All Skills

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.

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

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

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

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

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

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.

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

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.

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

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

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.

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

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

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

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

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

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.

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.

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.

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

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

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

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

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

Diagnoses how to turn a confirmed content topic into effective content, covering format matching, five-dimensional quality assessment, and actionable next steps.

Restores the most recent diagnosis snapshot saved by dbs-save, allowing users to continue a previous diagnostic session.

Turns any long-running domain (business, relationships, health, career, learning, investing) into a local knowledge project with four layers, source tags, immutable snapshots, and a concept library that learns patterns over time.

Breaks a topic into a sequence of adaptive learning articles, adjusting depth and pace based on user feedback from the previous lesson.

Diagnoses whether a draft will resonate with its audience using a five-dimension communication psychology framework, identifies structural problems, and gives specific fixes.

Turns a local folder into a searchable, maintainable knowledge base for AI agents, handling setup, navigation, content ingestion, querying, and health checks without external databases or RAG systems.

从 75 个验证过的爆款公式中，为小红书内容匹配最合适的标题公式，生成定制标题并解释选择理由。

Diagnoses whether a user's current approach is trading short-term speed for long-term pain, and recommends slower methods that build compoundable assets through friction.

Converts Markdown into HTML formatted for WeChat Official Account publishing, with 15 built-in styles.

Transforms fuzzy problems into structured briefs that AI agents can reason about, critique, and act upon, while evaluating how much of the problem can be automated.