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 ai-programming-topic-plannergit 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/ai-programming-topic-planner)<a href="https://agentmods.dev/skills/chengkj99/kj-skills/ai-programming-topic-planner"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/ai-programming-topic-planner/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/ai-programming-topic-planner"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/ai-programming-topic-planner.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 | $0.00115 | $0.02570 |
| Opus 5 | $0.00057 | $0.01285 |
| Sonnet 5 | $0.00023 | $0.00514 |
| Haiku 4.5 | $0.00012 | $0.00257 |
Grade A, and why
ai-programming-topic-planner 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 编程内容选题策略
把一条输入（动态/问题/痛点）转化为「有人看、能写出来、符合定位」的内容角度。
真实性边界
选题角度不得预支尚未存在的事实。只有输入素材或可追溯记录明确支持时，才能策划“我踩过的坑”“亲测”“用了 N 个月”“效率提升 N 倍”“用户都反馈”等角度。材料不支持时，改成常见错误、机制分析、官方信息解读、可复现演示或待验证选题，不得为了传播性补造亲历、数字、对话、反馈和结果。
执行流程（每次必走）
第 1 步：判断输入类型
先读输入，判断是哪一类：
| 类型 | 特征 | 例子 |
|---|---|---|
| 工具动态 | 新版本发布、新功能、行业新闻 | 「Claude Code 支持了 xxx」 |
| 实战记录 | 具体问题 + 解决过程，有命令/报错/截图 | 「我今天用 Cursor 遇到了 xxx」 |
| 痛点/困境 | 程序员的模糊感受或具体卡点 | 「感觉用 AI 没有提效」 |
| 想法/灵感 | 一句话观点、对比、反常识判断 | 「我发现 Cursor 用户和 Claude Code 用户思维方式不同」 |
| 已有素材 | 旧文章、笔记、草稿 | 提供一段已有内容需要改编 |
如果输入是实战记录（有完整的问题-排查-解决流程），直接建议用
coding-session-to-tutorial技能先结构化，再回来选角度。
第 2 步：如果在 LLM Wiki 中做选题，先做连载去重
当工作目录是 kj-llm-wiki，或用户要求“基于已发布内容、连载、后续选题、内容规划”时，必须先读：
wiki/playbooks/topic-bank/series-planning.mdwiki/playbooks/topic-bank/index.md
并检查已发布与待写内容：
raw/studio/transcripts/raw/studio/funnel/formatted/raw/studio/funnel/backlog/manual/raw/studio/funnel/backlog/queue.md
再从以下目录挖掘知识库支撑：
raw/notes/raw/papers/raw/assets/raw/studio/curriculum/lessons/raw/articles/docs/
候选选题优先作为已发布内容的续集、方法篇、案例篇、升级篇、反面篇，不要换标题复述旧观点。
每个候选选题必须补充 5 个字段：
- 已发布连接：连接哪条已发布内容，避免凭空立题
- 重复风险：是否和已发布内容重复，重复点是什么
- 连载位置：续集 / 方法篇 / 案例篇 / 升级篇 / 反面篇
- 知识库支撑：哪些目录或文件可作为内容池
- 下一集钩子：这一条发布后，下一条自然接什么
第 3 步：对照角度模式库，找 3-5 个候选角度
引用 references/angle-patterns.md，逐一过以下 7 个模式，找最匹配的：
- 认知反转型 — 输入里有被推翻的假设或反常识事实？
- 痛点具象化型 — 能精准钉住某类程序员的真实感受？
- 方法论提炼型 — 能从具体案例提炼出可迁移框架？
- 工具对比评测型 — 涉及两个及以上工具的选择？
- 实战案例记录型 — 有完整的「问题→过程→结果」？
- 趋势解读型 — 新动态发布，需要帮程序员翻译意义？
- 「我踩过的坑」型 — 用户素材是否明确记录了教训、弯路和认知升级？没有证据时跳过该模式。
每个候选角度写清楚：
- 一句话描述这个角度：读者看到后会想什么
- 核心洞见句：这篇文章要让读者「哦，原来如此」的那一句
- 3 个候选标题（痛点型 / 反常识型 / 方法型各一个，参考
references/content-criteria.md）
第 4 步：用五问框架评估，筛出最优
引用 references/content-criteria.md 里的五问框架，对每个角度逐项打分（✅/⚠️/❌）：
[ ] 符合定位（Claude Code / Cursor / Codex / AI编程方法论 / 程序员破局）
[ ] 读者真实痛点
[ ] 我有独特且可支撑的视角（有证据的真实经历 / 可复现演示 / 有来源的分析 / 明确的个人判断）
[ ] 可多渠道转化（长文→短视频→小红书）
[ ] 能与已有内容连接
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.
- 10d ago First seen · 209 lines · 115 tokens per session scan A 543040ffb6df
ai-programming-topic-planner is a skill published in the GitHub repository chengkj99/kj-skills (14 stars, last pushed 9d ago), licensed MIT. It adds 115 tokens to every session and 2,570 once invoked, about $0.0006 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…