claude

building-agents

Expert prompt-engineering reference for AI agents on Claude, GPT, Gemini, Kimi, and Grok APIs, plus authoring CLAUDE.md / AGENTS.md project-instruction files

6 on GitHubMITupdated today
/

Plugin building-agents from marketplace shaharsha-skills in shaharsha/claude-skills. Commands read from the repo's manifest — today.

What it installs

Skills (27)

  • brand-assets

    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 ico

  • brand-system

    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

  • codex-review

    Use only when a brief, plan or document names the codex-review skill, codex_review.sh, verify_artifact.sh or verify_prompt.sh. The skill was renamed to pair-intelligence; load that instead.

  • deck-to-video

    Use when turning a slide deck plus per-slide narration audio into an mp4 video — a self-playing/self-presenting deck video, "slides to video", "presentation to mp4", a shareable WhatsApp/Slack/Drive video of a narrated deck, or when a slide video needs a per-slide progress bar / countdown / slide co

  • elevenlabs-stt

    Use when transcribing speech with ElevenLabs Scribe in any language (Hebrew, English, mixed) - a meeting, talk, call, podcast, voice note or video, a YouTube link, a transcript.md with timestamps and speakers, or SRT subtitles from audio. Also for speaker labels (diarization), word timestamps, keyte

  • elevenlabs-tts

    Use when generating speech, voiceover, narration or any spoken audio with ElevenLabs in any language (Hebrew, English, mixed), including the everyday ask "make me an MP3 explaining X" - an audio briefing of a plan, thread, meeting or open decisions for someone to listen to. Also for audio-tag script

  • excalidraw-diagrams

    Use when creating, editing, or updating any Excalidraw scene, diagram, flowchart, architecture/system diagram, mind map, wireframe, timeline, or slide deck through the Excalidraw+ MCP — whenever the user says "excalidraw", "draw a diagram", "make a flowchart/architecture diagram", "put this on a can

  • gdoc-sync

    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, re-applies paragraph styling (line spacing, spa

  • generating-video-clips

    Use when turning a still image, illustration, comic panel or character art into a short animated clip (image-to-video), choosing a video model or provider (Gemini Omni, Veo, Seedance, Kling, ElevenLabs Flows) or hitting their API gates, lip-syncing a character's mouth to existing dialogue audio (Syn

  • gsheets

    Read, find, write and format Google Sheets from the command line. Covers reading ranges as JSON or as header-keyed records, finding a row by its content, guarded compare-and-set edits on Sheets other people also edit, writing many ranges in one call, one-call table layout (header, number formats, fr

  • gslides-sync

    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, warns when the pptx's audio or

  • image-generation

    Generate logos, icons, UI mockups, hero images, product shots, and other design assets using OpenAI GPT Image 2.5 (Sunburst, Flare) or Google Gemini (Nano Banana 2, Nano Banana Pro, Nano Banana 2 Lite). Use whenever the user asks to create, design, generate, mock up, render, or illustrate a visual a

  • namecheap-domains

    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 acr

  • narrating-pptx

    Use when adding voice narration, voiceover, or TTS audio to a PowerPoint/pptx or Google Slides deck in ANY language (Hebrew, English, mixed) — making a deck self-presenting, generating per-slide speech with ElevenLabs, re-narrating slides after edits, or when embedded pptx audio won't autoplay, trig

  • office-render

    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 th

  • pair-intelligence

    Use when another model's independent view would help - reviewing a plan or diff before it lands, a second opinion on a decision or diagnosis, brainstorming over several rounds, checking a screenshot, web research, or having the other model drive a browser. Also when the user says ask Codex, GPT or G

  • presentation-generator

    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,

  • producing-animated-episodes

    Use when making a narrated or voiced animated video with recurring characters - an anime, cartoon or comic episode, a short for a group chat, a story video about friends, family, a class or a team - from photos, a chat export, a story idea or a script, in any visual style, Hebrew/RTL or English. Als

  • prompt-engineer

    Use whenever an LLM agent, chatbot, or assistant is built, debugged, reviewed, planned, or migrated - users rarely say 'prompt'; they say 'the agent keeps calling the wrong tool', 'it ignores my instructions', 'it got worse after the upgrade', or paste a log. Trigger when a file in scope has a syste

  • proton-pass

    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.

  • reviving-sessions

    Use when a Claude Code session exists on disk but the Claude desktop app does not list, open or name it - a session started with `claude -p` or from a shell script, from the VS Code extension, or under another account; a session that vanished from the sidebar after its worktree was deleted; headless

  • self-presenting-decks

    Use when a presentation needs to explain itself — the user wants a deck with voiceover/narration, a self-playing or self-presenting deck, "add audio to my slides and also make a video", a narrated deck to share async (WhatsApp/Slack/Drive/email), or asks how to produce/update the whole deck → narrat

  • tavily-extract

    Use when a web page won't come through a normal fetch — WebFetch (or curl) returns an empty shell, a "Loading…" skeleton, or a 403/Forbidden. That happens on JavaScript-rendered single-page apps (React/Next.js/Vue dashboards, leaderboards and docs such as Artificial Analysis, LMArena, developers.ope

  • tech-design-doc

    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 archit

  • viewing-videos

    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

  • writing-plainly

    Use when drafting or editing text that someone other than the user will read - Slack, Teams or WhatsApp messages, emails, status and done updates, answers and recommendations, asks, announcements, PR descriptions, tickets, docs - especially drafts sent or posted under the user's name. Also use when

  • writing-project-instructions

    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

View source on GitHub

More from shaharsha/claude-skills

All 7 plugins →

Author production-grade brand books, run logo / favicon / icon-pack pipelines, generate AI imagery via GPT Image 2.5 (Sunburst, Flare) and Gemini Nano Banana, and build architecture / flow / system diagrams in Excalidraw

27 skills

6

Sync Markdown to Google Docs, .pptx to Google Slides, CSV / values to Google Sheets, generate AI-rendered 16:9 presentation decks, generate ElevenLabs Eleven v4 speech with audio-tag direction, transcribe speech and make subtitles with ElevenLabs Scribe v3, add per-slide voice narration with autoplay to any pptx, turn narrated decks into self-playing mp4 videos, orchestrate the whole deck-to-narration-to-video chain, and write messages, emails, updates and tickets that read plainly and not like AI

27 skills

6

Author and audit technical design docs, RFCs, and ADRs, and consult a second model (OpenAI Codex or Google Gemini) to review a plan or diff, give a second opinion, brainstorm, research, or browse before it lands

27 skills

6

All 26 agent skills - gdoc-sync, gslides-sync, gsheets, presentation-generator, elevenlabs-tts, elevenlabs-stt, narrating-pptx, deck-to-video, self-presenting-decks, writing-plainly, brand-system, brand-assets, image-generation, prompt-engineer, writing-project-instructions, tech-design-doc, namecheap-domains, office-render, viewing-videos, proton-pass, excalidraw-diagrams, tavily-extract, pair-intelligence, reviving-sessions, generating-video-clips, producing-animated-episodes

27 skills

6

utilities

claude

Domain availability via Namecheap API; rendering Microsoft Office files (.docx/.pptx/.xlsx) to PDF/images via the real Office apps on macOS; viewing video files (mp4/mov) by extracting the fewest frames that answer the question; managing credentials and secrets via the Proton Pass CLI (pass-cli); plus fetching JavaScript-rendered or bot-blocked web pages that WebFetch can't, via the Tavily Extract API

27 skills

6

Produce voiced, subtitled, lip-synced animated episodes from photos and a script with one config-driven engine; animate stills with Gemini Omni and lip-sync dialogue with Sync 3 on fal

27 skills

6

Maintain building-agents?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins7 plugins