Render remotion review

Skill bigpowert25-del/render-remotion-review/skill/render-remotion-review

Turn evidence-backed daily reviews, weekly summaries, project retrospectives, or structured status data into a rendered Remotion video with a still preview, MP4 output, and validation evidence. Use when the user asks to make a 复盘视频, 日报视频, 周报动画, project recap video, data-driven vertical video, or Codex plus Remotion animation. Do not use for ordinary manual video editing, unverified marketing claims, or automatic publishing.From its SKILL.md

Install

npx -y skills add bigpowert25-del/render-remotion-review --skill render-remotion-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.8 KB, 495 tokens by cl100k_base, as published. Nobody here has run it

Render Remotion Review

Build a data-driven review video, render it locally, and verify the actual output. Keep facts, inferences, and recommendations distinct in the source data.

Workflow

Gather evidence-backed review data. Do not invent accomplishments, causes, metrics, or priorities.
Read references/data-contract.md, then create review-data.json that satisfies the contract.
For a new project, run:
```
node scripts/scaffold.mjs <target-directory>
```
For an existing Remotion project, reuse its structure and only add the required composition and data contract.

Replace the starter review-data.json, then validate it:

node scripts/validate-review-data.mjs <target-directory>/review-data.json

Install the pinned dependencies and run the project checks. Upgrade Remotion deliberately as one aligned version set; run the dependency audit after any install.
Render a representative still before the full video. Inspect typography, overflow, hierarchy, contrast, and Chinese font fallback.
Render the MP4. Verify duration, dimensions, frame rate, codec, file size, and several frames across the full timeline.
Report the source facts, exact output paths, tests, audit result, and any unsupported features. Do not imply that narration, music, cloud rendering, or publishing exists unless verified.

Output rules

Default to 1080 × 1920, 30 fps, and 20–45 seconds for mobile review videos unless the brief says otherwise.
Use one narrative spine: opening → completed work → problem and lesson → next priorities.
Keep each scene readable as a still; motion must clarify sequence or state change.
Prefer structured props/data over hard-coded claims inside components.
Render locally by default. Publishing, uploading, or sending requires explicit confirmation.
Preserve an auditable still and contact sheet beside the MP4.

Validation gate

Do not report completion until all are true:

data validation passed;
package checks and production bundling passed;
dependency audit has no unresolved critical issue;
still preview was visually inspected;
MP4 was rendered and probed;
beginning, middle, and end frames were inspected;
output contains no credentials or sensitive raw text.

Use the bundled starter as a base, not as a visual identity that must be copied unchanged.

What ships with it: 9 files

9.3 KB alongside SKILL.md, 2 of them executable

agents/

openai.yaml272 B

assets/

references/

data-contract.md863 B

scripts/

scaffold.mjsruns913 B
validate-review-data.mjsruns1.6 KB

Gives 0 of the 12 instructions most review quality skills give in 495 tokens

Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07

Ask questions one at a timein 81 of 1048, across 64 files
Provide a recommended answer for each questionin 73 of 1048, across 50 files
Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
Interview the user relentlessly about the planin 38 of 1048, across 13 files
Order findings by severityin 31 of 1048
Resolve each branch of the decision treein 27 of 1048, across 5 files
Run a grilling sessionin 26 of 1048, across 5 files
Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
Create documentation files lazilyin 24 of 1048, across 5 files
Assign severity to every findingin 24 of 1048

Said here and by no other author read

create review-data.json that satisfies the contract
run scaffold script for new projects
run the review-data validator
run dependency audit after installing dependencies
render a representative still before the video
render the final mp4 locally

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.