".

Image optimization analysis for SEO and performance — checks alt text, file sizes, formats, responsive images, lazy loading, CLS prevention, fetchpriority, filenames, and CDN usage. Use when user says "image optimization", "alt text", "image SEO", "image audit", "optimize images", "lazy loading", "WebP", or "CLS images".

GSC data-driven SEO optimization. Connects to Google Search Console (API, browser, or CSV), pulls search performance data, runs 8 analysis types (striking distance, low-CTR, declining pages, content gaps, cannibalization, quick wins, top performers at risk, device/geo gaps), prioritizes findings, and executes optimizations. Use when user says "optimize SEO", "GSC", "Google Search Console", "search performance", "CTR optimization", "keyword cannibalization", "striking distance", "declining pag...

Deep single-page SEO analysis covering on-page elements, content quality, technical meta tags, schema, images, and performance. Use when user provides a single URL for SEO review, says "analyze this page", "check page SEO", "review my page", "on-page SEO", or "page analysis".

Strategic SEO planning for new or existing websites. Industry-specific templates, competitive analysis, content strategy, and implementation roadmap. Use when user says "SEO plan", "SEO strategy", "content strategy", "site architecture", "SEO roadmap", or "content calendar".

Programmatic SEO planning and analysis for pages generated at scale from data sources. Covers template engines, URL patterns, internal linking automation, thin content safeguards, and index bloat prevention. Use when user says "programmatic SEO", "pages at scale", "dynamic pages", "template pages", "generated pages", "data-driven SEO", "thin content", or "index bloat".

Detect, validate, and generate Schema.org structured data (JSON-LD preferred). Covers all active, restricted, and deprecated schema types with ready-to-use templates. Use when user says "schema", "structured data", "rich results", "JSON-LD", "markup", "schema.org", "add schema", or "generate JSON-LD".

Analyze existing XML sitemaps or generate new ones with industry templates. Validates format, URLs, and structure. Supports sitemap index files and content-type splitting. Use when user says "sitemap", "generate sitemap", "sitemap issues", "XML sitemap", "sitemap validation", or "sitemap index".

Technical SEO audit across 9 categories — crawlability, indexability, security, URL structure, mobile, Core Web Vitals, structured data, JavaScript rendering, and IndexNow. Use when user says "technical SEO", "crawl issues", "robots.txt", "Core Web Vitals", "site speed", "security headers", "indexability", "JS rendering", or "mobile SEO".

Comprehensive SEO toolkit — full site audits, single-page analysis, technical SEO (crawlability, Core Web Vitals), schema markup, E-E-A-T content quality, image optimization, sitemap analysis, GEO for AI Overviews/ChatGPT/Perplexity, programmatic SEO, competitor pages, hreflang, and GSC data-driven optimization. Use when user invokes /seo, wants a full website SEO audit, or asks about SEO capabilities.

Produce a Market Intelligence Report — YouTube competitive research, channel analysis, content gap discovery, idea generation, daily scanning, and AI trend scouting — then render it as a BenAI-branded HTML dashboard in the instant-ui design language.

Generate a YouTube title shortlist for a new video using two parallel lenses, topic-based and pattern-based. Pulls the LAST 20 to 25 uploads from a locked comp set of competitor channels plus Ben's own channel (recent only, never all-time-popular), clusters them by subject and by structure, weights what is overperforming right now, then produces two labeled angle sets. Reasons about the video first, lets the fresh data reshape the angle, and never forces the topic into an irrelevant template....

Create a detailed video brief for a new YouTube video through a structured, collaborative process. This is a STEP-BY-STEP, interactive process — never output a complete brief immediately. Each step requires suggestions, user decision, then progression to the next step. USE THIS SKILL WHEN: - User wants to plan a YouTube video - User has a video idea and wants to flesh it out into a brief - User says "video brief", "brief a video", "plan a video" - User mentions "video planning", "video conce...

Create excalidraw visuals specifically designed for YouTube videos — diagrams, process flows, intro slides, and visual aids that will appear on screen during filming. Optimized for 16:9 video format and readability at YouTube resolution. USE THIS SKILL WHEN: - User wants to create visuals for a YouTube video - User says "make the video diagrams", "excalidraw for the video" - User mentions "video visuals", "on-screen graphics", "YouTube excalidraw" - User has a video outline with visual needs...

Generate and evaluate YouTube video ideas based on Ben's content strategy, audience interests, and competitive landscape. This is an interactive brainstorming process that produces ranked, validated video ideas ready for the brief creation phase. USE THIS SKILL WHEN: - User wants video topic ideas - User says "what should I film next", "video ideas", "content calendar" - User mentions "YouTube ideation", "brainstorm topics", "content ideas" - User wants to plan multiple videos ahead of time ...

Create a structured video outline from a video brief. Plans the flow of the video including section structure, demos and examples placement, excalidraw visual needs, and timing estimates. This bridges the brief and the script. USE THIS SKILL WHEN: - User has a video brief and wants to structure the video - User says "outline this video", "video outline", "structure the video" - User mentions "video structure", "section planning", "outline" - User wants to plan what goes where in the video T...

Create optimized YouTube packaging — titles and thumbnail concepts — for maximum click-through rate. Extends the title-generation skill with thumbnail planning, A/B testing suggestions, and packaging strategy aligned with the video brief. USE THIS SKILL WHEN: - User wants title + thumbnail for a video - User says "package this video", "thumbnail ideas", "title and thumbnail" - User mentions "YouTube packaging", "CTR optimization", "video packaging" - User has a video brief and wants to defin...

Create a video script or structured bullet points for filming, based on the video outline. Supports full scripts, teleprompter-ready text, or talking-point bullet lists depending on Ben's preference for each video. USE THIS SKILL WHEN: - User wants to write the script for a video - User says "script this", "write the script", "talking points" - User mentions "video script", "filming notes", "teleprompter" - User has an outline and wants to prepare for filming TRIGGERS: "script", "video scri...

Continuing work in `/Users/macbook/Documents/Projects/benai/benai-skills` (the BenAI Skills marketplace repo, branch `develop`). Goal of this session: keep iterating on the `refresh` skill, ship the pending rename, and close the open loops.

Build Anthropic Managed Agents through a non-technical conversation. The skill asks the user what kind of agent they want, which connectors and abilities it should have, and then silently translates that into Anthropic's Managed Agents REST API: creates the Agent, Environment, Vault and credentials, attaches MCP servers and Skills, opens a Session, and sends a first message. Hides the developer details. USE THIS SKILL WHEN user says \"agent builder\", \"build an agent\", \"create an agent\", ...

Puts a running Open WebUI or Odysseus on a shareable public URL through an ngrok tunnel, so a teammate can sign in and use the local models without installing anything. Use when the user says "share Open WebUI with my team", "share Odysseus with my team", "let my colleague use my local AI", "expose Open WebUI", "share localhost:8080", "share localhost:7860", "give someone access to my models", "set up an ngrok tunnel", "make my local AI reachable from another machine", or asks how to let some...

Answer any question about Baalda (the team second-brain app at baalda.com) in plain, non-technical language — what it is, what it can and cannot do, which file formats it supports (Markdown, images, PDF, DOCX, XLSX, code files), how sync, offline, sharing, permissions, version history, AI/MCP, pricing, platforms and self-hosting work. Use this whenever someone asks "does Baalda…", "can Baalda…", "how does Baalda…", compares it with Obsidian/Notion/Logseq, or asks what happens to a file type i...