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 knowledge-mapgit 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/knowledge-map)<a href="https://agentmods.dev/skills/chengkj99/kj-skills/knowledge-map"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/knowledge-map/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/knowledge-map"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/knowledge-map.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00264 | $0.02535 |
| Opus 5 | $0.00132 | $0.01267 |
| Sonnet 5 | $0.00053 | $0.00507 |
| Haiku 4.5 | $0.00026 | $0.00253 |
Grade A, and why
knowledge-map 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 9d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
knowledge-map · 知识地图生成
把一个主题做成像「一人公司最强 skills 组合」那样的高信息密度全景图:深色背景、彩色卡片网格、阶段流程条、实战工作流、底部建议框。输出是一个自包含单文件 HTML,双击即可在浏览器打开,可直接截图导出为长图/海报。
框架源文件:skill 内置 assets/template.html,随 skill 分发、自包含、零外部依赖。模板内置渲染引擎,你只需填一个 DATA 配置对象,视觉风格(配色、排版、列数自适应)由框架统一保证。
输入收集
- 必填:主题(如「AI 副业」「前端工程师学习路线」「大模型应用开发全景」)。
- 可选:副标题/定位语、想覆盖的维度清单、配色主题(
dark/midnight/ink,默认dark)。
只给主题就够了——不要反问用户"你想分哪几个维度"。本 skill 的职责就是替用户把结构规划好。只有当用户主动给了维度清单时才采用其结构。
生成流程
第 1 步:3-5 轮知识调研(核心,不可跳过)
知识地图的价值在于信息密度和准确性,凭空编造的条目会让地图沦为空架子。所以动手画图前,必须用 WebSearch(必要时配合 WebFetch 读取关键页面)对主题做 3-5 轮递进式调研。每轮聚焦一个目的,前一轮的发现指导后一轮的检索词:
- 第 1 轮 — 框架/链路:这个主题的核心是什么?业内通常分成哪几个阶段/维度?有没有公认的流程或框架?目的是定出主网格的 4-6 个列(维度)和顶部阶段流程条。
- 第 2 轮 — 维度填充:针对第 1 轮定出的每个维度,搜索该维度下具体有哪些工具/技能/步骤/概念/资源。目的是填满每列的条目(每列建议 3-5 条)。
- 第 3 轮 — 实战组合:这个领域有哪些公认的"打法/工作流/学习路径/最佳实践组合"?目的是填底部的实战工作流面板。
- 第 4-5 轮 — 校验与补强(按需):核对术语是否准确、是否有遗漏的重要维度或过时信息、有没有更权威的提法;补充"使用建议 / 适用场景 / 核心优势"等底部建议框内容。
调研约束:
- 用
WebSearch实打实地查,不要凭记忆编。优先权威来源(官方文档、领域头部博客、知名从业者),对过时信息保持警惕,使用用户环境当前日期判断时效。 - 三轮的递进关系就是 框架 → 维度 → 打法:先定骨架,再填血肉,最后补实战组合,缺一不可。
第 1.5 步:汇报维度清单,等用户确认(硬性检查点,不可跳过)
调研完成后先停下来,不要直接画图。用简洁的列表向用户汇报规划结果,让用户有机会增删调整:
主题定位:<一句话>
配色主题:<dark / midnight / ...>
计划维度(主网格 N 列):
1. <维度名> —— <该列将放哪些条目,列出条目短名>
2. ...
阶段流程条:<N 个阶段>
实战工作流:<有/无,若有列出工作流名>
增强标签 / 建议框:<有/无>
然后明确问一句「这个维度规划 OK 吗?需要调整哪里?」收到用户确认(或调整意见处理完)后,才进入第 2 步生成。 只有当用户在最初就明说「不用确认/直接出图/一步到位」时,才跳过本检查点。
第 2 步:组织内容到 DATA 结构
把调研结果映射到模板的 DATA 对象(字段见下方「DATA 数据契约」)。要点:
- 维度列数 4-6 列最佳,过多会拥挤、过少显单薄。
- 条目用「短名 + 一行小字说明」:短名是关键词/工具名/概念名,说明是 4-12 字的白话注解。
- 命名规则:英文工具名、产品名、技术术语、API/函数名一律保留英文原文(如
Next.js、LangChain、pgvector、seo-audit),不要硬译成中文;说明小字一律用中文。标题、副标题、维度名、流程文案、建议框等叙述性文字也用中文。这样既专业可检索,又对中文读者友好。 - 阶段流程条与主网格的列通常一一对应,但流程强调"先后顺序",网格强调"内容清单"。
- 工作流、标签区、建议框是可选模块,内容不足时可设为
[],框架会自动跳过该区块。 - 文案去 AI 腔:说人话、具体、有信息量,避免"综上所述""值得注意"等套话。
第 3 步:生成 HTML 文件
- 读取
assets/template.html。 - 用组织好的内容整体替换模板中
const DATA = {...};这一段(保留前后的注释和渲染引擎不动)。 - 设置
DATA.theme为用户选的主题(默认dark)。 - 保存到当前工作目录,命名
knowledge-map-<主题简写>.html(主题用简短英文或拼音,避免空格和特殊字符)。
What ships with it
3 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.
- 9d ago First seen · 144 lines · 264 tokens per session scan A 401bf50ed321
knowledge-map is a skill published in the GitHub repository chengkj99/kj-skills (14 stars, last pushed 7d ago), licensed MIT. It adds 264 tokens to every session and 2,535 once invoked, about $0.0013 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.