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 chengkj99/kj-skills --skill extract-conversation-insightsgit clone --depth 1 https://github.com/chengkj99/kj-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/chengkj99/kj-skills/extract-conversation-insights)<a href="https://agentmods.dev/skills/chengkj99/kj-skills/extract-conversation-insights"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/extract-conversation-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/chengkj99/kj-skills/extract-conversation-insights"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/extract-conversation-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 | $0.00147 | $0.01845 |
| Opus 5 | $0.00073 | $0.00923 |
| Sonnet 5 | $0.00029 | $0.00369 |
| Haiku 4.5 | $0.00015 | $0.00185 |
Grade A, and why
extract-conversation-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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
录音对话价值挖掘
把录音或转写稿作为定性证据处理，执行“保真 → 观察 → 假设 → 质疑 → 洞见 → 内容/行动 → 沉淀”闭环。保留不确定性，不把单次聊天包装成普遍真理。
先划定边界
- 读取目标仓库的
AGENTS.md、CLAUDE.md或其他写入规则。 - 确认输入是音视频、原始转写、整理稿还是已有纪要。
- 输入只有音视频时，优先调用可用的 STT Skill；若无法转写，如实说明，不臆造内容。本 Skill 不重复实现 STT。
- 保留原文件不变。需要可读稿时新建整理稿，不覆盖原始转写。
- 默认把私人聊天标为
private；公开复用前匿名化，并排除身份、职业、收入、家庭及其他可识别细节。 - 只在用户授权的目标中写文件。遵守只读、只追加与人工确认门闩。
选择工作深度
| 模式 | 适用请求 | 产物 |
|---|---|---|
| 快速扫描 | “这段录音有什么价值” | 关键观察、风险、Top 3 洞见/行动 |
| 标准挖掘 | “整理、质疑并沉淀” | 完整提炼卡、内容候选、行动实验、落盘 |
| 跨录音综合 | “对比多次聊天找模式” | 跨源模式、矛盾、证据强度、综合结论 |
用户未指定时采用标准挖掘。材料过长时先建立主题/说话人覆盖清单，再分段处理，最后跨段综合。
核心流程
1. 建立保真层
记录日期、场景、参与者（可匿名）、来源路径、隐私级别与处理目标。区分：
- 原始录音：最高保真证据。
- 原始转写：允许口头语和识别错误，供回查。
- 整理稿：只修断句、明显识别错误和无意义重复；不改立场，不补造内容。
- 提炼卡：保存观察、假设、质疑与去向。
需要详细保真、证据等级和隐私规则时，读取 references/analysis-framework.md。
2. 提取原子观察
输出 5–10 条最有价值的观察。每条必须：
- 只描述明确听到的原话、行为、故事或分歧。
- 附时间戳、段落号或可搜索的短语锚点。
- 标注
direct_quote、paraphrase、reported_claim或uncertain。 - 将解释写在独立字段，不混入观察。
没有证据锚点的句子不能进入洞见主链。
3. 聚类并形成假设
按主题、痛点/张力、期望结果、证据性质和复用等级聚类。只有多个观察形成关系时才写“模式”；解释模式原因时先标记为“待验证假设”。
对每个假设写清：
- 主张是什么。
- 哪些原子观察支持它。
- 它是单人经验、多人重复还是已有外部证据。
- 什么情况会使它不成立。
- 还缺什么证据。
4. 执行质疑门禁
对准备进入知识、内容或行动的每个主张逐项追问：
- 这是原话、转述还是我的解释？
- 是否把单一个案当成普遍规律？
- 是否把相关性或结果倒推成因果？
- 有什么反例或替代解释？
- 是否为追求“反常识”而夸大？
- 什么证据能证伪它？
- 公开表达是否泄露隐私或制造不必要焦虑？
无法回答时降低证据等级，保留为线索，不写成确定结论。
5. 转化为四类资产
不要强迫每份录音产出所有资产。只晋升有证据、有价值的部分。
| 资产 | 判断标准 | 最小产物 |
|---|---|---|
| 知识 | 可跨场景复用，边界清晰 | 概念、方法、来源摘要或综合判断 |
| 内容 | 有读者痛点、张力、案例和独立判断 | 1 个主选题 + 2 个分发角度 |
| 行动 | 能验证关键假设，而非泛泛待办 | 假设、实验、指标、成功/失败阈值 |
| 关系 | 对当事人有明确后续价值 | 一个问题、资料或约定的跟进 |
内容候选必须写清：读者痛点、反常识点、原始证据、反例/边界、隐私风险、与已发布内容的连接、下一集钩子。
行动不得只写“继续研究”。优先设计一周内能支持或推翻假设的最小实验。朋友的赞同只能验证表达是否清楚，不能证明付费需求。
6. 评分并路由
每项 1 分：真实证据、明确痛点/张力、机制解释、案例/反例支撑、已有内容连接。
0–1：只保存原文或私密纪要。2–3：进入知识卡/选题种子，标记待验证。4–5：可进入内容队列或行动实验，仍需隐私与事实检查。
读取 references/sink-routing.md，选择目标仓库的实际路径。若用户只要分析，不做写入；若用户明确要求沉淀，则完成落盘、索引和日志，不把结果只留在聊天中。
7. 输出与复核
标准输出必须包含：
- 来源与隐私说明。
- 原子观察表（含证据锚点）。
- 假设与质疑卡。
- 可晋升知识、内容、行动、关系资产。
- 不可公开内容。
- 实际写入路径或建议去向。
- 不确定项与待补证据。
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.
- 12d ago First seen · 134 lines · 147 tokens per session scan A e47cfc493fad
extract-conversation-insights is a skill published in the GitHub repository chengkj99/kj-skills (14 stars, last pushed 11d ago), licensed MIT. It adds 147 tokens to every session and 1,845 once invoked, about $0.0007 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…