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 research-backed-content-loopgit 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/research-backed-content-loop)<a href="https://agentmods.dev/skills/chengkj99/kj-skills/research-backed-content-loop"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/research-backed-content-loop/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/research-backed-content-loop"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/research-backed-content-loop.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 | $0.00172 | $0.02853 |
| Opus 5 | $0.00086 | $0.01426 |
| Sonnet 5 | $0.00034 | $0.00571 |
| Haiku 4.5 | $0.00017 | $0.00285 |
Grade A, and why
research-backed-content-loop 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 11d 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 — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research-backed Content Loop
把内容生产从“让 AI 写一篇文章”,升级为一条可以回查、复用和继续生长的闭环。
本技能是总控编排器,不重复其他技能的专业规则。根据任务实际需要,路由到选题、洞察、调研、写作、作者风格、插图、发布和知识沉淀能力;不要为了展示流程而机械调用全部技能。
核心闭环
真实问题 / 已有素材
→ 检查已发布内容与本地知识
→ 用户问题与外部证据
→ 核心洞见和边界
→ 正文生产
→ 作者视角 + 用户视角评审
→ 证据与配图逐一对应
→ 发布稿与过程资产
→ 知识沉淀决策
→ 下一篇连载
使用边界
使用本技能:
- 用户给出一个困惑、现象或想法,希望完成调研、洞察、成稿和配图。
- 用户提供文章草稿,要求核验时效、去 AI 味、补研究图、连接知识库并规划下一篇。
- 用户希望公开一篇真实案例,展示内容如何从想法进入知识库并产生下一轮内容。
- 用户明确要求一条完整内容生产闭环,而不只是写一版文字。
不要使用本技能:
- 素材和角度已经确定,只需写正文:使用
content-creator。 - 只需调整为康健本人语气:使用
kangjian-skill。 - 只需去除已有文字中的 AI 痕迹:使用
humanizer-zh。 - 只需做公众号封面、摘要、转发文案或草稿发布:使用
wechat-publish-kit。 - 只需把讨论写入个人 Wiki:使用
wiki-doc-sink,并服从目标 Wiki 的本地规范。
开始前:先确定交付边界
从对话和现有文件中提取以下信息,能合理推断时不要重复追问:
- 内容形态:公众号、短视频、小红书、知识星球或系列策划。
- 目标读者:谁会看,他们正在卡在哪里。
- 作者目标:为什么现在写,想建立什么判断或信任。
- 当前输入:真实经历、用户原话、评论、草稿、研究报告、截图、课程或知识库材料。
- 交付范围:只出正文,还是包括配图、发布包、知识沉淀和下一篇。
- 事实边界:哪些是作者亲历,哪些是外部证据,哪些仍待验证。
如果目标仓库有 AGENTS.md、CLAUDE.md、SCHEMA.md 或内容生产协议,先完整阅读并以本地规则为最高落地依据。
阶段一:检查已有内容,避免凭空立题
先搜索本地知识库、已发布内容、待写队列和已有草稿。
在 kj-llm-wiki 中做公众号或连载内容时,优先检查:
HOME.md、wiki/index.md;wiki/playbooks/topic-bank/series-planning.md;raw/studio/funnel/transcripts/;raw/studio/funnel/formatted/;raw/studio/funnel/published/;raw/studio/funnel/backlog/manual/与queue.md。
明确当前内容属于续集、方法篇、案例篇、升级篇还是新系列。记录重复风险和与上一篇的连接。
需要系统选题时使用 ai-programming-topic-planner。不要换一个标题重复已经发布的观点。
阶段二:找到用户真正的问题
不要把作者想讲的主题直接当成用户问题。优先寻找:
- 用户自己的原话、评论、搜索问题或对话;
- 作者反复遇到的真实场景;
- 本地资料中的失败记录和阻力;
- 外部社区、调查或研究中可核验的共性。
把观察与证据分开:
- “我看到几位读者这样问”是观察;
- 有范围、样本和来源的调查才是研究证据;
- 没有数据时,诚实写成个人判断,不编造“很多人都……”。
从现象中寻找机制和反常识判断时,使用 phenomenon-insight。产出必须包含边界:这个判断在什么情况下不成立。
阶段三:建立证据账本
当文章包含数据、论文、报告、产品能力、年份、模型名称或可能过期的信息时,读取 references/evidence-visual-protocol.md。
为重要主张记录:
- 主张是什么;
- 来自作者经验、用户观察还是外部来源;
- 来源名称、链接、发布日期或更新时间;
- 证据能够支持到什么程度;
- 是否存在地域、样本、自报数据或模型版本限制;
- 正文如何用普通人的话表达;
- 是否需要对应配图。
时效敏感内容必须查询当前资料。若具体模型和年份不是论证重点,优先写长期有效的能力判断;若历史版本不可省略,要说明它只代表当时实验条件。
What ships with it
5 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.
- 11d ago First seen · 225 lines · 172 tokens per session scan A 8f120124f3b9
research-backed-content-loop is a skill published in the GitHub repository chengkj99/kj-skills (14 stars, last pushed 10d ago), licensed MIT. It adds 172 tokens to every session and 2,853 once invoked, about $0.0009 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…