com um clique
georgeskills
georgeskills contém 96 skills coletadas de georgewangyu, com cobertura ocupacional por repositório e páginas de detalhe dentro do site.
Skills neste repositório
Select, score, and source-remap standalone vertical short-form clips from a finished long-form video, creator-edited timeline, transcript, and original camera/audio/screen-recording sources. Use when repurposing a course, podcast, interview, tutorial, livestream, or horizontal A-roll edit into Instagram Reels, TikTok videos, or YouTube Shorts; when the user wants a ranked candidate list before editing; or when an approved long-form cut must be traced back to higher-quality untouched media for vertical reframing.
Direct and execute the visual pass after a short- or long-form talking-head video's A-roll and spoken story are locked. Use when a creator has a versioned A-cut export and wants Codex to apply a creator visual-style profile and produce A-roll punch-ins or reframes, proof assets, B-roll, captions, sound effects, transitions, transcript-anchored full-screen takeovers, diagrams, and Remotion or Manim animation while preserving the locked story. Supports long-form course openings, live Remotion Studio review, full-composite renders, transparent overlay tracks, individual editor assets, and native editor integration.
Umbrella skill for private export and import pipelines. Use this when the task spans multiple data sources or when no more specific export skill applies.
Modular tooling for journal ingestion, prep, and derived-context generation. Use when work involves reusable journal processing logic.
Run IgnitionBot trend sweeps and return scored briefs across configured sources.
Measure the current virality, velocity, and editorial usefulness of a news story, product launch, model release, funding event, or trend. Use when the user asks for a heat score, asks how hot/viral/trending something is, wants to compare competing news waves, decide whether a topic is worth covering now, distinguish mass attention from niche audience fit, or audit why a radar missed a high-signal canonical announcement.
Check X/Twitter using xbot's browser-session GraphQL reader. Use for fast, browserless fetches of For You, Following, user, and search/outlier surfaces without consuming official X API credits.
Create precise programmatic explanatory animations with Manim Community Edition and hand editor-ready assets into a video workflow. Use for math, equations, machine-learning concepts, algorithms, data structures, graphs, geometric transformations, coordinate systems, causal mechanisms, and other explanations where semantic objects must transform with exact timing; keep UI, brand, and text-led motion on Remotion, and use Blender only after an explicit real-3D request.
Design and produce richer visual assets for selected short-form or long-form video beats, including coded motion graphics, diagrams, screen demonstrations, official promo excerpts, generated stills, and generated video. Use when an explicit visual work order needs more explanatory power, novelty, humor, or motion than a screenshot can provide, or when a video asset pack identifies a small number of high-value custom visual opportunities; use the asset-pack skill instead for whole unsorted scripts.
Check a TikTok account or video for public status and recent viewable content, preferring lightweight probes before browser viewing.
Maintain compiled knowledge pages that sit between raw source artifacts and compact structured memory.
Organize recurring short-form video batch production folders, lifecycle state, correctly named empty CapCut draft shells, final-export handling, and owned-platform posting audits. Use when planning weekly TikTok, Instagram Reels, or YouTube Shorts batches; setting up a canonical video project; marking a filmed project active, completed, or dropped; carrying unfinished filmed work into a new week without moving media; the creator says they have new videos or clips in Downloads and gives the video context; asks to move those clips into the current weekly batch and create a properly titled CapCut draft for A-roll; handles CapCut export inboxes with awkward default names; normalizes final video names; creates quick-access final-video indexes; refreshes weekly phone-transfer bundles; or checks which final videos have already been posted.
Archive reference videos from social platforms without putting large media inside active repos. Use when a user wants to download, preserve, transcribe, or keep a reference copy of an X/Twitter, YouTube, TikTok, Instagram, LinkedIn, Product Hunt, or other social/web video; when extracting direct MP4/HLS media URLs from platform metadata; or when creating repo-side provenance notes and symlinks that point to an external raw-media archive.
Turn a settled short-form video script, transcript, or beat outline into a sourced, editor-ready asset pack. Use when editing is about to begin and the project needs screenshots, posts, articles, benchmarks, photos, logos, product UI, official clips, proof receipts, a numbered asset folder, or a beat-to-asset manifest; also use proactively after script lock when the user has signaled that filming or editing is underway.
Orchestrate a short-form video edit through intake lock, narration/A-cut lock, asset and visual planning, editor assembly and persistence, rendered evaluation, and final acceptance. Use when starting or resuming a multi-step video edit, preparing a CapCut or similar editor handoff, handling sponsor/product footage or creator-supplied proof, recovering from repeated correction cycles, or requiring independent content, visual-brand, and technical-audio evaluator subagents before declaring an edit complete.
Audit a first export, near-final render, or locked-A-roll video for visual coverage and overlay quality using its transcript or SRT, asset manifest, and optional read-only editor-metadata snapshot. Use after the A-roll/story is locked or when a user asks to evaluate B-roll, screenshots, overlays, visual pacing, caption collisions, evidence alignment, or unused prepared assets and wants exact timestamped fixes without mutating the live editor draft.
Work with the private Gmail pipeline for export, triage context, scope verification, and lightweight send or reply helpers.
Processes offline audio recordings from an external mic into the daily log pipeline.
Check disk usage on a Mac or Linux machine, surface the largest folders and files, and produce conservative cleanup suggestions with risk framing.
Evaluate and optionally perform conservative macOS disk cleanup and no-restart relief. Use when a user wants recurring Mac storage cleanup, safe-to-delete candidates, cache/log cleanup, startup-freeze triage, launch-agent review, CapCut draft/archive follow-up, APFS/purgeable-space explanation, or a risk-ranked cleanup plan that avoids breaking app state and user data.
Create, update, publish, and verify Cal.com consultation offers, including recurring or one-time schedules, shared availability across multiple event types, positioning copy, intake fields, conferencing, manual or integrated payment wording, and live slot checks. Use when setting up a new consultation product, changing its hours or audience, cloning an existing offer, troubleshooting missing Cal.com availability, or confirming that a public booking page works end to end.
Automate daily X (Twitter) posting by synthesizing content from journal summaries and optimizing for 2026 virality algorithm.
Fetch and analyze GitHub trending repositories (daily/weekly) to surface high-signal development trends.
Modular tooling for structured memory extraction, validation, promotion workflows, and document access/salience indexing.
Scout Product Hunt launches for products, positioning patterns, and market signals.
Scout YC companies, batches, and Launch YC signals for standout startups and market patterns.
Design lightweight eval harnesses for coding or workflow agents, especially when testing whether agents follow steering docs, use tools correctly, preserve user edits, recover from failures, and produce the intended artifact.
Define and enforce proof-before-done gates for agent workflows, automations, integrations, UI changes, and queued work.
Sort raw camera-card clips into the right short-form video project folders. Use when a creator says they filmed several videos on a DJI/camera card or external drive and needs the clips grouped by topic, separator shots, timestamp order, or spoken context into weekly batch folders while preserving raw sidecars such as MP4, WAV, LRF, SRT, or proxy files and writing intake manifests before rough-cut editing.
Turn messy short-form video clips, creator intent, and optional format runbooks into an inspectable edit decision list and rough draft plan for CapCut or similar editors.
Evaluate a frontend with end-to-end checks that combine real user journeys, clickable-control validation, visual screenshots, responsive fit, source/link integrity, and production-preview confidence. Use when a page or app appears functional but may have fake controls, broken navigation, clipped text, invalid links, layout regressions, or browser-specific issues before launch.
Explain and run the Apple Books export workflow that turns local Apple Books highlights, notes, and bookmarks into private markdown drafts. Use when a user asks how Apple Books/iBooks import works, where annotations are stored, how to export Apple Books notes, how to reconcile Apple Books drafts into a books source repo, or how Apple Books data feeds a public Books Radar-style site.
Use when starting or hardening a public website, catalog, radar, directory, companion page, product site, or installable-skill site so the repo has the required README, design contract, agent startup rules, environment contract, intake/lead-capture plan, verification commands, and launch boundary before implementation drifts.
Select source-backed hooks for TikTok, Instagram Reels, and YouTube Shorts. Use for choosing or adapting opening lines, first frames, on-screen text, and retention angles.
Track a private markdown watchlist of niche creator accounts across YouTube, TikTok, and Instagram, then surface new or newly viral videos above an absolute view threshold for format emulation.
Modular Aida workflow bookkeeping and audit tooling.
Export Apple Notes into private markdown artifacts for downstream search, journaling, and context-building workflows.
Produce single-company case studies for small-team, under-the-radar, or narrow-scope products that appear to generate disproportionate revenue; focuses on paid workflow mechanics, ignition events, pricing power, and transferable wedges.
Evaluate and improve public-ready book recommendation notes before they are published to a catalog, reading radar, newsletter, or agent skill. Use when checking whether a book summary, recommendation rationale, reader fit, personal-note synthesis, or copyable markdown is substantive, public-safe, and distinct from raw import metadata.
Find apps or SaaS tools with breakout traction relative to a small apparent starting base.