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 oyorf/personal-workbench-skills --skill research-social-insightsgit clone --depth 1 https://github.com/oyorf/personal-workbench-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/oyorf/personal-workbench-skills/research-social-insights)<a href="https://agentmods.dev/skills/oyorf/personal-workbench-skills/research-social-insights"><img src="https://agentmods.dev/badge/skills/oyorf/personal-workbench-skills/research-social-insights/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/oyorf/personal-workbench-skills/research-social-insights"><img src="https://agentmods.dev/badge/skills/oyorf/personal-workbench-skills/research-social-insights.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 | $0.00102 | $0.01627 |
| Opus 5 | $0.00051 | $0.00813 |
| Sonnet 5 | $0.00020 | $0.00325 |
| Haiku 4.5 | $0.00010 | $0.00163 |
Grade A, and why
research-social-insights 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Social Insights
目标
把公开中文网页和用户已授权登录后可见的中文社媒页面，整理成可复查的本地研究报告。此 Skill 只在用户主动触发时运行，不创建定时任务，不让 Workbench 保存平台登录态，也不自动生成选题。
先确定目标知识库根目录。优先使用用户明确提供的路径，其次读取 PERSONAL_DASHBOARD_VAULT_ROOT。仍无法确定时先询问用户，不猜测用户名、主目录或知识库名称。目标目录必须允许创建 10_raw/social-insights/。
开始时必须明示：本次模式、时间范围、将实际读取的来源类型、最终产出位置和下一步。结束时说明真实覆盖、未能可靠读取的来源、结论边界和报告路径。
两种模式
根据用户目的只选择一种模式：
trend-scan：回答“最近大家都在干什么、聊什么、争什么”。同义触发包括近期风向、趋势雷达、最近 7 天 AI 圈在做什么、哪些主题突然变多。完整流程见 trend-scan.md。topic-deep-dive：围绕一个明确主题研究延伸子题、观点阵营、评论与回复、需求、痛点、反例和新闻背景。完整流程见 topic-deep-dive.md。
“刷新”只是用新的捕获时间重新运行同一模式，不是第三种模式。若意图仍不明确，默认：有明确主题用 topic-deep-dive；否则用 trend-scan，范围为 AI，时间窗为最近 7 天，深度为标准。
固定执行流程
1. 确认任务合同
若目标知识库存在 AGENTS.md，先读取并遵守。然后从用户指令提取：
- 模式；
- 主题或范围；
- 研究问题；
- 时间窗；
- 深度：快速、标准或深度；
- 用户点名的平台或来源。
Workbench 生成的交接文本是任务输入，不代表已执行。不得声称 Workbench 已提交、后台已运行或结果已生成。
2. 制定查询与来源计划
先把主题拆成实体、动作、问题、别称、反向表达和相邻概念，再选来源。来源分工与读取边界见 source-policy.md。至少区分：
- 国内官方或一手事实来源；
- 国内科技新闻与中文行业报道；
- 国内中文社媒内容；
- 一级评论与二级回复。
对近期事实和产品变化优先联网核实，并优先使用 source-policy.md 列出的中文来源。公开网页使用当前 Agent 可用的网络搜索与打开能力；需要登录或交互才能读取的国内社媒页面，在 macOS 上使用 Ego Lite 提供的 ego-browser，复用用户已有登录态。不得尝试绕过登录、验证码、反爬或访问权限。
Ego Lite 当前不支持 Windows 或 Linux。在这些平台上使用可靠的中文公开网页，将缺少的登录态社媒覆盖写进证据边界，并把报告状态按实际质量降为 partial 或 needs-review；不得声称完成了完整的跨平台登录态扫描。
国内平台职责、来源分工、Ego Lite 登录态复用、独立来源判定、转载去重、代表性边界与失败降级统一以 source-policy.md 为真源。trend-scan 的发现顺序、候选门槛、深度档位和时间序列用词边界统一以 trend-scan.md 为真源，不在 Workbench 交接文本或其他运行入口复制这些策略。
3. 收集与留痕
中间抓取、临时截图、候选列表和解析文件放在系统临时目录。只有最终报告写入 10_raw/social-insights/。不要把浏览缓存、低价值候选或失败页面长期写进 Vault。
可靠读取失败的内容不进入结论，不推测正文、评论或回复。只在证据边界中记录失败的来源类型和排除原因。昵称、头像、用户 ID、地区和其他可识别个人信息默认不进入报告。
4. 分析
遵循 comment-analysis.md 和 quality-gates.md：
- 事件、行动和讨论分开；
- 事实、用户观点、作者观点、AI 综合推论分开；
- 一级评论和二级回复保持链路；
- 聚类后保留反方、小众声音和内部冲突；
- 不把互动量等同支持率，不把可见评论当总体民意；
- “趋势”必须有时间变化或多源趋同证据；只有单次横截面时写“当前风向”。
What ships with it
8 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 · 105 lines · 102 tokens per session scan A f8ee314bd2fb
research-social-insights is a skill published in the GitHub repository oyorf/personal-workbench-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 1,627 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
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…