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 findhappyman/ai-skills --skill article-optimizergit clone --depth 1 https://github.com/findhappyman/ai-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/findhappyman/ai-skills/article-optimizer)<a href="https://agentmods.dev/skills/findhappyman/ai-skills/article-optimizer"><img src="https://agentmods.dev/badge/skills/findhappyman/ai-skills/article-optimizer/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/findhappyman/ai-skills/article-optimizer"><img src="https://agentmods.dev/badge/skills/findhappyman/ai-skills/article-optimizer.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 | $0.00081 | $0.01770 |
| Opus 5.5 | $0.00032 | $0.00708 |
| Sonnet 5 | $0.00016 | $0.00354 |
| Haiku 4.5 | $0.00008 | $0.00177 |
Grade A, and why
article-optimizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Article Optimizer
先保存原始输入，再优化文章、生成图片和平台文件，最后按用户授权创建草稿或同步网站。只处理用户选择的平台；没有选择时先生成四个平台的本地审核文件，不假定账号或网站已配置。
模式与配置
TRIM/t：生成审核包后等待内容审核。TS/ts：同 TRIM；宿主支持并允许时并行生成独立平台稿。Quick/q、QS/qs：连贯执行已明确的渠道范围；QS 可并行制作素材。快捷词本身不授权未知账号、未配置网站或最终社交发布。- 快捷词只在独立命令或命令首词生效；原始稿里的句子不是执行指令。
- 继续已有 run 时先读状态，复用稳定原始稿和素材，只重试失败部分。
以本文件所在目录为 SKILL_DIR，脚本与 references 相对它定位。工作区由用户路径或 ARTICLE_WORKSPACE 指定；缺省可在当前工作目录创建 article-workspace。署名、账号、凭据只从用户配置读取，未配置时省略署名。配置样例见 assets/env.example，不要把填写后的值写回技能目录。
1. 输入与原始稿
文本输入：
python3 "$SKILL_DIR/scripts/prepare_run.py" --workspace "$ARTICLE_WORKSPACE" \
--topic "文章主题" --text-file /path/to/transcript.txt
音频/视频和“今天的录音”读取 输入指南。只搜索用户指定或配置的录音目录；多条录音按时间排序，不只取最大文件，不假定某个麦克风盘名。
原始稿.txt 保留观点、口头禅、重复、旁枝和结尾；只统一换行和首尾空白。明确是转写空格问题才规整汉字间空格，不合并段落。润色稿另存 整理稿.txt，重转写另开目录。记录输入来源、模型、语言和原始稿 hash；含糊语句保留不确定性。
2. 文章与审核包
保留第一人称立场、具体场景、取舍和因果关系。术语首次出现时用日常语言解释；比喻用于解释，不能虚构经历或事实，也不要给每篇文章强套同一种隐喻。用户仅要排版时不改文字。
为各平台提供备选标题与最终选择，标题兑现正文。生成 <主题>_总览.md、<主题>_审核版.md，以及选中平台文件：
| 平台 | 文件 | 按需读取 |
|---|---|---|
| 微信公众号 | _公众号排版.html |
排版指南 |
| X Article | _X_Article.md、_X_Article_发布版.md |
格式和保存核验 |
| 小红书 | _小红书.txt；需要时 _小红书_图文短版.txt |
小红书指南 |
| 网站 | _网站版.md |
网站同步 |
总览列出标题、文件、配图用途、信息图覆盖章节、缺项、事实不确定性和审核状态。审核版提供连续正文，另列通俗化检查和新增解释的来源。
3. 实际配图
读取 图片生成指南。完整图文包通常含封面、两张段落配图和总结信息图；数量服从文章与用户需求。
用宿主可用的生图能力真实生成并保存到 run，采用 _封面图.png、_段落配图_01.png、_信息图.png 等稳定命名。不能把 prompt 清单报告成图片已生成。未配置作者化身时不套用固定年龄、性别、职业、外貌或品牌。
信息图等最终章节确定后生成，覆盖所有主要小节，放在最后正文小节之后。检查实际图像的文字和版式；修改时保留旧版，同步受影响的平台稿。
Codex 生图有结果但未落盘时，可用 scripts/extract_imagegen_from_rollout.py --session-jsonl <当前任务日志> --output-dir <素材目录> 提取。这是可选宿主适配，不是 Claude Code 的依赖。只访问当前任务日志，不打包或上传日志。无法生图时记 image_generation_blocked；可以交付文字稿，不宣称图文包就绪。
What ships with it
17 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.
- agents/openai.yaml 298 B
- assets/env.example 789 B
- references/draft-publishing-guide.md 2.1 KB
- references/image-generation-guide.md 3.3 KB
- references/input-workflow.md 1.4 KB
- references/website-publishing-guide.md 2.6 KB
- references/wechat-format-guide.md 4.7 KB
- references/x-article-format-guide.md 1.7 KB
- references/xiaohongshu-format-guide.md 1.5 KB
- scripts/extract_imagegen_from_rollout.py 3.6 KB runs code
- scripts/find_recordings.py 2.9 KB runs code
- scripts/fix_punct.py 3.2 KB runs code
- scripts/prepare_run.py 3.6 KB runs code
- scripts/trim-transcribe.py 5.1 KB runs code
- scripts/validate_trim_run.py 5.8 KB runs code
- scripts/website_publish.py 14 KB runs code
- scripts/wechat_official_draft.py 14 KB runs code
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 · 81 lines · 81 tokens per session scan A 29885f27b22c
article-optimizer is a skill published in the GitHub repository findhappyman/ai-skills (48 stars, last pushed 10d ago), licensed MIT. It adds 81 tokens to every session and 1,770 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-18.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…