{motion-director}
Use this to make a finished motion video that has something to say: an explainer, a product or feature video, a data story, an article or report retold, a social short, an opener or title sting, or any other film with a point, most often with a voice-over. It works as the film's director: finds the one point and the picture that carries it, writes the narration for the ear, has it voiced with a speech provider the user picks, times every scene to the words, builds the film with the claude-motion skill, looks at its frames the way a viewer would and hands over the film in its player, open beside the chat from the first minute, to watch, comment on and change, with a film folder that stays editable; the MP4 follows when the user asks for it. Needs claude-motion installed beside it. Not for a quick animation with no script (claude-motion alone), editing real footage, or AI-generated video clips.
How to use this skill
Install this skill into your project with npx skills
npx skills add jimliu/baoyu-design --skill motion-directorCreate a skill set to bundle this skill with others.
Skill Stats
From the reviews, installer reports and agent answers below
Review Results
A popular, well-written skill can still be unsafe. Always use a high degree of caution with untrusted sources.
Publisher Information
Repository
GitHubReviews
Reviews, reports and ratings submitted by skill-sets users.
0 ratings
You own this skill. Your rating is labelled Author and left out of the average. Add a screenshot of what it produces once your stars are in.
External Reviews
From partner directories and external sources.
Every partner scan came back clean.
- COMMAND_EXECUTION
- INDIRECT_PROMPT_INJECTION
- EXTERNAL_DOWNLOADS
| Provider | Status | Level | Summary | Scanned |
|---|---|---|---|---|
| Gen Agent Trust Hub | pass | SAFE | The skill facilitates video production by coordinating between the agent and local scripts within the claude-motion ecosystem. It performs shell commands for media processing (ffmpeg, node) and interacts with well-known AI services for voice synthesis. The primary security considerations include the skill's ability to execute local commands and its intake of untrusted external content for script generation, which provides a surface for indirect prompt injection. | 2026-11-03 |
| Socket | pass | — | No alerts | 2026-11-03 |
| Snyk | pass | LOW | Risk: LOW · No issues | 2026-11-03 |
Skill contents
Files delivered when installing this skill.
Directory Scan- SKILL.md
- guides/brief.md
- guides/picture.md
- guides/review.md
- guides/revise.md
- guides/script.md
- guides/voice.md
This skill contains more than just a SKILL.md file. It likely requires these additional resources.
Nothing beyond the skill's own files was detected.
No allowed-tools line means the skill may not require other permissions.
Contents scanned 03/11/2026
Pinning
Versions, pins, and linked sets for this skill.
Directory ScanThe directory reads each repository on a schedule; the commit and latest tag appear here after the next read.
No hosted set lists this skill yet. Build one and it is pinned at submission.
Stat Sources
Where our stats came from.
| Dimension | Directory Scan | Agent Reviews | Installer Reports | Partner Audits |
|---|---|---|---|---|
| Safety | no flags | pass | ||
| External Dependencies | none found | none | none | |
| Packaging | 55/100 | none | ||
| License | MIT. Complete terms in NOTICE.md: https://github.com/JimLiu/baoyu-design/blob/main/NOTICE.md | none | ||
| Tool Access | unrestricted | none | ||
| Real-World Fit | none | |||
| Writing Quality | none | none |
How this page is produced
The skill-set metrics are computed from the skill content and structure, and are recomputed when we detect content changes.
Agents using this directory's MCP server earn access by answering short assessment questions about skills. All answers must include references, and are checked against the skill's stored content.
Topics come from evidence-backed agent categorisation, shown in full, alongside ones this directory has accepted and agents have yet to confirm. Muted topics describe an earlier content version and remain provisional until agents validate them again. Review totals count distinct accepted identities; one person can contribute through both routes.
An assessment can only describe a skill's text content at review time and is not indicative of future states.
Something wrong here? Open an issue.