skills

Build premium, TV-commercial-grade product highlight-reel promo videos from a handful of screen recordings. Music-only by default (optional VO-narrated cut), HyperFrames + paused GSAP, rendered and muxed locally. Ships a full kit — 16:9 + 9:16 films and matching key-art posters — in three swappable, production-proven themes. Use when the user asks for a product promo / launch film / hero reel / app commercial / "video like <reference>" / feature sizzle from screen captures, or says "highlight reel", "product TV commercial", "aurora theme", "minimal / notion-style promo". Three theme presets: AURORA (dark, glowing, chromatic, bold), MINIMAL (light Notion-white, floating cards, one accent, confident restraint), and LINE ART (cream paper, bold navy ink, one gold accent, hand-drawn framed panels). Ships a self-contained EnConvo scaffold (bundled logo, keycaps, SFX, music bed) that reproduces the launch film by dropping in new product clips.

Turn screen recordings into polished videos — marketing promos, user guides, product demos, and more. Goal-aware pipeline: detects user intent, selects strategy, recommends a plan, then executes. Full pipeline: intent detection → strategy selection → source analysis → storyboard planning → source prep → VO generation → frame-by-frame compositing → audio mixing → final encode. Supports animated presenters (AI animal/character with rembg cutout), per-word caption sync (pop, karaoke, static styles), multi-zoom animations, overlay dissolve transitions, time-mapped VO-to-source sync, CJK-aware captions, letterbox-aware cropping, and keypress + shortcut animation overlays with frame-aligned tick/tock SFX (canonical pattern for product demos that show hotkeys; ships proven SFX library at assets/sfx/). Use when: (1) user has screen recordings and wants a polished video — marketing, tutorial, demo, or changelog, (2) user says "make a promo video", "tutorial from this recording", "TikTok video", "marketing video", "use

Unified financial analysis & portfolio management toolkit. Routes to the right sub-system based on intent. Covers: daily market briefings, macro risk monitoring, sentiment scanning, strategy evolution & signals, options analysis, 禅動 chart analysis, COT smart-money reports, and full portfolio checking (structured notes, sell puts, FX options, accumulators) with XLSX report generation. Use when user says /financial-analysis, 'daily briefing', 'morning briefing', 'macro risk', 'liquidity check', 'sentiment scan', 'market sentiment', 'evolve strategy', 'create strategy', 'strategy signal', 'what does the strategy say', 'quick look', 'scan ticker', 'ride the rally', 'catch dips', 'play safe', '禅動', 'chandong', 'analyze ticker', 'fcn check', 'fcn status', 'check fcn', 'portfolio check', 'portfolio report', 'structured products', 'are my fcns safe', 'sell puts', 'accumulators', 'options analysis', 'cot report', 'smart money'.

Visible step-by-step walkthrough mentor for live browser/app tutoring across OptionCharts.io, TradingView, and EnConvo Settings. Use when the user wants to be walked through a page, chart, setup flow, tool, or concept viewport by viewport, including options/stock analysis with option chains, GEX, DEX, open interest, max pain, Greeks, volatility, P&L charts, TradingView charts, indicators, drawing tools, watchlists, screeners, alerts, layouts, paper trading, or EnConvo setup tasks such as global providers, AI models, credentials, agents, tools, skills, shortcuts, dictation, knowledgebase, account, and developer settings.

Conduct rigorous, McKinsey-style industry / sector research and produce a structured research report. Use when the user says /industry-research-mckinsey or asks to research an industry/sector/market/value chain, wants market sizing (TAM/SAM/SOM), competitive landscape, value-chain / industry-chain analysis, profit pools, demand-supply dynamics, industry drivers, or trend/outlook analysis, or asks for a 行业研究 / 产业研究 / 行业报告 / 赛道分析 / 投研报告 / industry report / sector deep-dive / market analysis. Also fires when the user wants to find supply bottlenecks, pricing-power chokepoints, or the source of excess returns (超额收益) along a value chain (the 产业投资人 / bottleneck lens). Bilingual: follows the user's language. Do NOT use for company-only financial modeling unrelated to an industry, or for pure document formatting.

Produce multi-act long-form Mandarin financial analysis videos for social-media upload (TikTok/Bilibili/YouTube/WeChat视频号/X). Given any input source (news article, earnings call, IPO filing, macro print, chart, tweet thread, raw data), build a broadcast-grade anchor-led explainer using a locked pipeline — script in tight 5字/second cadence, render anchor with xAI Grok Imagine Video i2v with baked Mandarin VO and locked identity, composite editorial GSAP overlay panels via HyperFrames in the right 40% of frame, concat acts, mix BGM, ship MP4. Use when the user gives a finance/markets/macro/equity/options/IPO/crypto source and asks for a viral video, a 解读视频, a 拆解视频, an explainer, a TG/SNS-ready clip, or simply says "make a video about this". Also use when the user says "finance-capital-markets-video-maker", "FCM video", "market video", "anchor video", or "Vivieen video".

Real-person tutor mode for any topic. Plans a stepped curriculum, actively drives the learning surface (web pages via browser-use, native macOS apps via computer-use), and teaches by *pointing at the real screen* — not by dumping textbook walls of text. Speaks in short conversational turns sized for TTS, asks eye-exercises after each concept, opens the matching Obsidian deep-dive note one step at a time, and logs the full curriculum into the user's Obsidian vault for later self-study. Use when the user says "teach me X", "be my tutor", "walk me through X like I'm a newbie", "tutor mode", "/ai-tutor", or hands you a live app/webpage and asks you to teach against it.

Investment analysis tutor for stocks, ETFs, ADRs, and major liquid tickers with technical analysis, ticker-specific macro context, and investor narrative research. Use when the user asks whether a ticker is a buy, hold, sell, worth buying, should be sold, or wants RSI/MACD/EMA/SMA/Bollinger/ADX/ATR/Fibonacci/support/resistance explained with current values. First obtain a financial-analysis baseline from the financial-analysis skill, Yahoo Finance OHLCV, or direct calculations; add a macro/fundamental narrative overlay directly relevant to the ticker using financial-analysis and, when the user has logged-in access, Bloomberg and Seeking Alpha via Chrome; then use Chrome/TradingView as the visual second-pass verification and teaching surface.

Studio-grade single-page web design with **swappable design shells across 16+ styles** (auto-picked by industry or manually chosen) and an opt-in **3D / motion / special-effects toolkit** (depth displacement, tilt+sheen, glass refraction, volumetric slices, light caustics, particle samplers, three.js on demand). Designs with the taste of a tier-1 studio (Apple / Pentagram / Bureau Borsche / Linear / Vercel / Aesop / Klim / Order / MSCHF). Picks aesthetic direction BEFORE writing code, pulls palette from the actual subject, ships portable single-folder static sites with built-in navigation (3 tiers), 7-language i18n via [data-i18n] slots, and zero build step. Use for personal brand sites, founder portfolios, product landings, company about pages, launch teasers, lookbooks, lesson microsites, annual reports, or any one-page site — or when the user asks for "fancy website", "multi-style website", "3D website", "Apple-style depth", "portrait website", "product landing", "brand site", "公司官网", "产品落地页", or provides

Configure any aspect of Hermes Agent (Nous Research) via CLI. Channels, models, plugins, gateway, skills, cron, hooks, memory, MCP, and the ACP bridge. Mirrors the openclaw-configure skill structure.

Expert-level OpenClaw CLI configuration skill. Covers channels, models, plugins, gateway, agents, hooks, cron, security, sandbox, memory, browser, nodes, DNS, webhooks, approvals, backup, ACP provenance, ClawHub skill registry, tasks, and more. Self-evolving: updates itself after learning new patterns.

Expert Word document design agent for macOS using python-docx and AppleScript. Creates and edits stunning, professional documents with premium design quality. Use when: (1) Creating new Word documents from scratch with python-docx, (2) Editing or redesigning existing .docx files, (3) Building documents with custom design (cover pages, styled tables, callout cards, pull quotes, sidebars, KPI panels), (4) Live editing documents via AppleScript IPC (text, fonts, paragraphs, find/replace, fields, TOC), (5) Updating fields, TOC, or exporting to PDF via AppleScript on macOS, (6) Generating AI images for document covers and content, (7) Any task requiring python-docx code generation with design best practices. Features request-sized Workflow Gate, always-on task tracking for builds, audit loop with snapshot-and-rollback, AR-safe image insertion with auto-crop, page size Letter/A4 support, and page-flow estimation flagged honestly (python-docx has no layout engine, so flow issues are WARNINGS to verify in Word).

AI image generation via Google Nano Banana (Gemini image models) with native aspect ratio and resolution control. Use when: (1) Generating images with specific aspect ratios (16:9, 9:16, 1:1, etc.), (2) Generating images at specific resolutions (1K, 2K, 4K), (3) Other skills need image generation backend (pptx-design, docx-design, xlsx-design), (4) User says 'generate image', 'nanobanana', 'nano banana', or needs AI image generation with precise dimension control.

Obsidian vault toolkit: interact with vaults via Obsidian CLI (read, create, search, daily notes, properties, tasks, plugins); create/edit Markdown notes with wikilinks, callouts, embeds, and properties; build Bases (.base) views with filters and formulas; create JSON Canvas (.canvas) mind maps and flowcharts; extract clean markdown from web pages with Defuddle. Activates on: obsidian, vault, wikilink, callout, .base file, .canvas file, obsidian cli, obsidian note, obsidian markdown, daily note, defuddle, or any Obsidian-related request.

Find & remove duplicate photos using perceptual hashing. Interactive browser review page — no server needed. Use when user says: dedup photos, find duplicate photos, remove duplicate images, photo dedup, /photo-dedup.

Audit and fix PowerPoint (.pptx) layout issues directly on files using python-pptx. No PowerPoint app needed. 5-phase audit: (1) structural scan for overlaps and out-of-bounds shapes, (2) text truth check for hidden overflow via font metrics, (3) visual/readability audit for font size and contrast, (4) layout consistency for margins and spacing, (5) composition coverage detection — flags overlay shapes blocking full-bleed background images (>30% single shape = WARNING, >50% combined = CRITICAL). Auto-fixes text box sizing, font sizes, empty placeholders, and vertical reflow. Use when: (1) User wants to check a .pptx for layout problems, (2) User asks to fix or clean up a PowerPoint file, (3) After creating/editing a presentation to validate quality, (4) User says 'audit pptx', 'fix pptx', 'check my slides', or similar.

Expert PowerPoint design agent for macOS. python-pptx + lxml is the sole editing engine — all content and design changes go there. AppleScript is used only for app lifecycle (open, quit, navigate, slideshow, screenshot). Use when: (1) Creating new PowerPoint presentations from scratch, (2) Editing or redesigning existing .pptx files, (3) Building slide decks with custom design (gradients, cards, KPI panels, charts, tables), (4) Refreshing/previewing presentations in PowerPoint on macOS via the quit-rebuild-reopen cycle, (5) Generating AI images for slide backgrounds and content, (6) Any task requiring python-pptx code generation with design best practices. Features request-sized workflow gate (simple tweaks skip planning; 5+ slide decks use the 3-phase plan), 27 critical rules grouped into 5 clusters (including mandatory subject-bbox declaration and subject-side panel placement to prevent gradient-over-subject collisions), mandatory dark-BG + targeted-gradient contrast strategy, add_gradient_shape() for overl

Expert Excel workbook design agent for macOS using openpyxl and AppleScript. Creates and edits stunning, professional spreadsheets with premium design quality. Use when: (1) Creating new Excel workbooks from scratch with openpyxl, (2) Editing or redesigning existing .xlsx files, (3) Building workbooks with custom design (KPI dashboards, styled data tables, charts, conditional formatting, cover sheets), (4) Live editing workbooks via AppleScript IPC (cell values, fonts, recalculation, PDF export), (5) Refreshing/recalculating workbooks live in Excel on macOS, (6) Generating AI images for cover sheets and section headers, (7) Any task requiring openpyxl code generation with design best practices.

Install or uninstall skills from the Enconvo curated skills store, Skills.sh, ClawHub, or a GitHub URL. Use when a user asks to list, install, or uninstall skills.

Tier-1 creative agency for end-to-end video production. Owns creative direction, scriptwriting, rich-media generation (T2I/I2I/T2V/I2V), music, word-synced captions, HyperFrames rendering, and QA — delivers a broadcast-quality MP4. Use when user says "make me a video", "product reel", "brand film", "60-second explainer", "cinematic intro". User describes the idea; this skill owns the rest. Never ships AI-slop.

Manage Telegram bots via @BotFather — create/delete bots, set name/description/about/commands/photo, toggle inline/groups/privacy, get/revoke tokens.

Text-to-speech voice toolkit. DEFAULT ACTION: When called with text (e.g. /voicebox hello), IMMEDIATELY run: uv run $SKILL_DIR/scripts/voicebox.py generate "Calm Narrator" "<text>" --play. Do NOT ask questions, do NOT greet the user — just generate and play the speech. Also supports: voice cloning, multi-speaker conversations, recording, and transcription.

Use ACE-Step API to generate music, edit songs, and remix music. Supports text-to-music, lyrics generation, audio continuation, and audio repainting. Use this skill when users mention generating music, creating songs, music production, remix, or audio continuation.

Comprehensive media processing: transcribe, translate, summarize, and dub videos/audio with professional TTS. Supports local files (MP4, MP3, WAV, M4A, etc.) and URLs (YouTube, Twitter, TikTok, 1000+ sites). Use when user says /video-transcribe, /video-translate, /video-dub, /video-summary, or asks to transcribe, translate, dub, or summarize any video/audio.

Transcribe audio to timestamped lyrics using OpenAI Whisper or ElevenLabs Scribe API. Outputs LRC, SRT, or JSON with word-level timestamps. Use when users want to transcribe songs, generate LRC files, or extract lyrics with timestamps from audio.

Render music videos from audio files and lyrics using Remotion. Accepts audio + LRC/JSON lyrics + title to produce MP4 videos with waveform visualization and synced lyrics display. Use when users mention MV generation, music video rendering, creating video from audio/lyrics, or visualizing songs.

Full end-to-end MTV music video creator. From a song concept and optional character reference photo, produces a complete cinematic MTV: (1) writes lyrics and generates music with ACE-Step, (2) generates cinematic scene images, (3) animates with I2V (Grok/Seedance), (4) assembles clips with audio and crossfade transitions, (5) transcribes audio for accurate lyric timing, (6) burns synced lyric subtitles + opening/ending credits with branding. Use when user says "make an MTV", "create a music video", "generate MTV", "/mtv", or describes a song they want turned into a full visual music video.

Generate videos using Grok AI via Chrome browser automation. Supports T2V (text-to-video) and I2V (image-to-video) with reference image uploads. Uses grok.com/imagine. Use when user says "Grok video", "create video with Grok", or wants AI video generation through Grok.

Generate speech from text using iFlytek's Spark TTS model locally on Apple Silicon via mlx-audio. Supports Chinese and English with controllable gender, pitch, and speed. Also supports voice cloning from a 3-second reference audio clip. Use when: user asks to "generate Chinese speech", "中文语音合成", "TTS in Chinese", "spark tts", "clone my voice", "read this in Chinese", or needs Chinese text-to-speech locally. Preferred over Voxtral for Chinese/CJK content. Lightweight 0.5B model (~1GB).

Generate speech from text using Mistral's Voxtral TTS model locally on Apple Silicon via mlx-audio. 20 preset voices across 9 languages (English, French, German, Spanish, Portuguese, Italian, Dutch, Arabic, Hindi). Does NOT support Chinese/Japanese/Korean. Use when: user asks to "generate speech", "text to speech", "TTS", "voxtral", "read aloud", "speak this", or needs high-quality multilingual voice synthesis locally. Preferred over cloud TTS for privacy and cost.

Seedance 1.5 Pro video generation via Volcengine Ark API. Supports T2V (text-to-video) and I2V (image-to-video). Use when user says 'seedance api', 'seedance 1.5', 'volcengine video', 'ark video', or '/seedance-api'.

Team-wide luxury fashion advisor. Reads any agent's profile (IDENTITY.md + MEMORY.md), cross-references SS26 runway intelligence, decides what to wear based on day of week + time of day + occasion, then builds the optimised generation prompt. Activates when user says 'what should I wear', 'fashion advice', 'style me', 'outfit today', 'plan my outfit', 'consult luxury brands', 'selfie', or any portrait request. Covers ALL occasions — work, social, travel, holiday, morning through late night. Each agent reads their own workspace. When no occasion or day is specified, the agent makes its own decision based on current day, time, and season.

Review the current conversation history and extract valuable knowledge. Use when the user asks to "learn from this conversation", "summarize what to remember", "extract skills from chat history", or "what should we remember from this session". The skill analyzes the dialogue, identifies reusable knowledge worth storing as memories or skills, and persists them using the memory system.

End-to-end team member lifecycle management: create channel bots (Telegram/Discord), configure AI agents (OpenClaw/EnConvo), pair channels to agents, set up agent2agent mesh, manage group allowlists. Supports ad-hoc add/remove and full team setup from scratch. Self-contained: bundles enconvo-gw, auto-installs OpenClaw, walks through all first-time setup.

Manage Discord applications/bots via Developer Portal API — create/delete apps, set name/description/icon, manage bot tokens, configure OAuth2, intents, slash commands.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Codex's capabilities with specialized knowledge, workflows, or tool integrations.

Manage Telegram bots via @BotFather — create/delete bots, set name/description/about/commands/photo, toggle inline/groups/privacy, get/revoke tokens.

macOS utility toolkit: screenshot capture (select area, current screen, frontmost app, select window). Activates on: screenshot, take screenshot, capture screen, screen capture, select area screenshot, frontmost app screenshot, select window screenshot, or any screenshot request.

Media processing toolkit: image editing/compression, video compression/extraction/downloading, audio compression/transcription. Activates on: image resize, image compress, video compress, extract audio, download video, compress audio, transcribe audio/video, screenshot, or any media processing request.