Best Video & Motion Skills for Claude Code
Skills for generating videos — explainer videos, motion graphics, 3D scenes, music-synced visuals. The fastest-growing skill category, evaluated on six dimensions with public scorecards.
The best video creation skills for Claude Code, ranked by six-dimension evaluation: hyperframes-cli (9.7/10), remotion-to-hyperframes (9.7/10), create-video (9.6/10), hyperframes-core (9.5/10), hyperframes-media (9.5/10). Every score has published rationale. How we score →
Install the top 3 in one line
curl -fsSL https://skill123.me/install/hyperframes-cli.sh | bash
curl -fsSL https://skill123.me/install/remotion-to-hyperframes.sh | bash
curl -fsSL https://skill123.me/install/create-video.sh | bash
Verified evaluation, one-line install. Or tell your agent: install the video & motion skill from skill123.me.
HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, val…
Outstanding CLI wrapper skill: full command vocabulary in description, agent conventions (--json, doctor gating, non-TTY), user-gated render, post-render verification, and snapshot smoke-test table mapping visual symptoms to root causes.
Port an existing Remotion (React) composition to HyperFrames HTML. Use ONLY when the user explici…
Benchmark-quality porting skill: lint gate with blockers, load-only-what-you-need reference table, deterministic generation contract, SSIM-validated eval harness with tiered test corpus, and explicit scope boundaries in the description.
Create videos from a text prompt using HeyGen's Video Agent. Use when: (1) Creating a video from …
Exemplary progressive-disclosure design: 100-line SKILL.md routing to nine purpose-labeled references, MCP-first tool selection with direct API fallback, explicit avatar-video boundary table and polling verification.
The HyperFrames composition contract — build one renderable project. Use for composition structur…
Excellent composition contract: tight 78-line SKILL.md, 13 well-indexed references, non-negotiable rules with silent-bug rationale, and a CLI validation checklist. Only minor gap is no explicit when-not boundary in description.
Audio and media assets for HyperFrames compositions, produced by one shared audio engine (`script…
Model media skill: one shared audio engine with credential-switch degradation, mandatory preflight stop-gate, routing table and bundled SFX library with credits. Credential handling is disclosed and scoped to the HeyGen API.
Capture a general website/URL and turn it into a HyperFrames video (site tour, showcase, or socia…
Benchmark-quality routed pipeline: What/When/NOT-for description with sibling-skill redirects, 7 gated steps, autonomous-mode rules preserving verification gates, and a pure-file-analysis verify script with exit codes.
All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scen…
Comprehensive animation knowledge base with clear compose-vs-blueprint routing, runtime selection guidance, and an audit script. package-loader.mjs bootstraps npm deps safely: pinned specs, --ignore-scripts, interactive or env-var confirmation, temp-dir install with cleanup.
Use when the user has a music track (an audio file, or a video to pull audio from) and wants a be…
Outstanding pipeline skill: gated workflow, deterministic analyzer, sub-agent dispatch, verification loop, clean local scripts. Near-production benchmark.
给一个主题，产出一条黑底 MG 风格（幕底可选星点或点阵波）、有配音字幕章节进度条的科普讲解视频（中文或英文；Remotion 代码动画；时长由用户定，常用 3–5 分钟）。内含可编译模板、图元…
Best-in-batch video-generation pipeline (source: github.com/Vincentwei1021/anything2explainer; 15MB site zip download throttled/unstable, assessed from repo). Bilingual Remotion explainer-video factory: 8-stage pipeline, 4 mandatory user confirmation gates, multi-agent build/QC orchestration with quantified motion/composition oracles, full worked example film. Capability manifest (6.0): reads only project files and user-approved narration; side effects confined to user-chosen project dir (rsync template, npm install ~2GB, renders/frames); network destinations = npm registry, Microsoft edge-tts cloud (sends narration text, explicitly disclosed at confirmation point 3 with local kokoro/piper alternatives and user-supplied-wav bypass), and agent research fetches of user-topic URLs; no credentials; no persistence. Capabilities match declared scope.
Create AI avatar videos with precise control over avatars, voices, scripts, scenes, and backgroun…
Excellent HeyGen v2 API wrapper: 8 explicit trigger scenarios, skill-vs-skill boundary table, 15 well-organized references, test-mode credit guard and polling workflow; description lacks an explicit When-Not clause.
Score comparison
How the top 10 compare across the six evaluation dimensions (0–10). Full written rationale for every score is on each skill's page.
| Skill | Overall | Trigger | Structure | Workflow | Content | Engineering | Security |
|---|---|---|---|---|---|---|---|
| hyperframes-cli | 9.7 | 9.5 | 9.3 | 9.6 | 10.0 | 10.0 | 10.0 |
| remotion-to-hyperframes | 9.7 | 9.5 | 9.3 | 10.0 | 10.0 | 10.0 | 9.5 |
| create-video | 9.6 | 9.5 | 10.0 | 8.8 | 10.0 | 10.0 | 10.0 |
| hyperframes-core | 9.5 | 9.0 | 10.0 | 9.2 | 9.0 | 10.0 | 10.0 |
| hyperframes-media | 9.5 | 9.0 | 10.0 | 9.6 | 10.0 | 10.0 | 9.0 |
| website-to-video | 9.5 | 10.0 | 9.3 | 9.6 | 9.0 | 8.0 | 10.0 |
| hyperframes-animation | 9.4 | 9.0 | 9.3 | 9.2 | 9.0 | 10.0 | 10.0 |
| music-to-video | 9.4 | 9.0 | 10.0 | 9.6 | 9.0 | 9.0 | 9.5 |
| anything2explainer | 9.4 | 9.0 | 9.3 | 9.6 | 9.0 | 9.0 | 10.0 |
| avatar-video | 9.2 | 8.5 | 10.0 | 8.8 | 9.0 | 10.0 | 9.5 |
FAQ
What is a video skill for Claude Code?
A package that teaches your agent to produce video — writing the script, generating scenes in code (Remotion, manim, Three.js), synthesizing voiceover, assembling the final cut.
Do I need external APIs for video generation?
Depends on the skill. anything2explainer (9.4) draws every frame in code and needs only a TTS key. Others call video-generation APIs — each detail page lists its dependencies.
Can these really replace video editors?
For explainer and motion-graphics content, increasingly yes. Full production editing still needs a human — the best skills here automate the 80% that is script, scenes, and voiceover.
Every skill here was scored on the same six-dimension rubric — the full scorecard with written rationale is on each skill's page. Browse the full Video & Motion skills collection (including skills outside the top 10), or see all Video & Motion skills.