Latest Agent Skills

Updates the dbskill collection from the official repository when the user requests an update, upgrade, or check for updates.

Analyzes why a piece of content resonates with audiences using five classic communication theories, identifies the emotional core and effective stance, and outputs discussion directions for a chatroom.

Merges multiple diagnosis snapshots from dbs-save into a single, timestamped Markdown report organized by topic.

Bridge any skill folder or directory of skill folders to Claude Code, Codex, generic Agents, and Grok using symlinks plus Grok bridge files.

Diagnoses why someone knows what to do but doesn't do it, using Adlerian psychology to identify root causes like procrastination, perfectionism, or avoidance.

Save the current diagnosis state to disk for cross-session recall, including conclusions, rejected directions, and next steps.

Diagnoses short video opening problems and generates actionable optimization plans based on content quality and hook strategies.

Audits fuzzy goals into checkable deliverables using Wittgenstein's philosophy of language, ensuring every word does work.

Routes users to specialized business tools based on their current context: onboarding, pre-task routing, or post-task navigation.

Detects and removes AI writing patterns from Chinese text, making it sound more natural and human-like. Based on Wikipedia's comprehensive guide to AI writing characteristics.

Provides a production-proven oversized macOS-style cursor technique for launch videos, covering size, entry, tip-targeting, click animation, and exit laws to carry the viewer's eye.

Defines the caption model (drop/rail/embed) and overlay law for compositing captions on top of video, never reserving a bottom band.

Port an existing Remotion (React) composition's source to HyperFrames HTML. Use only on explicit requests to migrate from Remotion; for new compositions or uncertainty, use the general HyperFrames skill.

Defines the high-level motion law for multi-scene videos, ensuring seamless transitions and continuous camera movement through vector rules, carriers, causal motion, and seam enforcement.

Turn a weekly changelog markdown into a branded square video with animated UI mockups, voiceover, and captions.

Creates seek-safe 2D/3D keyframe animations using GSAP, CSS, Anime.js, WAAPI, FLIP, SVG morph/draw, and text trails for HyperFrames compositions.

Provides atomic motion rules, multi-phase scene blueprints, scene transitions, motion-design techniques, and runtime adapters (GSAP, Lottie, Three.js, Anime.js, CSS, WAAPI, TypeGPU) for composing animations with HyperFrames.

Provides a catalog of cinematic transition techniques (zoom-through, cut-the-curve, waterfall cut, etc.) with GSAP parameters for velocity-matched seams and in-scene motion.

Turn a product URL, script, or brief into a polished launch video with brand assets, storyboard, and frame-by-frame animation.

Install, discover, and wire reusable blocks and components into HyperFrames compositions using the CLI.

Provides creative direction for HyperFrames videos, handling design specs, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand/style decisions.

Packages an existing talking-head, interview, or podcast video with timed, designed graphic overlay cards—kinetic titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture—synced to the transcript, on a 16:9, 9:16, or 4:5 canvas.

Turn any text into a faceless explainer video with typography, abstract graphics, diagrams, and data visualization.

Ensures scene-to-scene transitions composite correctly on the master timeline by defining render prerequisites, including the white-flash guard and how the injector overlaps wrappers.

Add captions or subtitles to a single-subject talking-head video without editing the footage, using a catalog of visual identities.

Build a single renderable HyperFrames composition using HTML with data-* timing attributes, clips, tracks, sub-compositions, variables, and deterministic rendering rules.

Creates short, design-led motion graphics like kinetic typography, data visualizations, logo reveals, and animated maps, rendered as MP4 or transparent overlays.

Run the HyperFrames CLI to scaffold, author, lint, preview, render, and publish video compositions locally or on HeyGen Cloud, AWS Lambda, and Google Cloud Run.

Turn a music track into a beat-synced video — lyric video, slideshow, or kinetic promo — with optional user-supplied images or videos cut onto the same beat grid.

Creates or edits custom video compositions using HyperFrames, supporting multi-scene pieces, brand reels, montages, and freeform builds with media, Figma, and creative treatments.

Turns a GitHub pull request into a code-change explainer video with changelog, feature reveal, or refactoring walkthrough built from the diff, commits, and files.

Creates, edits, and renders videos and animations from HTML compositions using the HyperFrames framework, handling project state, input adaptation, and workflow routing.

Author a HyperFrames slideshow — a presentation, pitch deck, or interactive deck with discrete slides, fragment reveals, branching, hotspot navigation, and built-in presenter mode with speaker notes; also converts an existing page into a deck.

Resolves, generates, and operates on media assets (audio, images, icons, logos, voice, color grades, LUTs) for HyperFrames projects, using a local cache and the HeyGen CLI for free-usage catalog search and TTS.

Import Figma designs into HyperFrames compositions as frozen assets, brand tokens, components, motion animations, and shaders.

Guide a visible, verified code walkthrough in Neovim with Terminal Control and Navi, optionally recording the presentation with OBS or retaining terminal evidence.

Provides opinionated defaults and reference documentation for building production TypeScript applications with Effect v4, covering schemas, services, layers, configuration, scheduling, caching, streams, HTTP clients, and testing.

Fine-tune Gemma models locally using QLoRA, Unsloth, or TRL for SFT, DPO, and reward modeling, with dataset preparation and conversion to GGUF or LiteRT-LM.

Selects the right Gemma model for a task, recommends deployment tooling (Gradio, Transformers.js, Vertex AI, MLX), and applies optimizations like MTP and QAT.

Polls a local relay for animation-refinement jobs from the Timeline Inspector, posts suggestions or applies changes to transition code.

Polishes existing motion against the transitions.dev motion-token scale by auditing duration, distance, scale, blur, and easing values and suggesting token-based corrections.

Provides portable CSS transitions for common UI patterns like dropdowns, modals, tooltips, and skeleton loaders. Each transition is a drop-in snippet with semantic CSS custom properties and a prefers-reduced-motion guard.

Provides a searchable database of UI/UX design rules with priority-based recommendations across 84 styles, 192 color palettes, 74 font pairings, 192 product types, 98 UX guidelines, 104 icon entries, 16 GSAP motion presets, and 25 chart types for 22 technology stacks.

Creates and manages design tokens with a three-layer architecture (primitive, semantic, component), generates CSS variables and component specifications, and produces brand-compliant slide presentations with Chart.js integration.

Design banners for social media, ads, website heroes, and print with multiple art direction options and AI-generated visuals.

Create beautiful, accessible user interfaces with shadcn/ui components, Tailwind CSS utility-first styling, and canvas-based visual designs.

Create strategic HTML presentations with Chart.js, design tokens, responsive layouts, copywriting formulas, and contextual slide strategies.

Creates brand identities, logos, corporate identity programs, presentations, banners, icons, and social media images using AI generation and HTML/CSS design.

Defines and manages brand identity including voice, visual standards, messaging frameworks, asset organization, and consistency audits.

Generates a comprehensive narrative report analyzing a project's entire development history from claude-mem's persistent memory timeline.

Build and query AI-powered knowledge bases from claude-mem observations, enabling focused conversational sessions on specific topics.

Generate a serial, multi-chapter narrative digest of a project's claude-mem history, producing one digest per ISO week with coherent story flow across chapters.

Reads every source file in a codebase to build a deep understanding of the project, using pagination for large files.

Explore codebases efficiently using AST-based structural search, outline, and symbol unfolding to reduce token usage.

Automates semantic versioning and release workflow for Claude Code plugins, including version increments across multiple manifest files, build verification, git tagging, GitHub releases, and changelog generation.

Clusters a GitHub issue backlog by root cause into plan-master issues, redirects children with a standardized comment, and bundles architectural-fix PRs that close clusters atomically.

Explains how claude-mem captures observations from Read, Edit, and Bash actions, when memory injection activates, and where data is stored locally.

Converts a single document into a kawaii-themed slide-deck PDF using NotebookLM, with an optional share link via the WOWerpoint Server.

Maps a codebase into feature-grouped flowcharts, identifies duplicated concerns across features, and proposes a unified architecture with handoff prompts for refactoring.

Search and retrieve past work from claude-mem's persistent cross-session memory database using a three-layer workflow: search, timeline, and fetch.