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 agentmods add skills/mabzhang/opc-toolkit/platform-adaptationnpx skills add mabzhang/opc-toolkit --skill platform-adaptationgit clone --depth 1 https://github.com/mabzhang/opc-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/mabzhang/opc-toolkit/platform-adaptation)<a href="https://agentmods.dev/skills/mabzhang/opc-toolkit/platform-adaptation"><img src="https://agentmods.dev/badge/skills/mabzhang/opc-toolkit/platform-adaptation.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.01033 |
| Opus 5 | $0.00053 | $0.00517 |
| Sonnet 5 | $0.00021 | $0.00207 |
| Haiku 4.5 | $0.00011 | $0.00103 |
Grade A, and why
platform-adaptation 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.
What it actually says
Platform Adaptation — 平台文案适配
把同一核心信息改写成不同平台“原生”的表达,保持策略一致,但语言、结构、钩子、标签、画面和行动指引按平台变化。
输入拆解
改写前先识别:
- 核心卖点:必须保留的信息。
- 支撑证据:数据、成分、功能、背书、场景。
- 目标人群:谁看、为什么会在意。
- 转化动作:评论、收藏、私信、进店、预约、下单、关注。
- 合规边界:不能夸大、不能绝对化、不能触碰行业禁语。
- 品牌语气:专业、温暖、年轻、理性、幽默、克制等。
如果缺少上述信息,先基于内容合理假设,并在输出末尾列“需确认”。
平台适配逻辑
| 平台 | 用户心态 | 适配重点 | 输出形态 |
|---|---|---|---|
| 抖音 | 快速滑动、即时兴趣 | 前 3 秒强钩子、口语化、画面动作 | 口播脚本、画面分镜、标题、标签 |
| 小红书 | 搜索种草、理性比较 | 标题关键词、真实体验、封面信息、收藏价值 | 标题、正文、封面建议、标签 |
| 微信朋友圈 | 熟人信任、轻表达 | 像朋友推荐,少营销感 | 短文案、配图建议 |
| 微信公众号 | 深度阅读、信任沉淀 | 观点、结构、案例、品牌解释 | 标题、导语、大纲 |
| 视频号 | 私域扩散、直播承接 | 人设、转发理由、直播/社群入口 | 口播、标题、转发语 |
| 微博 | 热点、话题、公共讨论 | 话题感、互动问题、短句 | 微博正文、话题、互动 |
| B站 | 深度内容、圈层语言 | 干货密度、真实测评、弹幕互动 | 标题、大纲、互动点 |
| 快手 | 信任、人情味、实用 | 真实口吻、强场景、朴素利益点 | 口播、场景脚本 |
改写步骤
- 提炼“内容原子”:核心信息、证据、情绪、行动。
- 为每个平台选择一个主钩子,不强行覆盖所有卖点。
- 写平台版本,并补画面/封面/标签/CTA。
- 检查是否过度承诺、是否不像该平台、是否丢失核心卖点。
输出格式
# 平台文案适配
## 核心信息
- 原始信息:
- 保留卖点:
- 目标人群:
- 合规边界:
## 抖音版
- 标题:
- 前 3 秒:
- 口播/脚本:
- 画面建议:
- CTA:
- 标签:
## 小红书版
- 标题:
- 封面文案:
- 正文:
- 标签:
- 收藏理由:
## 微信朋友圈版
- 文案:
- 配图建议:
## 微信公众号版
- 标题:
- 导语:
- 文章大纲:
## 微博版
- 文案:
- 话题:
- 互动问题:
## B站版
- 标题:
- 视频大纲:
- 弹幕/评论互动:
## 适配差异说明
| 平台 | 主要变化 | 为什么 |
|---|---|---|
## 需确认
[缺少的人群、证据、限制或 CTA。]
规则
- 不同平台不能只改称呼和标签;结构也要变。
- 标签少而准,不堆砌。
- 保留核心事实,不为平台风格牺牲真实性。
- 涉及功效、医疗、金融、教育、食品、母婴等高风险行业时,主动降低绝对化表达。
What ships with it
1 file 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.
- 5d ago First seen · 106 lines · 105 tokens per session scan A e89dec3226bf
platform-adaptation is a skill published in the GitHub repository mabzhang/opc-toolkit (3 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 1,033 once invoked, about $0.0005 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
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.
brainstorming
在任何创造性工作之前必须使用此技能——创建功能、构建组件、添加功能或修改行为。在实现之前先探索用户意图、需求和设计。.
chinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用,不要根据上下文自动触发。.
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.
chinese-code-review
中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。.
mcp-builder
MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具,让 AI 助手连接外部能力.