All authors
Claude Skills by broomva
github.com/broomva112 skills0 installs5 views
- Content Engine CinemaCinematic Generation Layer — the taste and technique library for premium AI content. Codifies start-frame doctrine, camera style vocabulary (Anderson/Fincher/Nolan/Villeneuve/Kubrick), node pipeline architecture, scene generation formulas, and 25+ design styles with exact prompts. Tier-1 generation via Higgsfield CLI (30+ models — Soul V2, Nano Banana 2, Veo 3.1, Kling 3.0, Seedance 2.0, Flux 2, Marketing Studio). Triggers on: 'generate content', 'cinematic', 'create scene', 'start frame', 's...Votes: 0GitHub stars: 4
- Content Engine DnaVisual DNA Compiler -- compiles raw brand assets, character references, and style inspiration into persistent, structured identity files. Uses Gemini multimodal analysis to extract color palettes, composition rules, lighting patterns, and texture preferences. Generates tool-specific prompt fragments for Nano Banana Pro, Soul Cinema, Weavy, and ComfyUI. Inspired by Karpathy's LLM Wiki (compile-then-query) and MemPalace spatial hierarchy. Triggers on: 'compile brand', 'extract DNA', 'character ...Votes: 0GitHub stars: 4
- Content Engine LoopContent Loop + Distribution — compounds existing broomva skills into a unified content lifecycle. Orchestrates /blog-post, /content-creation, /social-intelligence, /brainrot-for-good, and /brand-icons for multi-platform distribution. Adds performance tracking, feedback-driven identity refinement, content calendar, and campaign management. Triggers on: 'distribute content', 'content loop', 'publish campaign', 'content calendar', 'track performance'.Votes: 0GitHub stars: 4
- Creative ReviewMeta-review skill for validating generated creative assets (videos, images, designs) against a reference style brief. Extracts frames, compares against style criteria, scores adherence, and produces actionable feedback for iteration. Self-improving feedback loop: each review refines the style brief for the next generation. Use when: (1) reviewing a generated video against a reference style, (2) validating visual quality of AI-generated content, (3) scoring style adherence of a Remotion compos...Votes: 0GitHub stars: 4
- Launch VideoProduce polished product launch videos using the Liquid Glass aesthetic — dark void backgrounds, 3D perspective floating UI panels, particle effects, spring animations, and cinematic pacing. Built on Remotion with Imagen 4.0 for frames and Veo 3.1 for B-roll. Use when: (1) creating a product demo or launch video, (2) showcasing a UI/app/tool with cinematic polish, (3) building a social-ready video from screenshots and renders, (4) applying the liquid glass floating panel style, (5) composing ...Votes: 0GitHub stars: 4
- Ltx VideoSet up, configure, and run LTX-2/LTX-2.3 (Lightricks) for AI video and audio generation. Use when: (1) Installing LTX-2 locally or via ComfyUI, (2) Generating video from text, image, audio, or keyframes, (3) Running inference with the 22B dev/distilled models, (4) Fine-tuning with LoRA/IC-LoRA, (5) Configuring upscalers (spatial/temporal), (6) Optimizing VRAM usage (FP8, quantization, low-VRAM modes), (7) Building content-generation pipelines with LTX-2, (8) Writing prompts for video generati...Votes: 0GitHub stars: 4
- Video CutEdit raw footage into a finished cut by conversation, fully local. Drop clips in a folder, describe the video you want, get edit/final.mp4 back. Local-first raw-footage video editor — the editorial counterpart to the generative Remotion/launch-video skills. Uses a two-layer reading system (local faster_whisper word-level transcript + on-demand timeline_view composite) so the agent cuts with word-boundary precision without ever dumping video frames — llm-as-index applied to video. Swaps cloud ...Votes: 0GitHub stars: 4
- SkillFixture skill. Exists only so the eval harness has an artifact to bind its committed replay fixtures to, and so CI grades a real prompt set instead of only asserting that an empty fixture set fails. Triggered by the four cases in evals/prompts.json and by nothing else. NOT FOR any real task: it does nothing, and no agent should ever load it outside tests/skill_evals/.Votes: 0GitHub stars: 4
- Forkable ShellGives an agent session a disposable, sandboxed bash shell whose entire filesystem is a single JSON file — so the workspace can be snapshotted, forked, branched and resumed at ~0.24ms per fork instead of seconds per container. Backed by just-bash (in-process, no VM, no container, no host access). Use when you want to run agent-generated shell commands without giving them a real machine, checkpoint an agent workspace, fork one workspace into N parallel branches to try competing approaches, resu...Votes: 0GitHub stars: 4
- Ctx CoreThe shared context core, phase 1: a read-only shared board for every Claude Code session in a workspace scope. Hooks publish each session's start, the keyword of its ARC-STATUS line at every Stop, and its death on StopFailure to one append-only log per scope, as structured fields only. A SessionStart hook injects a short factual brief of the board rows for the session's branch and cwd, including other live sessions on the same branch. Sessions in different worktrees therefore see each other w...Votes: 0GitHub stars: 4
- Fleet ReconcileThe hourly fleet coordinator. Phase 1 observes and classifies, report only; phase 2 adds the coordinator and its verbs under dry run. Each tick reads every Claude Code session (claude agents --json --all and the background job files), Paseo's agent records and schedules from disk, the ctx-core board, transcript times, and GitHub (open PRs and the effective branch rules of every repo in the scope). It classifies each session with the spec's class table, runs the count check, inventories schedu...Votes: 0GitHub stars: 4
- Mod AnythingChange or extend software or a device the user owns but whose source they don't control (a desktop app, a website, a game, a device protocol, a CLI) by the cheapest route that reaches the idea. The running original is the oracle, a journal and a stall breaker keep long runs honest, and every run ends in a field note for the next agent. Generalizes rehan-remade/universal-modder's mod-any-game method beyond games. USE WHEN the user wants an app or site to do something it doesn't, to add a featu...Votes: 0GitHub stars: 4