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 bozhouDev/video-skills-toolkit --skill content-remixgit clone --depth 1 https://github.com/bozhouDev/video-skills-toolkitWrote 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/bozhoudev/video-skills-toolkit/content-remix)<a href="https://agentmods.dev/skills/bozhoudev/video-skills-toolkit/content-remix"><img src="https://agentmods.dev/badge/skills/bozhoudev/video-skills-toolkit/content-remix/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/bozhoudev/video-skills-toolkit/content-remix"><img src="https://agentmods.dev/badge/skills/bozhoudev/video-skills-toolkit/content-remix.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 | $0.00154 | $0.02240 |
| Opus 5.5 | $0.00062 | $0.00896 |
| Sonnet 5.5 | $0.00031 | $0.00448 |
| Haiku 4.5 | $0.00015 | $0.00224 |
Grade A, and why
content-remix 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 2mo 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
内容二创
把“这个爆款为什么成立”迁移成“泊舟凭什么能讲这件事”。二创不是同义改写,也不是把原稿换几个名词,而是保留功能机制、替换事实来源、重新确定内容承诺并按平台原生组织。
必读与调用
每次运行先读:
references/remix-contract.md:输入合同、原创边界、平台适配器、输出格式和保存约定。<NOTES_VAULT>/我的设定/个人创作方向.md:判断是否符合长期定位。<NOTES_VAULT>/我的设定/受众画像.md:确定目标读者和真实需求。
生成成稿时,再读取并遵循:
- 已安装的
bozhou-writing-styleSkill 及其要求的动态偏好。 content-angle:用户没有给出明确新角度时,先确定区别于原内容的角度。hook-writing:生成目标平台标题、封面文案或前三秒钩子时使用。
边界与路由
- 只消费已经选定、已经拆解的样本。只有原链接、原文或逐字稿时,先交给
viral-video-benchmark完成判级、证据化八部分拆解和入库;本 Skill 不跳过上游门禁。 - 正式爆款笔记的
analysis_status必须是current;limited只允许迁移未受缺失证据影响的机制,并明确降低置信度;stale必须先重新拆解。 - 八部分拆解至少要有
可复用点、不能照搬和本账号适配。缺少任一部分时不生成可发布草稿。 - 找新选题用
topic-extract,判断值不值得做用topic-priority,普通改稿用对应写作或润色 Skill,发布后复盘用creator-data-review。 - 本 Skill 只生成二创方案或内部草稿,不发布、不登记 publication、不上传图片、不写飞书、不采集后台数据。
工作流
1. 锁定样本与目标
确认唯一的爆款拆解笔记、platform + post_id、evidence_version、analysis_version、关联母题、目标平台和目标形式。标题不能充当样本身份。
多个样本或多个母题都可能匹配时,列出候选与证据,让用户选择;确认前零写入。一次二创只设一个主对标,其他样本只能作为补充证据。
目标平台未明确时:
- 上下文能唯一推出平台时直接使用;
- 无法唯一推出时先交付二创迁移卡,不同时生成多个平台成稿;
- 小红书默认以图文为主路径,小红书视频只在用户明确指定时生成。
2. 提炼一个主机制
从八部分拆解中选择一个最值得迁移、且本账号具备事实条件的主机制。把它写成与原句无关的功能链,例如:
圈定人群 → 结果前置制造信息差 → 过程证据建立信任 → 方法清单形成收藏理由 → 行动指令承接需求
同时记录:
benchmark_id = {platform}:{post_id};mechanism_id = {benchmark_id}#{简短机制名};mechanism_version = {analysis_version};- 该机制需要哪些一手事实才能成立;
- 发布后什么表现会支持或推翻迁移判断。
不要因为样本数据好,就假定其中每一个表达都有效。观察、传播假设和只能确认相关的指标必须继续分开。
3. 建立原创边界
逐项完成四栏迁移:
- 保留功能:用户需求、钩子功能、信任功能、信息推进和行动功能。
- 删除来源表达:原句、特色比喻、镜头组合、页面设计、叙事顺序和高度可识别的表达。
- 禁止借用事实:原作者身份、经历、客户、收入、结果、评价、数据和素材。
- 注入本账号内容:泊舟自己的经历、项目、截图、流程、判断、失败和产品连接。
出现下面任一情况时,判定原创距离不够,重新构思:
- 标题或钩子只是替换名词;
- 段落、卡片或镜头与原内容逐段一一对应;
- 沿用同一案例、数字、结果承诺或独特比喻;
- 结论与原内容相同,只有语气变化;
- 去掉来源后,剩下的仍能明显反推出原稿表达。
4. 映射一手素材
沿关联选题的 materials、用户指定文件和相关笔记寻找素材。每个“我做过 / 我发现 / 我的客户 / 我的数据 / 我的结果”都必须能回到用户提供的信息或本地来源。
至少具备以下两项,才生成无占位符的完整草稿:
- 一个只有泊舟能提供的一手事实、过程、演示或失败;
- 一个明确属于泊舟的判断,并能说明它与原内容的区别。
素材不足时不得编造。只输出“可迁移机制 + 素材缺口 + 建议补证方式”,或在用户明确接受时生成带 [待补:真实事实] 的内部骨架,并标记“不可发布”。
What ships with it
4 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.
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.
- 2mo ago First seen · 144 lines · 154 tokens per session scan A 10ba621e1525
content-remix is a skill published in the GitHub repository bozhouDev/video-skills-toolkit (159 stars, last pushed 3mo ago), licensed MIT. It adds 154 tokens to every session and 2,240 once invoked, about $0.0006 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 2026-08-30.
content-remix compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| content-remixbozhouDev/video-skills-toolkit | Skill | 159 | 3mo ago | MIT | A | 154 | Codex |
| video-strategy-orchestratoroyi77/1ai-skills | Skill | 17 | yesterday | MIT | A | 96 | Claude Code |
| video-transcriberellmos-ai/skills | Skill | 9 | 4d ago | MIT | A | 48 | Claude Code, Codex |
| video-hyperframesnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 18 | Claude Code, Codex |
| videoRemocn/remocn | Skill | 1.7k | yesterday | MIT | A | 96 | Claude Code |
| studioRemocn/remocn | Skill | 1.7k | yesterday | MIT | A | 72 | Claude Code |
| video-hyperframesnexu-io/html-anything | Skill | 9.4k | 24d ago | Apache-2.0 | A | 22 | Claude Code, Codex |