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 content-creatorgit 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/content-creator)<a href="https://agentmods.dev/skills/chengkj99/kj-skills/content-creator"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/content-creator/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/content-creator"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/content-creator.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 | $0.00162 | $0.04015 |
| Opus 5 | $0.00081 | $0.02008 |
| Sonnet 5 | $0.00032 | $0.00803 |
| Haiku 4.5 | $0.00016 | $0.00402 |
Grade A, and why
content-creator 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
内容创作者 (Content Creator)
概述
本 Skill 提供一套标准化工作流,基于「AI 编程实战」方法论,从人设、结构、深度拆解到最终封装,全链路支持高质量内容生产。
三条铁律,缺一不可:
- 真实性铁律:不得为了人设、情绪、戏剧性或说服力补造第一人称经历、故事、对话、耗时、次数、数据、用户反馈或结果。只有用户素材或可追溯来源支持时才能当作真事写;否则改为客观表述、条件句或明确标注的假设示例。
- 洞见铁律:每篇文章必须有一个让人「哦,原来如此」的核心洞见。不是整合大众观点,是穿透本质的那一刀。文章没有洞见,写再多也只是热闹。
- 人味铁律:真实 > 完美。所有内容必须经过「去AI味」检查,但“人味”只能来自真实立场、具体判断、自然节奏和有证据的亲历,不能靠假故事伪装。
与完整内容闭环的边界
本 Skill 是正文生产引擎:接收已经明确的角度、素材或初稿,完成洞见深化、结构、成稿和封装。
如果用户要求同时完成用户问题调研、已有内容查重、外部证据与时效核验、研究配图、双视角评审、知识沉淀决策和下一篇连载,使用 research-backed-content-loop 作为总控,再由它在正文阶段调用本 Skill。不要把完整内容项目压缩成一次直接起草。
工作流决策树
分析输入类型,选择对应工作流:
- 录音/转录稿 → 工作流 A(录音转文章)
- 想法/热点/一句话 → 工作流 B(灵感孵化)
- 已有文章/初稿 → 工作流 C(文章改编/润色)
- 文章转视频 → 工作流 D(视频脚本)
- 文章转小红书 → 工作流 F(小红书矩阵)
- 竞品文章拆解 → 工作流 E(深度拆解)
所有生成类工作流(A/B/C)结束后,必须执行 Package Phase(封装)。
工作流 A:录音转文章
目标:将口语素材转化为2000字左右、有核心洞见、逻辑严密的专业文章。
阶段一:清洗(Clean)
去除口语冗余、重复、语气词。提炼出原始素材中的核心观点句(每个观点用一句话写下来,为下一阶段准备)。
输出:流畅版.md + 一份「核心观点提炼清单」。
阶段二:深度重构(Deep Structure)
这是文章质量的决定性阶段。
-
洞见挖掘(必须先做):
- 从「核心观点提炼清单」中找到最反常识、最有价值的那一个。
- 问自己:「如果读者没看这篇文章,他们能想到这个结论吗?」如果答案是「能」,说明洞见不够,需要继续挖掘。
- 参考
references/深度论证框架.md的「5层深度论证法」,确认洞见深度。
-
结构选型:引用
references/文章结构.md,选择最能承载这个洞见的结构模式。 -
饱和式论证:
- 每个核心观点必须用「论点 → 案例 → 原理 → 反例 → 结论」五步完整论证。
- 若素材不足,可以补充逻辑连接、概念解释和明确标注的作者分析;不得补造事实、案例、亲历、引语、数据或结果。需要事实支撑时,先补充可追溯来源或明确标记待核实。
- 文章必须包含至少一处「颠覆直觉」的分析(读者看到这里会停下来,重新读一遍)。
-
文章节奏设计:按照「开场高能 → 中段转折 → 收尾升华」安排能量起伏,避免平铺直叙。
阶段三:洞见质检(Insight QA)⭐️
这是新增的质量关卡,防止「结构正确但内容平庸」。
对文章进行以下逐项检查:
- 洞见唯一性:文章是否有一个让人「哦!」的核心洞见?这个洞见是否贯穿全文?
- 论证完整性:每个核心论点是否都有案例+原理+反例的支撑?还是只有结论?
- 反直觉设计:文章至少有一处「大家以为是X,其实是Y」的反转。有吗?在哪里?
- 深度检验:把文章的核心观点提炼成一句话,这句话是「描述现象」还是「解释机制」?后者才是真深度。
- 读者收获感:读完这篇文章,读者能得到一个「以前不知道、现在知道了」的认知升级吗?
如果任何一项回答是「否」,必须回到阶段二继续深化,不能跳过。
阶段四:润色(Refine)
- 引用
references/人设.md和references/金句.md确认风格调性。 - 应用「反爹味」原则,加入类比和口语化表达。
- 执行完整去AI味检查:引用
references/remove-ai-tone-guide.md,检查全部 14 个核心检查项(含新增的洞见真实性和论证完整性检查)。 - 发现问题,立即修复,修复后再输出。
What ships with it
10 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 · 261 lines · 162 tokens per session scan A a0e24ec5a924
content-creator is a skill published in the GitHub repository chengkj99/kj-skills (14 stars, last pushed 10d ago), licensed MIT. It adds 162 tokens to every session and 4,015 once invoked, about $0.0008 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).
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.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.