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 owenliang60-ship-it/knowledge-mgmt --skill insightsgit clone --depth 1 https://github.com/owenliang60-ship-it/knowledge-mgmtWrote 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/owenliang60-ship-it/knowledge-mgmt/insights)<a href="https://agentmods.dev/skills/owenliang60-ship-it/knowledge-mgmt/insights"><img src="https://agentmods.dev/badge/skills/owenliang60-ship-it/knowledge-mgmt/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/owenliang60-ship-it/knowledge-mgmt/insights"><img src="https://agentmods.dev/badge/skills/owenliang60-ship-it/knowledge-mgmt/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 | $0.00096 | $0.02700 |
| Opus 5 | $0.00048 | $0.01350 |
| Sonnet 5 | $0.00019 | $0.00540 |
| Haiku 4.5 | $0.00010 | $0.00270 |
Grade A, and why
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 10d 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/insights — 商业洞察提取器
从任意文章中提取结构化、可操作的商业洞察。
核心理念
"读文章不是为了知道作者说了什么，而是为了发现作者没说出来的商业逻辑。"
这个 skill 训练的是一个商业分析师的阅读方式：
- 快速抓住文章在说什么（表层信息）
- 深挖背后的商业逻辑和战略意图（深层模式）
- 提炼出可操作的洞察和可迁移的模式（输出价值）
定位
| Skill | 职责 | 输出 |
|---|---|---|
/read |
学术深度阅读 — 论证结构分析 | 学术分析报告 |
/insights |
商业洞察提取 — 战略模式识别 | 结构化商业洞察 |
/note |
知识沉淀 — 原子卡片 | Obsidian 卡片组 |
典型工作流: /insights 分析文章 → 讨论 → /note 存入 Obsidian
⚠️
/insights不写 vault。所有写入由/note的双提议通道统一处理，详见SCHEMA.md§2 / §4。
Behavior
Step 0: 获取文章
根据来源类型获取内容：
| 来源类型 | 处理方式 |
|---|---|
| URL | WebFetch 抓取并解析 |
本地文件 (.pdf, .md, .txt, .html) |
Read 工具读取 |
| Obsidian 关键词 | obsidian search:context query="..." → obsidian read path="..."（CLI 不可用时回退 MCP） |
| 粘贴文本 | 直接分析 |
| 未提供 | 询问用户来源 |
长文处理：超过 5000 字的内容，先快速扫描全文结构，再聚焦关键段落深入分析。
Step 1: 文章定位（30 秒鸟瞰）
快速提取元信息，判断文章类型和分析策略：
📋 文章概况
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
标题：[标题]
来源：[媒体/作者/机构]
日期：[发表日期]
类型：[行业报告 / 深度报道 / 创始人访谈 / 产品分析 / 趋势评论 / 案例研究]
行业：[所属行业]
核心主题：[一句话概括]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Step 2: 核心洞察提取（重点）
这是分析的核心。从文章中提取 3-7 条高价值洞察。
每条洞察必须包含三层：
### 洞察 N：[一句话标题]
**原文信号**：[文章中的关键段落/数据/引言 — 证据来源]
**深层逻辑**：[这个信号背后的商业逻辑是什么？为什么重要？]
**可迁移模式**：[这个模式可以如何应用到其他场景？对我们有什么启发？]
洞察质量标准：
- 不是文章摘要（"文章说了 X"），而是分析性判断（"X 背后意味着 Y"）
- 必须有原文证据支撑，不臆断
- 必须有可迁移性——纯 domain-specific 的事实不算洞察
- 优先提取反直觉和非显而易见的洞察
Step 3: 根据 focus 参数深入分析
focus=general（默认）
输出「商业模式画布」快速扫描：
| 维度 | 发现 |
|---|---|
| 价值主张 | [文章揭示了什么价值创造方式？] |
| 收入模式 | [怎么赚钱？有什么创新？] |
| 竞争壁垒 | [护城河在哪？可持续吗？] |
| 增长引擎 | [靠什么驱动增长？] |
| 风险信号 | [文章中隐含的风险是什么？] |
focus=ai
输出「AI 切入点分析」：
🤖 AI 机会识别
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
## 当前痛点 → AI 解法
| 痛点 | AI 解法 | 技术成熟度 | 预期 ROI |
|------|---------|-----------|---------|
| [痛点1] | [解法] | [高/中/低] | [高/中/低] |
## 价值链 AI 化路径
[识别文章中描述的业务流程，标注 AI 可介入的环节]
## 竞争对手 AI 动态
[文章中提到的竞争对手 AI 布局]
## 建议优先级
1. [Quick Win — 最快能落地的 AI 应用]
2. [Strategic Bet — 需要投入但回报大的方向]
3. [Watch — 值得关注但时机未到]
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.
- 10d ago First seen · 321 lines · 96 tokens per session scan A d842e8dbf16b
insights is a skill published in the GitHub repository owenliang60-ship-it/knowledge-mgmt (37 stars, last pushed 5mo ago), licensed MIT. It adds 96 tokens to every session and 2,700 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
cortex-memory
Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.
heptabase-linking
Create real cross-links between Heptabase cards via the heptabase CLI. Use when the user wants to link Heptabase cards, cross-reference notes, build a card graph, or fix existing [[Card Title]] wiki-link text that is rendering as plain text instead of a clickable card pill. Real links require a ProseMirror card node…
heptabase-cli
Interact with Heptabase using the CLI to create, read, and edit notes, journals, tags, cards, list whiteboards and manage cards on whiteboards, and browse AI Tutor goals, courses, and lessons. Use when the user asks to manage their Heptabase knowledge base, search cards, work with journals, tags, or whiteboards, or…
validate
Check that an Open Knowledge Format (OKF) bundle is conformant with the v0.2 spec (§11). Use when asked to validate, lint, or check an OKF bundle, or before committing changes to one. Runs a deterministic Python checker — not an eyeball pass. Also migrates a v0.1 bundle to v0.2 in place with --migrate.
memex-sync
Sync Zettelkasten cards across devices via git.
council
Multi-persona debate for founder decisions. 4 personas argue a topic across structured rounds.