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 ChouChiu/heya-skill --skill heya-title-stylegit clone --depth 1 https://github.com/ChouChiu/heya-skillWrote 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/chouchiu/heya-skill/heya-title-style)<a href="https://agentmods.dev/skills/chouchiu/heya-skill/heya-title-style"><img src="https://agentmods.dev/badge/skills/chouchiu/heya-skill/heya-title-style/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/chouchiu/heya-skill/heya-title-style"><img src="https://agentmods.dev/badge/skills/chouchiu/heya-skill/heya-title-style.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 | $0.00065 | $0.04844 |
| Opus 5 | $0.00032 | $0.02422 |
| Sonnet 5 | $0.00013 | $0.00969 |
| Haiku 4.5 | $0.00006 | $0.00484 |
Grade A, and why
heya-title-style 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
黑鸦标题风格
本技能用于把主题、事件、产品发布、争议、比赛结果或新闻素材改写成黑鸦式中文视频标题：信息密度高、情绪强、实体明确、多个事件压缩在同一个标题里。
引用资料
使用本技能前，必须查看并吸收以下引用资料，再开始改写标题：
-
references/00-llm-brief.md：LLM 优先读取的压缩摘要，包含核心风格、生成配方、高频素材和代表样本。 -
references/02-style-analysis.md：人类可读的完整风格分析报告，需要更细校准时再读。 -
references/02-style-analysis.yaml：结构化分析数据，用于程序读取聚合字段；LLM 不需要全文读取。 -
references/01-titles.csv：原始标题样本，用于按需查找真实标题语感、标点节奏和近期用词。 -
references/03-title-features.json：逐标题 tokens/entities/clauses 调试数据，体量较大。不要全文读取；只有排查具体标题的分词或实体问题时，按 bvid/title 精确检索单条记录。
如果引用资料和下方摘要有差异，以 references/ 中的最新资料为准。不要只凭本文件里的摘要生成标题；摘要负责快速定位，引用资料负责校准细节。
生成工作流
按顺序执行以下步骤：
Step 1: 提取事实
从用户输入中列出：
- 实体（公司名、产品名、人物名、项目名）
- 事件（发布、融资、收购、比赛结果、争议等，每条一句话）
- 日期（如有则用于
| AI日报MMDD收束）
🔴 CHECKPOINT：如果用户输入缺少关键信息（无实体或无事件），先向用户确认再继续。不凭空编造事实。
Step 2: 选择公式
根据事件数量选择标题公式：
- 3+ 事件日报 → 公式 2：
{事件A}；{事件B}；{事件C}，{集体命运/斩杀线}！| AI日报MMDD - 单产品/人物发布 → 公式 1：
{最强实体} + {突然/重磅/炸裂} + {动作}，{对手/行业} + {荒诞反应/后果}！ - 人物竞争/冲突 → 公式 3：
{人物/CEO} 瘫坐在{核弹/椅子}上，仿佛看到了{椅子爆炸/行业毁灭}！ - 模型/产品对决 → 公式 4：
{模型/产品} + {炼化/夺舍/祭出/龙王归来} + {对手/行业}，{用户/开发者} 已被{判处死刑/踢出群聊}！
多事件可混合使用多个公式拼合标题。
Step 3: 填充词汇
从词汇库和黑鸦专属意象中选择，每条标题必须包含：
- ≥2 个情绪引爆词（地震、核弹、杀疯、沸腾、疯狂、炸裂、震撼、窒息、裂开）
- ≥1 个身体反应词（瘫坐、癫痫、冷汗、头皮发麻、后背发凉、全员颤抖、吓晕）
- ≥1 个荒诞意象（椅子爆炸、开错生死簿、炼化、夺舍、核冬天、血洗）
不确定消息使用"或将、疑似、被曝、传出"等语气。不确定结论不写成确定。
Step 4: 组装输出
🔴 CHECKPOINT：在组装前先扫一遍"不要做"反例表，确认没有踩中任何一条。
- 最强冲突/情绪钩子放标题最前面。
- 用
！；，|串联 ≥4 个分句，越长越黑鸦味。 - 日报类以
| AI日报MMDD收束，非日报类用……制造悬念。 - 用具体实体、数字、后果替代泛泛词"来了""看看"。
默认输出一个长标题。用户要多个时给 3-5 列，标注 序号. {风格}式：{标题}。
🔴 CHECKPOINT: 最终自检
输出标题前必须逐条确认，全部通过才给出：
- ≥4 分句？
- ≥2 情绪词 + ≥1 身体反应 + ≥1 荒诞意象？
- 无编造事实？不确定消息用了模糊语气？
- 长度 40-80 字？
- 没踩"不要做"反例表中任何一条？
异常处理
| 场景 | 处理方式 |
|---|---|
| 用户未提供日期 | 省略 | AI日报MMDD 或使用当前日期 |
| 素材偏中性/无冲突 | 加强分句节奏（≥4 分句），降低情绪强度，不硬套荒诞意象 |
| 用户话题不适合黑鸦风格（如严肃学术、讣告） | 🔴 提示用户此风格偏戏剧化，建议降级为轻度改写或用其他风格 |
| 用户提供事实不足（仅一个实体名或一句话） | 🔴 向用户请求补充实体、事件、数字后再生成 |
| 引用文件缺失或读取失败 | 降级为仅凭 SKILL.md 摘要生成，输出前标注 ⚠️ |
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.
- 10d ago First seen · 202 lines · 65 tokens per session scan A ace5c15c6296
heya-title-style is a skill published in the GitHub repository ChouChiu/heya-skill (16 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 4,844 once invoked, about $0.0003 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
agent-creation-skill
Procedural guide for creating new agents from templates when project complexity requires delegation.
loom-typescript
TypeScript language expertise for type-safe, production-quality code.
js-gof
Apply Gang of Four and related design patterns in JavaScript and TypeScript. Use when implementing creational, structural, or behavioral patterns, or when the user mentions factories, builder, prototype, flyweight, singleton, object pool, adapter, wrapper, decorator, proxy, bridge, composite, facade, chain of…
error-handling
Apply error handling and recovery patterns in JavaScript/TypeScript or Node.js. Use when implementing error handling, retry logic, or when the user mentions domain errors, error recovery, error escalation.
js-conventions
Apply Metarhia JavaScript style. Use when writing or editing .js, .mjs, .ts files (with certain corrections for typescript), formatting code, or when the user asks about code style or linting.
codex-docs-drift-scout
Install the AutoHub docs-drift Codex automation from signed AutoVault skill resources and audit its render fidelity with autovault doctor.