t0ddharris

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to 'open a website,' 'fill out a form,' 'click a button,' 'take a screenshot,' 'scrape data from a page,' 'test this web app,' 'login to a site,' 'automate browser actions,' or any task requiring programmatic web interaction.

Write a blog post from start to finish. Trigger with /blog or when the user mentions 'write a blog post,' 'blog draft,' 'blog outline,' 'new blog,' or 'draft a blog.' Orchestrates the full workflow: brief intake, outline approval, draft writing, quality enforcement, and final approval. For topic planning, see content-strategy. For editing existing drafts, see copy-editing.

When the user wants to create visual creative assets — LinkedIn ads, carousel images, social graphics, banners, display ads, presentation slides, or any visual marketing content. Also use when the user mentions 'design,' 'creative,' 'ad image,' 'carousel,' 'banner,' 'social graphic,' 'slide,' 'visual asset,' 'LinkedIn ad,' or 'display ad.' This skill ensures all visual output follows the brand system.

Create compelling B2B customer case studies for the company. Use when asked to write, draft, or help with case studies, customer success stories, customer testimonials, or win stories. Supports both branded case studies (with company name) and anonymous case studies (e.g., 'a customer in the retail space') when NDAs or privacy concerns apply.

Generate Excalidraw diagram files (.excalidraw) from a description. Use when the user mentions 'excalidraw,' 'diagram,' 'flowchart,' 'process flow,' 'architecture diagram,' 'visual diagram,' or 'draw a diagram.' Outputs valid JSON that opens in Excalidraw web app, VS Code extension, or Obsidian plugin. No API key needed.

Export HTML pages to print-quality vector PDFs using Playwright's page.pdf() API. Trigger with /html-to-pdf or when the user wants to export an HTML page to PDF, create a print-ready PDF from HTML, or generate a PDF of a handout, card, flyer, or any HTML design.

Implement CTA buttons in HubSpot email and landing page templates. Use when the user wants to add, fix, or style CTA buttons in HubSpot templates. Also use when the user mentions 'HubSpot CTA,' 'email CTA,' 'call to action button,' 'CTA module,' or 'email_cta.' Works alongside hubspot-email and hubspot-landing-page skills.

Build HTML email templates for HubSpot. Use when the user wants to create, edit, or troubleshoot HubSpot email templates. Also use when the user mentions 'HubSpot email,' 'email template,' 'HubL email,' or 'email HTML.' For email sequences and drip campaigns, see email-sequence. For CTA buttons, see hubspot-cta.

Create a new Marketing OS for your company. Trigger with /setup. Asks your company name, scaffolds a standalone repo with all skills and brain templates, then walks you through configuring everything.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to 'open a website,' 'fill out a form,' 'click a button,' 'take a screenshot,' 'scrape data from a page,' 'test this web app,' 'login to a site,' 'automate browser actions,' or any task requiring programmatic web interaction.

Write a blog post from start to finish. Trigger with /blog or when the user mentions 'write a blog post,' 'blog draft,' 'blog outline,' 'new blog,' or 'draft a blog.' Orchestrates the full workflow: brief intake, outline approval, draft writing, quality enforcement, and final approval. For topic planning, see content-strategy. For editing existing drafts, see copy-editing.

Check which brain files are complete, incomplete, or empty, and get recommendations for what to fill next. Trigger with /brain-health or when the user mentions 'brain status,' 'brain health,' 'what's missing in my brain,' 'brain completeness,' 'which brain files,' or 'brain check.' Also runs automatically at the end of /setup.

When the user wants to create visual creative assets — LinkedIn ads, carousel images, social graphics, banners, display ads, presentation slides, or any visual marketing content. Also use when the user mentions 'design,' 'creative,' 'ad image,' 'carousel,' 'banner,' 'social graphic,' 'slide,' 'visual asset,' 'LinkedIn ad,' or 'display ad.' This skill ensures all visual output follows the brand system.

Create compelling B2B customer case studies for the company. Use when asked to write, draft, or help with case studies, customer success stories, customer testimonials, or win stories. Supports both branded case studies (with company name) and anonymous case studies (e.g., 'a customer in the retail space') when NDAs or privacy concerns apply.

When the user wants to edit, review, or improve existing copy — including essays, posts, presentations, email copy, or any other written content. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' 'copy sweep,' 'sharper,' 'tighter,' 'improve the wording,' 'refine the language,' or 'make this hit harder.' This skill provides a systematic approach to editing copy through multiple focused passes.

When the user wants to write, rewrite, or improve copy for any page or piece — including landing pages, about pages, or long-form content. Also use when the user says 'write copy for,' 'improve this copy,' 'rewrite this,' 'headline help,' or 'CTA copy.'

/brief - Write session brief, commit, and push. Run at end of session to checkpoint all work.

Get an outside-Anthropic second opinion on any piece of work by sending it to Google Gemini with an adversarial critique prompt. Use when the user wants to pressure-test a decision, plan, assumption, blog draft, landing page, positioning statement, campaign, or chunk of code with a non-Claude model. Trigger when the user says 'devil's advocate,' 'play devil's advocate,' 'poke holes,' 'stress test this,' 'second opinion,' 'outside perspective,' 'non-Anthropic read,' 'sanity check from another model,' 'challenge this,' 'critique this from outside,' or '/devils-advocate.' This is explicitly a cross-model sanity check — do NOT substitute your own critique; the whole point is to surface blind spots Claude might share.

Analyze the current conversation for corrections, approvals, and patterns, then propose updates to the skill files that were used. Trigger with /reflect or automatically at end of /brief. Use when the user says 'reflect,' 'learn from this,' 'update the skill,' or 'remember this for next time.'

Audit all available Claude skills across user and project scopes — inventory them, map routing and overlap, score each on efficiency, reliability, clarity, maintainability, learning, currency, and safety, then produce a prioritized report and draft patches. Use when the user asks to audit, review, improve, optimize, modernize, clean up, consolidate, benchmark, or evaluate skills; to find outdated, duplicate, or inefficient skills; to identify missing skills; or to check whether skills follow current best practices. Diagnosis only — never edits a skill without explicit approval.

Start a new session. Trigger with /start at the beginning of a conversation. Reads the session brief, checks git status, summarizes where things stand, and increments the session number.

Sync Claude Code skills to Codex. Handles project-level (.claude/skills → .agents/skills) and user-level (~/.claude/skills → ~/.codex/skills). Trigger with /sync-skills or when the user mentions 'sync skills,' 'codex skills,' or 'sync to codex.'