AI Skills

Package, publish, and install Ren blueprints — the shareable snapshot of a resolved Spec. Use when a built setup should be published to the registry, installed into another pod, versioned, or deprecated; covers the resolution gate, cascade-publish consequences, public-view stripping, and install link-vs-fork semantics. Authoring the Spec itself is [[ren-systems-architect]].

Inline PR code review in this org's style: terse, blocking-vs-nits, grounded in the repo's own CLAUDE.md docs; posts inline review comments via gh and never approves.

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

Track and manage expenses on Splitwise via its REST API — record expenses, list recent ones, and check balances with friends and groups.

Connect Telegram to Ren - map a Telegram DM or group chat to a project for chat-to-project routing, and attach the `telegram` MCP to agents that need to message Telegram proactively (send messages, send documents, react). Use when the user wants a Ren agent to receive Telegram messages, post to Telegram, or both.

Explains the Ren data model, scope tiers, and the build chain, and decides what pods, projects, agents, skills, MCPs, stores, and triggers to set up and in what order. Load before any Ren build to choose the right primitives, run the reuse-before-create path, and wire everything together; and whenever a user asks how to structure or arrange their Ren setup. Designs multi-entity or share-worthy setups spec-driven — interview into a brief, research, author a Spec, push a draft blueprint, build the graph leaf-up pinning refs, publish. Owns the Ren CLI / registry mutations that compose a build — reuse, create, version, attach, scope, wire; the standalone dev skills hold only authoring craft.

Use when configuring Ren's native project email channel: enabling, listing, or disabling a project mailbox; or attaching the `email` MCP so cron, webhook, or other proactive agent runs can call `email_send`. Do not use for Gmail scanning, labelling, or mailbox automation; use Google Workspace for that.

Interact with Langfuse and access its documentation. Use when needing to (1) query or modify Langfuse data programmatically via the CLI — traces, prompts, datasets, scores, sessions, and any other API resource, (2) look up Langfuse documentation, concepts, integration guides, or SDK usage, or (3) understand how any Langfuse feature works. This skill covers CLI-based API access (via npx) and multiple documentation retrieval methods.

Connect Slack to Ren - install the workspace for channel-to-project routing, and attach the `slack` MCP to agents that need to call Slack proactively (post, reply, read history, look up users and channels, react). Use when the user wants a Ren agent to receive Slack messages, post to Slack, or both.

Connect GitHub to Ren - install the org's GitHub App, list accessible repos, and bind a repo to a project so the agent gets it mounted. Use when the user wants their Ren agent to work against a GitHub repository.

Manage vaults and credentials - the encrypted secret store that backs skills and MCPs. Use when a skill or MCP needs an API key, token, or OAuth credential, when running an OAuth connect flow, or when attaching a vault to a pod.

Author, edit, fork, optimize, and adapt skills — the modular capabilities (instructions plus optional scripts, references, and assets) an agent loads on demand when a task makes them relevant. Use when the user wants to create, update, improve, or debug a skill, adapt a third-party / community SKILL.md, or add a custom capability to an agent.

First-session setup for a new Ren user. Run when the user pastes an onboarding prompt or fetches this file. You are Ren's meta-agent for the session - read the user, translate Ren into their words, build their first real thing on Ren, and hand back a live session with concrete reasons to come back.

Define a custom remote MCP server - the third-party tool surface an agent can call - for when no registry MCP fits. Use to shape a custom remote MCP's server URL and auth-config and validate its Ren compatibility.

Design and write agents — their system prompt, model choice, and skill / MCP dependency shape. Use when the user asks to build, configure, modify, or debug an agent.

Create, schedule, and manage social media posts via Typefully. Use when asked to draft, schedule, post, or check tweets, posts, threads, or social media content for Twitter/X, LinkedIn, Threads, Bluesky, or Mastodon.

Review UI code for Web Interface Guidelines compliance. Use when asked to review my UI, check accessibility, audit design, review UX, or check my site against best practices.

Pull a YouTube transcript and turn it into summaries, Twitter/X threads, or blog posts. Use when an agent needs to extract or repurpose spoken content from a YouTube video.

X/Twitter via xurl CLI: post, search, DM, media, v2 API.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.

Generate videos from text prompts using AI models (Sora, Veo). Use when users want to create videos from descriptions, check generation status, download completed videos, or list generated videos.

Take a personality assessment via the SoulTrace API. Use when the user wants to take a personality test, discover their psychological archetype, understand their personality traits, or get a color-based personality profile. The API uses a 5-color psychological model (White=structure, Blue=understanding, Black=agency, Red=intensity, Green=connection) with Bayesian adaptive question selection to classify users into one of 25 archetypes. Triggers on: personality test, personality assessment, what's my personality, take a quiz, archetype test, color personality, soultrace.

Shopify Admin & Storefront GraphQL APIs via curl. Manage products, orders, customers, inventory, metafields, bulk operations, and webhooks. Use when working with a Shopify store programmatically — listing products, updating inventory, pulling orders, managing customers, or setting metafields.

Hunt for accounts of a given username across 400+ social media and online platforms (OSINT). Verify the user has authorization before running.

Scrape the web — HTTP fetching, stealth browser automation, Cloudflare bypass, and full-site spidering. Requires post-install browser-binary setup.

Best practices for building videos with Remotion (React-based video framework). Covers new project setup, compositions, sequencing, audio/video, text animations, GIFs, transitions, timing, Google Fonts, local fonts, Lottie, 3D, subtitles, and FFmpeg usage. Use whenever working on Remotion code or scaffolding a new video project.

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

54 real design systems (Stripe, Linear, Vercel) as HTML/CSS reference templates. Use when generating HTML/CSS in the visual style of a known brand — landing pages, marketing sites, dashboards, documentation.

Query Polymarket prediction markets — list markets, fetch prices, read orderbooks, and pull historical data. Read-only; no trade execution.

Generate pixel art with era-appropriate palettes — NES, Game Boy, PICO-8, and other retro consoles. Supports stills and short animated sequences.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Run web search, structured extraction, deep research, and dataset enrichment via the Parallel API. Paid third-party service.

Generate p5.js sketches as single self-contained HTML files — generative art, shaders, interactive scenes, and 3D. Optional Puppeteer + ffmpeg pipeline to capture sketches as MP4 or GIF.

Extract text from PDFs and scanned documents using pymupdf for native PDFs and marker-pdf for high-quality OCR on scans. Marker-pdf is heavy (~5GB models, optional GPU acceleration).

Edit PDF text in place using the nano-pdf CLI with natural-language prompts — fix typos, change titles, update small sections without re-typesetting the document.

Generate real meme images by picking a template and overlaying text with Pillow. Produces actual .png meme files.

Geocode addresses, find points of interest by category, compute driving/walking/cycling routes, and look up timezones using OpenStreetMap and OSRM. No API key required.

Produce 3Blue1Brown-style animated math and algorithm explainer videos using Manim Community Edition. Heavy dependencies (manim, full LaTeX, ffmpeg).

Generate, edit, and create variations of images using AI models (GPT-Image, DALL-E, Gemini). Use when users want to create new images from descriptions, edit existing images, or create variations.

Rewrite AI-generated text to sound human — strips 29 common AI tells (em-dashes, 'in conclusion', tricolons, hedging) and adds natural cadence while preserving meaning.

Gmail, Calendar, Drive, Docs, Sheets via the Google Python client. Reads a vault-issued OAuth access token from the environment.

Clone, create, fork, and configure GitHub repositories; manage remotes and cut releases.

Manage the GitHub pull request lifecycle — create branches, commit (Conventional Commits enforced), open PRs, monitor CI status, and merge.

Create, triage, label, assign, and close GitHub issues via the `gh` CLI or the REST API. Use for bug intake, backlog grooming, or automating issue workflows.

Review GitHub pull requests — read diffs, leave inline comments, approve or request changes. Works via the `gh` CLI or the REST API.

Set up GitHub authentication: HTTPS personal access tokens, SSH keys, and `gh` CLI login. Use as a prerequisite for any other GitHub workflow when the user is not yet authenticated on the host.

Search Tenor for GIFs by keyword and download the best match. Use when an agent needs to fetch a relevant animated GIF for a chat reply, social post, or document.

Gym workout planner and nutrition tracker. Search 690+ exercises by muscle, equipment, or category via wger. Look up macros and calories for 380,000+ foods via USDA FoodData Central. Compute BMI, TDEE, one-rep max, macro splits, and body fat — pure Python, no pip installs. Built for anyone chasing gains, cutting weight, or just trying to eat better.

Generate hand-drawn-style Excalidraw diagrams as JSON files — architecture, flow, sequence, and freeform sketches. Output can be opened directly in Excalidraw or exported to images.

Search the web for free via DuckDuckGo — supports text, news, image, and video search with no API key required. Useful as a fallback when a managed web-search primitive is not available.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Author, validate, and export DESIGN.md token spec files in Google's design.md format. Use when defining design tokens (colors, typography, spacing) for a product, or when checking a token spec against the built-in lint rules including WCAG contrast.

Generate flat, minimal light/dark-aware SVG diagrams as standalone HTML files, using a unified educational visual language with 9 semantic color ramps, sentence-case typography, and automatic dark mode. Best suited for educational and non-software visuals — physics setups, chemistry mechanisms, math curves, physical objects (aircraft, turbines, smartphones, mechanical watches), anatomy, floor plans, cross-sections, narrative journeys (lifecycle of X, process of Y), hub-spoke system integrations (smart city, IoT), and exploded layer views. If a more specialized skill exists for the subject (dedicated software/cloud architecture, hand-drawn sketches, animated explainers, etc.), prefer that — otherwise this skill can also serve as a general-purpose SVG diagram fallback with a clean educational look. Ships with 15 example diagrams.

Generate images, video, and audio with ComfyUI on Comfy Cloud — submit workflows, inject parameters, monitor jobs, and download outputs via the hosted REST/WebSocket API.

Inspect a codebase to report total lines of code, language breakdown, and code/comment/blank ratios using pygount. Use when sizing a repository, comparing language distribution, or producing engineering metrics for a report.

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says caveman mode, talk like caveman, use caveman, less tokens, be brief, or invokes /caveman. Also auto-triggers when token efficiency is requested.

Generate professional infographics with 21 layout types and 21 visual styles. Analyzes content, recommends layout×style combinations, and generates publication-ready infographics. Use when user asks to create "infographic", "信息图", "visual summary", "可视化", or "高密度信息大图".

Knowledge comic creator supporting multiple art styles and tones. Creates original educational comics with detailed panel layouts and sequential image generation. Use when user asks to create "知识漫画", "教育漫画", "biography comic", "tutorial comic", or "Logicomix-style comic".

Convert text to speech and transcribe audio using AI models (OpenAI TTS, ElevenLabs, Whisper). Use when users want to generate audio from text or transcribe speech to text.

Convert video and audio files into colored ASCII MP4s or GIFs using ffmpeg + Python. Optional ElevenLabs TTS integration for voiced narration over the rendered output.

Generate ASCII art — text banners (pyfiglet), styled boxes and quotes (cowsay, boxes), and image-to-ASCII conversion. Use for terminal-friendly logos, README headers, chat decorations, or anywhere monospaced visual output is needed.

Create professional, dark-themed architecture diagrams as standalone HTML files with SVG graphics. Use when the user asks for system architecture diagrams, infrastructure diagrams, cloud architecture visualizations, security diagrams, network topology diagrams, or any technical diagram showing system components and their relationships.

Read and write Airtable bases via the REST API — list and filter records, create/update/delete rows, run upsert operations, and query views. Use when an agent needs to query, mutate, or sync data stored in an Airtable base.