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 AlanSong2077/Amplipost --skill bilibili-publishergit clone --depth 1 https://github.com/AlanSong2077/AmplipostWrote 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/alansong2077/amplipost/bilibili-publisher)<a href="https://agentmods.dev/skills/alansong2077/amplipost/bilibili-publisher"><img src="https://agentmods.dev/badge/skills/alansong2077/amplipost/bilibili-publisher/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/alansong2077/amplipost/bilibili-publisher"><img src="https://agentmods.dev/badge/skills/alansong2077/amplipost/bilibili-publisher.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 | $0.00097 | $0.01137 |
| Opus 5 | $0.00048 | $0.00568 |
| Sonnet 5 | $0.00019 | $0.00227 |
| Haiku 4.5 | $0.00010 | $0.00114 |
Grade A, and why
bilibili-publisher 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 12d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
B站专栏自动发布 Skill
使用模式
模式一：内容生成 + 自动发布（推荐）
内容生成由 content-coordinator Agent 负责，Skill 仅执行发布。Agent 生成好标题和正文后，直接调用本 Skill 脚本发布。
模式二：直接发布
用户直接提供标题和正文，跳过生成步骤直接发布。
发布技术流程
1. 启动 Playwright Chromium（持久化 profile，复用登录态）
- 视口固定为 1440x900
- Profile: ~/.catpaw/bilibili_browser_profile
2. 导航到 member.bilibili.com/platform/upload/text/new-edit
⚠️ 注意：URL 是 new-edit，不是 edit
3. 检测登录态 → 未登录则等待手动登录（90s）
4. 等待编辑器 iframe 加载（iframe[src*='read-editor']）
- 轮询检测 iframe 内 textarea.title-input__inner 出现（最多 20s）
5. 通过 frame 对象操作 iframe 内的元素：
- 标题: textarea.title-input__inner（TEXTAREA，不是 input！）
→ fill() + dispatchEvent('input') 触发响应式
- 正文: div.tiptap.ProseMirror.eva3-editor
→ execCommand('selectAll') + execCommand('insertText')
→ 降级：clipboard paste → 逐段 keyboard.type()
6. 话题标签（可选）：button:has-text('添加话题') → 输入框 Enter
7. 截图（发布前确认）
8. 点击发布：iframe 内 button（文字「发布」）
9. 等待成功弹窗：检测「你的专栏已提交成功」文字出现
10. 截图确认
实测验证的关键 selector：
| 元素 | Selector | 说明 |
|---|---|---|
| 编辑器 iframe | iframe[src*='read-editor'] |
所有编辑操作在此 frame 内 |
| 标题输入框 | textarea.title-input__inner |
TEXTAREA，非 input |
| 正文编辑器 | div.tiptap.ProseMirror |
ProseMirror，非 Quill |
| 发布按钮 | button（文字「发布」） |
在 iframe 内 |
| 成功弹窗 | 文字含「提交成功」 | 不跳转 URL |
快速运行
前置安装（首次，在目标电脑上执行）
pip install playwright -i https://mirrors.aliyun.com/pypi/simple/
python3 -m playwright install chromium
CLI 调用
SKILL_DIR=~/.openclaw/skills/bilibili-publisher
# 基础发布
python3 $SKILL_DIR/scripts/bilibili_publish.py \
--title "深度好文：技术人职业规划指南" \
--content "正文内容（800-1500字）..."
# 带话题标签
python3 $SKILL_DIR/scripts/bilibili_publish.py \
--title "标题" \
--content "正文内容" \
--tags "职业规划,程序员,互联网,技术成长"
# 从 JSON 文件读取（推荐，内容较长时使用）
python3 $SKILL_DIR/scripts/bilibili_publish.py \
--content-file "/path/to/content.json"
# 指定截图保存目录
python3 $SKILL_DIR/scripts/bilibili_publish.py \
--title "标题" --content "正文" \
--workspace ~/Desktop
content.json 格式
{
"title": "文章标题（建议30字以内）",
"content": "正文内容（800-1500字）",
"tags": ["职业规划", "程序员", "互联网", "技术成长"]
}
What ships with it
5 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.
- 12d ago First seen · 114 lines · 97 tokens per session scan A 321feefbbfa7
bilibili-publisher is a skill published in the GitHub repository AlanSong2077/Amplipost (45 stars, last pushed 4mo ago), licensed MIT. It adds 97 tokens to every session and 1,137 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…