claude-skills

Use when adding voice narration, voiceover, or TTS audio to a PowerPoint/pptx deck in ANY language (Hebrew, English, mixed) — making a deck self-presenting, generating per-slide speech with ElevenLabs, or when embedded pptx audio won't autoplay or triggers PowerPoint's "found a problem / Repair" dialog. Use whenever the user mentions narration, voiceover, audio in slides, TTS for a presentation, ElevenLabs + pptx, or a self-playing deck — even if they don't say "narration" explicitly.

Manage secrets and credentials using Proton Pass CLI (pass-cli). Use when the user asks to store, retrieve, list, or manage passwords, API keys, secrets, or credentials in Proton Pass. Also triggers when the user mentions Proton Pass, pass-cli, vault management, or saving/looking up secrets.

Use when authoring, editing, updating, trimming, or adding rules to a CLAUDE.md, AGENTS.md, CLAUDE.local.md, or other project-level instruction file for an AI coding agent — including small one-line changes. Triggers on "write a CLAUDE.md", "audit my CLAUDE.md", "trim my CLAUDE.md", "is my CLAUDE.md too long", "what should go in my CLAUDE.md", "why isn't Claude following my CLAUDE.md", "add this to CLAUDE.md", "edit CLAUDE.md", "update CLAUDE.md", "put a rule in CLAUDE.md", "remember this in CLAUDE.md", or the equivalent for AGENTS.md. Always load this skill before modifying any CLAUDE.md/AGENTS.md, not just when explicitly asked.

Use when the user wants Claude to view, watch, inspect, or extract information from a video file (mp4, mov, webm, mkv, screen recording, Zoom/Meet/Teams meeting recording, demo, screencast, phone clip) — e.g. "can you see this video", "what numbers are shown on screen", "what slide was up when X was said", "check the recording", or when a transcript exists but on-screen content (figures, slides, UIs, dashboards) must be read visually. Claude cannot ingest video natively; this skill is how Claude sees one.

Use when you need to SEE how a Microsoft Office file actually renders on macOS — preview/screenshot/convert a Word .docx, PowerPoint .pptx, or Excel .xlsx to PDF or page images, visually QA a generated Office document, check fonts/tables/slide layout, or read a doc's real appearance. Renders with the REAL Office apps (Word/PowerPoint/Excel), which is far more faithful than LibreOffice for fonts, complex tables, RTL/Hebrew, and slide layouts. macOS only.

Use ANY time an LLM-powered agent, chatbot, or AI assistant is being built, debugged, reviewed, planned, or migrated — the user almost never says 'prompt.' They say 'the agent keeps calling the wrong tool,' 'why is it ignoring my instructions,' 'fix this bug,' or just paste a log. TRIGGER when (1) any file in scope contains a system prompt, tool/function description, function-calling schema, tools.json, agents/* file, or imports an LLM SDK or agent framework (anthropic, openai, google.genai, AWS Bedrock, Vertex, Azure OpenAI, LangGraph/LangChain); (2) an agent loops, picks the wrong tool, hallucinates arguments, runs verbose despite low-verbosity settings, over- or under-escalates, ignores instructions, or shifts behavior after a model upgrade; (3) the user is thinking through or planning agent architecture — subagents, orchestrator/worker splits, state passing, multi-agent workflows — before code is written; (4) the user is comparing providers, migrating a prompt to a newer model, or asking 'is this good eno

Read, write, update, delete cells in a Google Sheet; create / rename / duplicate / delete worksheet tabs; style headers with bold + colored backgrounds; freeze rows or columns; set column widths and row heights; add basic filters and sort ranges; apply alternating-row banding (zebra stripes), conditional formatting, borders, and number formats; or push a CSV file into an existing Sheet. Use when the user asks to push data into a Google Sheet, sync a CSV / DataFrame / table to a Sheet, format or style a Sheet (header colors, filters, freeze, banding), add or rearrange tabs / worksheets, build a stakeholder review or dashboard Sheet, or do anything Sheets-API-shaped that the gdoc-sync skill does for Docs.

Use when authoring, scaffolding, or auditing a technical design doc, RFC, ADR, technical spec, or architecture proposal — for any audience including external dev partners. Triggers include "design doc for X", "I need an RFC", "should this be an ADR or a full design doc", "help me prep for the architecture review meeting", "audit this design doc". Skip for product plans / PRDs, single-line decisions that fit in a commit message, post-mortems, or process-only meeting agendas without architectural content.

Professional logo/brand asset pipelines — vectorize a PNG logo into a multi-color SVG, finalize an SVG (clamp fills to exact brand hexes, filter extraneous counters, square a viewBox), rasterize SVG back to pristine PNG at target size/padding, and generate a full favicon + apple-touch-icon + PWA icon pack from a single SVG source. Use when the user asks to vectorize a raster logo, clean up an SVG, re-render a logo at a specific size, produce favicons, build an icon pack, or audit brand color fidelity.

Author a production-grade brand book + design system for a web product — a long-form BRAND.md (20 sections covering the core idea, logo system, color, typography, spacing, surfaces, motion, voice, accessibility, components, and Tailwind v4 @theme tokens), a printable BRAND.html + PDF sibling, and a matched tokens.css / tokens.json with primitive/semantic/component tiering. Use when the user asks to create, draft, author, scaffold, or update a brand book, brand guidelines, design system, design tokens, style guide, visual identity, or BRAND.md; or when a new product needs its first documented identity.

Sync a Markdown file to an existing Google Doc — pushes the markdown via Drive upload, rewrites Google's broken `[text](#slug)` in-doc anchors AND `[text](other.md#slug)` cross-doc references into working heading links, resizes oversized inline images, and optionally applies right-to-left paragraph direction for Hebrew/Arabic. Use when the user asks to sync/push/deploy markdown to a Google Doc, update an existing Google Doc from a local .md file, link from one synced Doc into a sibling synced Doc, or maintain a Hebrew/Arabic Doc whose body must render RTL.

Sync a .pptx file to an existing Google Slides presentation — pushes the pptx via Drive resumable upload (Google auto-converts), rewrites broken in-deck slide references and cross-presentation links into native pageObjectId links, resizes images that overflow the page, and optionally applies right-to-left paragraph direction for Hebrew/Arabic decks. Use when the user asks to sync/push/deploy a pptx to a Google Slides, update an existing Google Slides from a local .pptx file, refresh a stakeholder-facing slide deck whose source of truth is a locally-generated pptx, or maintain a Hebrew/Arabic deck whose text must render RTL.

Generate logos, icons, UI mockups, hero images, product shots, and other design assets using OpenAI gpt-image-2 or Google Gemini (Nano Banana 2 Flash, Nano Banana Pro). Use whenever the user asks to create, design, generate, mock up, render, or illustrate a visual asset, or asks for image prompt engineering. Picks the right model for the job, writes a model-specific prompt following the official prompting rules of each provider, calls the API, and saves the PNG to disk.

Check domain availability against the Namecheap API — single domain, batch up to 50 at once, or multi-TLD sweeps of a base name. Use when the user asks whether a specific domain is available/taken/free, wants to brainstorm and screen candidate names for a product/company/project, sweeps one name across TLDs like .com/.io/.ai/.dev/.co, or asks about premium pricing and EAP fees. Triggers on 'is X.com available', 'is X taken', 'check these domains', 'find me an available .ai', 'is this domain free', 'domain availability', 'check namecheap', 'what .io names are free', 'brainstorm domain names'. Returns available/taken per domain with premium pricing flags; auto-chunks lists larger than 50 across batches.

Generate superb 16:9 widescreen presentations (PDF and PPTX) where every slide is a custom AI-rendered image. Each slide is free to take any visual form — full-bleed photograph, structured infographic, architecture diagram, big-number callout, comparison cards, UI mockup with annotations, timeline, quote card, do/don't table — whatever the slide actually needs. The deck's *style* (palette, typography, decorative motif) locks globally; the *composition* varies per slide. The skill researches the topic (local files or web), designs a narrative arc (SCQA / Duarte oscillation / Kawasaki 10/20/30), locks a global visual style via a reference image, then generates all slides in parallel (concurrency 4) by calling the image-generation skill. Use whenever the user asks to create, build, design, generate, or draft a presentation, slideshow, slide deck, pitch deck, keynote, briefing deck, masterplan, or any visual document where slides should be visually distinctive rather than templated. SKIP when the user wants a tex