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 ZJU-REAL/Easel --skill skill-hook-generatorgit clone --depth 1 https://github.com/ZJU-REAL/EaselWrote 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/zju-real/easel/skill-hook-generator)<a href="https://agentmods.dev/skills/zju-real/easel/skill-hook-generator"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-hook-generator/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/zju-real/easel/skill-hook-generator"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-hook-generator.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 | $0.00113 | $0.01046 |
| Opus 5 | $0.00056 | $0.00523 |
| Sonnet 5 | $0.00023 | $0.00209 |
| Haiku 4.5 | $0.00011 | $0.00105 |
Grade A, and why
skill-hook-generator 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 8d 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.
What it actually says
Hook 变体生成
针对任意主题，生成 6 种经过验证的 Hook 变体，每条 Hook 为 2 行结构（开场 + 反转），用于社媒内容开头的注意力捕获。
输入
用户 prompt 中提供的主题文本。可以是关键词、短语或一句话描述。
输出
6 条 Hook 变体，每条包含：
- 第 1 行（开场）：≤40 字符，陈述句，出人意料/具体/有冲击力
- 第 2 行（反转）：≤40 字符，与开场形成矛盾/重构/颠覆
输出格式：
### 1. 数字领衔
> [开场]
> [反转]
### 2. 逆向认知
> [开场]
> [反转]
### 3. 个人蜕变
> [开场]
> [反转]
### 4. 权威借势
> [开场]
> [反转]
### 5. 自我坦白
> [开场]
> [反转]
### 6. 未来冲击
> [开场]
> [反转]
输出完成后，追加下一步操作提示：
---
选一条 Hook，我帮你扩写成完整帖子。回复编号即可。
执行步骤
- 获取主题 — 从用户 prompt 中提取主题；用户已提供则直接使用，无需追问。
- 生成 6 种 Hook 变体 — 按 hook-formulas.md 中的 6 种公式逐一生成：
- 数字领衔 (Number-led)
- 逆向认知 (Contrarian)
- 个人蜕变 (Personal transformation)
- 权威借势 (Authority steal)
- 自我坦白 (Admission)
- 未来冲击 (Future shock)
- 逐条校验 — 每条 Hook 必须通过以下检查：
- 每行 ≤40 字符：用脚本取确定性字数，不靠肉眼数。把每一行喂给
python3 skills/shared/scripts/wordcount.py count（stdin 传入），读social_count字段（社媒计数口径 = 中文字符 + 英文单词 + 数字串 + 标点）。 超过 40 就据结果压缩该行后重数，直到social_count ≤ 40。 - 开场行不含问号
- 优先第一人称（"我"）视角增强代入感（趋势/未来/权威类公式可例外）
- 优先使用阿拉伯数字
- 每行 ≤40 字符：用脚本取确定性字数，不靠肉眼数。把每一行喂给
- 按结构化格式输出 — 见上方输出格式。
- 提供下一步操作提示 — 告知用户可选一条 Hook 扩写为完整帖子。
Profile 感知
- 有 Profile：根据 Profile 中的
platform、tone、language等字段调整 Hook 的语气、用语风格和平台习惯用法。例如小红书偏口语化、抖音偏节奏感。 - 无 Profile：退回通用模式，使用中性语气生成，附注"如提供账号 Profile 可适配平台风格"。
规则
- 每行严格 ≤40 字符，用
../../shared/scripts/wordcount.py count逐行取social_count判定，超限即改 - 开场行禁止使用问句
- 禁止使用破折号（—）
- 禁止填充词（其实、就是、所以、然后）
- 数字一律用阿拉伯数字，不拼写
- 不含犹豫措辞（可能、也许、大概）
- 优先第一人称视角增强代入感；趋势/未来冲击/权威借势类公式可不含"我"
- 自动开始，不输出前言或寒暄
What ships with it
2 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.
- 8d ago First seen · 96 lines · 113 tokens per session scan A 37c86328f0cb
skill-hook-generator is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 113 tokens to every session and 1,046 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 2026-09-03.
Other skills, from other repositories
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
roadtrip-navigator
Generate North American road-trip itineraries as a map-first, offline-friendly single-file HTML page. Plans around daily driving segments, overnight stops, fuel/EV-charging, national-park reservations (Recreation.gov / NPS), seasonal road closures, and timezone/border crossings — for executable, decision-ready trips.…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.