Borrowing it
Nothing to install: this file belongs to ThreeFish-AI/negentropy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ThreeFish-AI/negentropy/master/.agent/skills/science-video-pipeline/SKILL.mdgit clone --depth 1 https://github.com/ThreeFish-AI/negentropyWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/threefish-ai/negentropy/science-video-pipeline)<a href="https://agentmods.dev/skills/threefish-ai/negentropy/science-video-pipeline"><img src="https://agentmods.dev/badge/skills/threefish-ai/negentropy/science-video-pipeline/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/threefish-ai/negentropy/science-video-pipeline"><img src="https://agentmods.dev/badge/skills/threefish-ai/negentropy/science-video-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01292 |
| Opus 5 | $0.00000 | $0.00646 |
| Sonnet 5 | $0.00000 | $0.00258 |
| Haiku 4.5 | $0.00000 | $0.00129 |
Grade A, and why
science-video-pipeline scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
科普视频制作流水线（导航壳）
本 Skill 是路由层：内容 SSOT 在 apps/negentropy-influence/pipeline/skills/01–09.md，工具 SSOT 在
apps/negentropy-influence/pipeline/scripts/，不在此复制任何正文（防第二事实源）。
九阶段速查
| Stage | 做什么 | 规格链接 | 工具/命令（编排入口 pipeline.py） |
通过门 |
|---|---|---|---|---|
| ① 信源精读取证 | A 型论文：并行子代理逐章 + 官方站点补充；B 型文档/代码/课程站点：固定提交取证 + 证据三级 | 01 | A 型 paper_extract.py（map/text/captions/find/render）；B 型 source_ledger.py（fetch/list/verify/sync/audit——sync/audit 消费系列级 source-map） |
全部断言可回溯；RISKY=0 |
| ② 策划 | 受众/结构/视觉契约（色彩语义） | 02 | — | planning.md 六节齐 |
| ③ 逐字稿 | narration.md ★单一事实源 | 03 | pipeline.py build |
build_narration.py 通过 |
| ④⑤ 双重校验 + 分镜 | 真实性回溯 + 易懂性；beat 覆盖性 | 04 / 05 | pipeline.py check（+--check-scenes） |
RISKY=0；覆盖率无缺句 |
| ⑥ TTS 配音 | 本人音色克隆（IndexTTS-2.5） | 07 | pipeline.py tts --plan |
refs 指纹门 + 试听 + ETA |
| ⑦ Remotion 场景 | 代码动画实现（动效走 src/motion/ 运动模型，分镜动效列 @动词 标注） |
06 | tsc --noEmit + node --test scripts/motion.test.ts |
七条渲染红线 + 运动层铁律 |
| ⑧ 草渲 + 抽帧 QA | 半分辨率快速迭代（--beat-heads 入场瞬态补盲；重制回归 --compare） |
08 | pipeline.py render + qa |
自动体检零 FAIL |
| ⑨ 终渲 + 交付 | 1080p30 + srt/vtt | 09 | render --final + captions |
实测时长在预算窗 |
关键不变量
- 逐字稿只改
narration.md；narration.json/manifest.json是派生物。 - 口播永不出现他集标题与集数序号——顺序只在视觉层与 series.json（校验：
check_series.py）。 多系列（顶层seriesList[]）语义：反串线规则跨系列全局，顺序类规则按系列内判定。 - 证据分级：B 型信源里「他人对闭源产品源码的分析」属三级证据，口播必须带归属句， 不得表述为产品既成事实；活数据（行数、总量、star 数）不进口播。
- 每集
pipeline.toml是可执行参数的唯一来源；README 不复制命令行参数。 - 时序常数只在
video/src/timing.json（timing.ts 与 Python 共读）；运动语汇（时长/缓动/弹簧/错峰）只在video/src/motion/（frozen，改 = 模板 + 8 集同步）。 - 声音样本是生物特征：不入库（
voices/refs.toml只存指纹），试听后即删。 - 新集脚手架与复用边界（Python 集中 SSOT / Remotion 复制不共享）见 pipeline/README.md。
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 36 lines · 0 tokens per session scan A 5922e7ada47e
science-video-pipeline is a skill published in the GitHub repository ThreeFish-AI/negentropy (10 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,292 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-06.
Other skills, from other repositories
Bulk Omics Clustering Analysis
Systematic workflow for clustering biological samples, features, or any quantitative data matrix. Implements multiple clustering algorithms with rigorous validation, comparison, and interpretation to identify meaningful data groupings.
Bulk RNAseq differential expression (DeSeq2)
Core DESeq2 workflow for RNA-seq differential expression analysis with count data.
Single-Cell RNA-seq Core Analysis (Seurat)
Complete workflow for single-cell RNA-seq analysis using Seurat v5. Process raw data through quality control, normalization, clustering, and cell type annotation with publication-ready visualizations.
Experimental Design
Comprehensive workflow for statistical experimental design in genomics, from power analysis and sample size determination to batch-balanced experimental layouts and multiple testing strategy.
Functional Enrichment Analysis (GSEA + ORA)
Translate differential expression results into biological insights using GSEA and ORA.
Genetic Variant Annotation
Annotate genomic variants in VCF files with functional effects, clinical significance, and pathogenicity predictions.