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 lovstudio/skills --skill media-preprocessorgit clone --depth 1 https://github.com/lovstudio/skillsWrote 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/lovstudio/skills/media-preprocessor)<a href="https://agentmods.dev/skills/lovstudio/skills/media-preprocessor"><img src="https://agentmods.dev/badge/skills/lovstudio/skills/media-preprocessor/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/lovstudio/skills/media-preprocessor"><img src="https://agentmods.dev/badge/skills/lovstudio/skills/media-preprocessor.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 | $0.00071 | $0.02951 |
| Opus 5.5 | $0.00028 | $0.01180 |
| Sonnet 5.5 | $0.00014 | $0.00590 |
| Haiku 4.5 | $0.00007 | $0.00295 |
Grade A, and why
lov-media-preprocessor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
视频素材精整 · Video Prep
把原始实录准备成明亮、清楚、按内容组织的可剪辑素材库。交付经过统一增强的分段视频、连续取舍清单、源时间码映射和可选合并版本。原片只读。默认保留内容顺序、原速、原声、画幅、帧率和真实课件，不添加字幕、BGM、Logo 或海报包装。
需要从整场实录继续做独立传播切片时，用 成片交接契约 导出经过文件与时间码核验的 creator-handoff.json 和可直接打开 MP4 的列表，交给 lov-media-creator。完整增强版不等于完成内容选片；该边界不另建 Skill。
Triggers
Activate when
- “这组明亮效果不错，对全片这样处理，并去掉低质量、无意义的部分。”
- “把线下课程实录提亮、分主题切段，保留有内容的讲解和演示。”
- “Help preprocess and segment this recording into enhanced, useful source clips.”
Do not activate when
- 只挑朋友圈照片：交给
lov-video-moments。 - 只要字幕或章节条：使用转录或章节能力。
- 要精剪、动画、包装和发布规格的最终成片：交给
lov-media-creator。 - 上传或发布：另循发布授权；本 Skill 止于本地验收。
Runtime context
每次读取 skill.yaml 与 Profile contract，并执行：
python3 "$SKILL_DIR/scripts/profile_store.py" read --skill-id lov-media-preprocessor
当前请求/参数 → 环境 → 项目上下文 → 本 Skill records → 共享 Profile → 默认值。只保存用户直接要求跨会话复用的视觉目标、剪辑倾向和输出偏好；单次路径、字幕、人物身份和推断值不写长期记录。
python3 "$SKILL_DIR/scripts/profile_store.py" record --skill-id lov-media-preprocessor --path records.visual_style --value '"bright-documentary"' --confirm
保存后报告 canonical Profile 位置。先读 组合边界：这是 Single + 独立 Python CLI，各阶段共享 source/analysis/plan 契约。外部 Skill 只通过文件交接。新增段名和说明使用 branding 门禁；转录、课件与源标识符不改写。
Workflow (MANDATORY)
1. 输入与完成标准
直接使用已提供的视频和已认可的视觉参考。只有缺失信息实质影响结果时，使用宿主 AskUserQuestion 或等价提问工具；不让用户选择技术引擎。
python3 "$SKILL_DIR/scripts/media_preprocessor.py" probe "$VIDEO"
确认时长、音视频轨、尺寸、帧率、色彩标记、源身份和实际可用空间。大原片直接随机定位，不复制几十 GB 到系统盘。先短窗估算速度与体积，再选择足够空间的派生目录；保留源工程的独立轨道。
默认按完整内容单元分段，不固定段数和时长。必须覆盖全片；稀疏采样不能声称逐帧审阅。分别记录分析、转录、增强、语义判断和渲染的实际状态。
2. 校准连续视频的明亮方向
读取 增强契约。以已认可照片的主体清楚、肤色自然、暗部可见和投影可读为目标，选择逆光人物、白色/暗色课件等代表窗口。视频使用保持帧间稳定的摄影处理，不逐帧生图重画人物或文字。
先写含源身份、全覆盖时间线和 grade 的计划，用 render --preview 12 验证代表片段。实际回读输出帧、连续运动和音轨；黑位发灰、皮肤过曝、闪烁或课件不可读要修正。照片风格认可不能替代视频验收。
若用户同时要完整增强版，可在技术索引完成后用 plan --enhancement-only 生成明确不做删减的计划，并独立渲染。此步骤不依赖转录；所有区间标记 review，不能称为完成语义审阅。完整增强版和精简分段版分目录交付。
What ships with it
22 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.
- .gitignore 84 B
- cases/cases.json 1.7 KB
- cases/course-evidence.json 2.6 KB
- CHANGELOG.md 1.3 KB
- LICENSE 1.0 KB
- pricing-card.yaml 471 B
- README.md 3.9 KB
- references/creator-handoff.md 1.9 KB
- references/enhancement-contract.md 2.1 KB
- references/segmentation-contract.md 2.6 KB
- references/skill-card-standard.md 660 B
- references/skill-composition.md 2.3 KB
- references/user-profile.md 2.7 KB
- scripts/check_workflow.py 7.0 KB runs code
- scripts/creator_handoff.py 4.0 KB runs code
- scripts/media_preprocessor.py 39 KB runs code
- scripts/profile_store.py 8.3 KB runs code
- scripts/render_metal.swift 6.5 KB
- scripts/validate_skill.py 26 KB runs code
- skill-card.md 1.7 KB
- skill-card.yaml 3.5 KB
- skill.yaml 1.9 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.
- 1mo ago First seen · 148 lines · 71 tokens per session scan A 30e2010293ef
lov-media-preprocessor is a skill published in the GitHub repository lovstudio/skills (72 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 2,951 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-08.
Other skills, from other repositories
mongodb-connection
Optimize MongoDB client connection configuration (pools, timeouts, patterns) for any supported driver language. Use this skill when working/updating/reviewing on functions that instantiate or configure a MongoDB client (eg, when calling connect()), configuring connection pools, troubleshooting connection errors…
frontend-testing-debugging
Use when testing, debugging, or making targeted improvements to rendered frontend apps through the Frontend Design Skills or web dev plugin: local dev servers, UI regressions, interaction bugs, console errors, responsive layout, and visual QA. Check whether the Browser plugin is available and use it first when it is…
mongodb-search-and-ai
Guides MongoDB users through implementing and optimizing Atlas Search (full-text), Vector Search (semantic), and Hybrid Search solutions. Use this skill when users need to build search functionality for text-based queries (autocomplete, fuzzy matching, faceted search), semantic similarity (embeddings, RAG…
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
web-performance-optimization
Audit, diagnose, or optimize website loading and interaction performance, Core Web Vitals, and Lighthouse performance scores.
grill-design
Decide a UI design by building several genuinely different working prototypes and comparing them side by side, in rounds, until the choice is locked. Use when asked to "grill the design", "design this screen", "show me options", "prototype some variants", "what should this look like", "I can't decide on a layout".