Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kezd088/100x-skill-tiktok --skill 100x-video-reversegit clone --depth 1 https://github.com/kezd088/100x-skill-tiktokWrote 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/kezd088/100x-skill-tiktok/100x-video-reverse)<a href="https://agentmods.dev/skills/kezd088/100x-skill-tiktok/100x-video-reverse"><img src="https://agentmods.dev/badge/skills/kezd088/100x-skill-tiktok/100x-video-reverse/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/kezd088/100x-skill-tiktok/100x-video-reverse"><img src="https://agentmods.dev/badge/skills/kezd088/100x-skill-tiktok/100x-video-reverse.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00128 | $0.02249 |
| Opus 5 | $0.00064 | $0.01125 |
| Sonnet 5 | $0.00026 | $0.00450 |
| Haiku 4.5 | $0.00013 | $0.00225 |
Grade A, and why
100x-video-reverse 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 11d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
100X Video Reverse v2.3
把参考视频转成用户可直接审阅、下游生成 Skill 可消费的标准反推包。默认只分析和验证，不调用付费生成、不上传原视频、不发布素材。
开始前
- 确认用户提供的视频可读和授权边界。用户未指定输出目录时，直接使用当前工作区下
outputs/100x-video-reverse/<video-stem>-<timestamp>/，不为目录选择额外追问；始终只读源文件并输出到新的独立目录。 - 始终阅读 workflow.md、output-contract.md 与 native-output.md。进行模型分析时再读 analysis-prompt.md。涉及商业文案、密集剪辑、外部上传或准备交给生成环节时读 failure-gates.md。只有评估、替换或升级本 Skill 时才读 golden-baseline.md。默认交付由
scripts/digest.py从机器包确定性生成，Agent 不手工重排片段。 - 检查
ffmpeg、ffprobe、Pythonjsonschema和本地读写权限。缺少jsonschema时验证器必须硬停止；只在隔离环境补依赖，不做全局安装。调用任何外部模型前，实时核对官方模型列表和输入限制；用户指定模型优先。不能核实时停止外部调用，但继续完成本地证据包。
执行流程
- 用
scripts/prepare_evidence.py建立源文件指纹、规格、双阈值切点提议、稠密帧和独立音轨。自动切点只是诊断信号，不是真实镜头边界。 - 同时查看完整视频与证据包，优先使用当前 Agent 已有的本地媒体理解能力，不要求用户另配 API。只有当前任务已明确授权外部语义分析时，才可沿用金样的 Google 官方
gemini-3.7-flash；调用前必须从官方模型列表核实真实 ID 和视频输入能力，不可用时保留原始错误并停止外部阶段，不静默换旧模型。按references/analysis-prompt.md校正镜头时间轴，区分可观察事实、推断和未知，不以固定间隔代替语义切镜。 - 建立稳定资产 ID 和跨镜头一致性锚点，覆盖人物、商品、场景、道具、服装、音频与文字。看不清或听不清的品牌、价格、功效、台词和屏幕文字不得补写。
- 生成完整的
reverse.json：镜头、四类关键帧、资产引用、音频/字幕、通用提示词、模型适配提示词、分段方案、拼接说明和must_not_change。每个分段还要包含execution_plan：目标时长、生成状态、选定模型、生成方式和输入素材；没有实时核实模型能力时明确写needs_model_selection，不得伪装成可执行。 - 用
scripts/materialize_reverse_media.py将镜头帧和资产截图物化到包内相对路径，并生成materialization_manifest.json。已有媒体只有在源 SHA-256、请求时间戳和文件 SHA-256 全部匹配 provenance 时才复用；否则硬停止，不覆盖。 - 用
scripts/validate_reverse_package.py做媒体与契约预检。硬错误必须修复后才能继续；警告必须保留并解释，不能改成通过。 - 严格验证通过后运行
scripts/digest.py，再按 native-output.md 原样交付。Codex 使用--format fragment --fragment-dir <本轮 thread 可视化目录>：首 tab 是左侧窄 9:16 播放器 + 右侧分段素材板，每段固定同组展示首帧／高光帧／尾帧；图片可拖出 JPEG 预览，需要原图时复制包内原帧路径。“镜头定位”保留逐镜联动，点击任一三帧或镜头都会暂停并定位视频，先显示中文操作说明，再显示所属分段的英文生成提示词。窄屏改为上下结构但三帧仍同组。其他客户端默认使用--format md；判断不了客户端能力时不得赌内联协议。
用户给出观看反馈时，把每条反馈映射到具体镜头、资产或提示词字段，并明确标为“用户偏好/修正”，不要反写成源视频观察事实。新建修订包，只改受影响字段和媒体，再完整验证；不覆盖上一版。
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 374 B
- axioms.md 5.0 KB
- evals/example-01-synthetic-product-demo.json 11 KB
- metadata.json 3.2 KB
- package-lock.json 2.3 KB
- package.json 327 B
- references/analysis-prompt.md 2.9 KB
- references/failure-gates.md 4.0 KB
- references/golden-baseline.md 6.1 KB
- references/native-output.md 11 KB
- references/output-contract.md 5.6 KB
- schema.json 14 KB
- scripts/digest.py 124 KB runs code
- scripts/materialize_reverse_media.py 15 KB runs code
- scripts/prepare_evidence.py 17 KB runs code
- scripts/test_digest.py 5.4 KB runs code
- scripts/validate_reverse_package.py 38 KB runs code
- scripts/validate.js 14 KB runs code
- sources.md 2.7 KB
- workflow.md 6.0 KB
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.
- 11d ago First seen · 65 lines · 128 tokens per session scan A 10624965caa0
100x-video-reverse is a skill published in the GitHub repository kezd088/100x-skill-tiktok (8 stars, last pushed 15d ago), licensed MIT. It adds 128 tokens to every session and 2,249 once invoked, about $0.0006 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.