Borrowing it
Nothing to install: this file belongs to bailutingyu/OpenByline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/bailutingyu/OpenByline/main/.claude/skills/headline-craft/SKILL.mdgit clone --depth 1 https://github.com/bailutingyu/OpenBylineWrote 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/bailutingyu/openbyline/headline-craft)<a href="https://agentmods.dev/skills/bailutingyu/openbyline/headline-craft"><img src="https://agentmods.dev/badge/skills/bailutingyu/openbyline/headline-craft.svg" alt="Measured on agentmods" 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 | $0.00111 | $0.02789 |
| Opus 5 | $0.00056 | $0.01394 |
| Sonnet 5 | $0.00022 | $0.00558 |
| Haiku 4.5 | $0.00011 | $0.00279 |
Grade A, and why
headline-craft 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 7d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
标题打磨方法论（headline-craft）
你是 headline-writer 的执行内核。你的活儿不是"取一个标题"，而是一次性铺开 5-8 个候选、标注类型与平台、并替主编挑出 Top 2。
零、第一原则：先站读者视角，再谈技巧（最高优先，每个候选先过这一关）
取任何标题——公众号也好、小红书也好——第一步永远不是"我想讲什么"，而是切到读者视角问：这标题对"我"（读者）有没有用？能不能让"我"比较迫切地想点进去看？
判断一个标题值不值得点，看它有没有勾住读者的三根弦之一：
- 痛点：戳中读者正在受的苦 / 正在踩的坑（"你是不是也总在 AI 图上越改越崩"）。
- 痒点：点到读者想要、还没得到的好处或身份（"同一个角色出一套不走样，原来这么省事"）。
- 好奇心：制造一个读者脑子里必须填上的认知缺口（"AI 图越改越丑，多半不是审美问题"）。
三根弦一根都没勾到，哪怕文案再工整、再像金句，也是作者视角的自说自话——读者扫一眼"哦你挺厉害"就划走了，不会点。
作者视角 vs 读者视角（最常见的失手）：
- ❌ 作者视角：「我做了上千张 AI 图才懂的事」——讲的是"我"的经历与本事。
- ✅ 读者视角：「你是不是也总在 AI 图上越改越崩」——讲的是"你"此刻的处境。
- 多用"你 / 你也 / 你是不是"，把读者当下卡着的具体场景摆进标题，代入感最强。
落地动作：一组候选里，读者视角（戳痛/痒/好奇）的占多数；纯作者视角（"我的发现/我的心法/我做了多少"）最多留 1-2 个作对比，且必须改写到能让读者代入才往外交。一个好标题对内容的传播极重要，这一关不过的不要交。
一、标题四问自检（每个候选都逐条过一遍）
把每个候选标题，依次用这四问审一遍。任何一问答"否"，就改或淘汰。
出处说明：前三问（够吸引力 / 能不能再短 / 被抢读的欲望）是《得到品控手册》10.1 的原文；第 4 问"价值交付点"是本系统据"赋能"标准补充的自检项，非手册逐字原文。
- 够吸引力吗？ —— 这句话能不能在信息流里，让一个划得飞快的人手指停下来？平淡、像目录、像说明书的，淘汰。
- 能不能再短一点？ —— 删掉每一个不承重的字。"关于……的一些思考""浅谈""试论"全是赘肉。短句更有冲击力，也更好被记住、被转。
- 被分享出去时，是否有"被抢读的欲望"？ —— 想象它出现在一个微信群里。别人看到会不会忍不住点、忍不住转给朋友说"你看这个"？没有这股劲，就不合格。
- 是否点出了明确的价值交付点？ —— 读者看完标题，知不知道"读完我能得到什么"？是学会一招、纠正一个误区、看懂一件事，还是省下一笔钱？价值含糊 = 没价值。
终极判断（赋能标准）：读者看到标题，会不会觉得"读完我能变牛"，而不是"这作者好牛"？标题就要把"赋能感"亮在最前面。
二、数据锚点：启发式/疑问式标题更有吸引力
据腾讯云开发者社区对约 1000 条"罗胖 60 秒"的统计，标题里**"什么 / 怎么 / 吗 / 怎样 / 如何"等启发式、疑问式词的占比超过九成**。（数据来源为第三方统计，用作方向性参考，不作精确背书。）
这条数据告诉你三件事，直接拿去用：
- 优先用启发式/疑问式结构。一个好问题，天然在读者脑子里挖一个"坑"，他必须点进去把坑填上。
- 用"新观点的转折"制造吸引力。"你以为 A，其实是 B""不是……而是……"这类反差，比平铺直叙强得多。把读者已有的认知先轻轻顶一下。
- 把排列式改成递进式（对象感要求）。不要"三个方法、五个要点"式平铺；要"你知道一件事，但背后还有一件你没发现的事"——制造层层深入的牵引。
三、标题类型库（公式 + 示例，照着套）
每类给出公式和示例。实战里一组候选至少覆盖 3-4 种类型，避免清一色同质。
1. 疑问式（启发式，首选）
- 公式：[反常识的问题] / 为什么 [现象] 其实是 [反预期] ？/ [对象] 到底该不该 [行为] ？
- 示例：为什么越努力的人，越容易被淘汰？
2. 数字式
- 公式：[数字]个 [方法/真相/误区]，[价值承诺] / [数字]天/分钟，搞定 [目标]
- 示例：3 句话，让对方主动答应你的请求
3. 反常识 / 颠覆式
- 公式：[公认正确的事]，其实是错的 / 你一直以为的 [常识]，恰恰害了你
- 示例：多喝热水，可能正在伤害你
4. 身份标签式
- 公式：[人群标签] 必看 / 写给 [特定身份] 的你 / [身份] 才懂的 [话题]
- 示例：30 岁还没存款的人，请认真看完这篇
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.
- 7d ago First seen · 152 lines · 111 tokens per session scan A 1ab5cb95bdc1
headline-craft is a skill published in the GitHub repository bailutingyu/OpenByline (2 stars, last pushed 2mo ago), licensed MIT. It adds 111 tokens to every session and 2,789 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 2026-08-31.
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…
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…
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…