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-publish-checklistgit 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-publish-checklist)<a href="https://agentmods.dev/skills/zju-real/easel/skill-publish-checklist"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-publish-checklist/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-publish-checklist"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-publish-checklist.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 | $0.00143 | $0.01604 |
| Opus 5 | $0.00072 | $0.00802 |
| Sonnet 5 | $0.00029 | $0.00321 |
| Haiku 4.5 | $0.00014 | $0.00160 |
Grade A, and why
skill-publish-checklist 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
发布前完整性检查
发布前的最后一道关卡，逐项检查内容是否齐全，防止漏标题、漏封面、漏标签等低级错误。
与其他 SKILL 的区别
| SKILL | 定位 | 检查深度 |
|---|---|---|
| publish-checklist（本 SKILL） | 完整性检查——"有没有漏东西" | 浅层，逐项打勾 |
| skill-quality-gate | 深度合规 + 质量审核 | 深层，评分 + 返工 |
| skill-persona-check | 人设一致性 | 风格/调性维度 |
| skill-risk-scanner | 原创度 + 版权 | 抄袭/侵权维度 |
输入
用户提供待发布的内容，支持以下形式：
- 产物目录路径：指向
outputs/主题名/下的完整产物目录（含 meta.json、正文、图片等） - 单篇文案文本：直接贴文案内容
- 混合：文案 + 图片路径 + meta.json
可选指定目标平台（小红书、抖音、微博、公众号、LinkedIn、X 等），未指定时做通用检查。
输出
输出结构化检查报告，JSON 格式：
{
"status": "ready | not_ready",
"score": "7/10",
"platform": "平台名或generic",
"checklist": [
{
"item": "检查项名称",
"status": "pass | fail | warn",
"detail": "具体说明"
}
],
"blocking_issues": ["必须修复才能发布的问题"],
"warnings": ["建议修复但不阻塞发布的问题"],
"summary": "一句话总结：可以发 / 还差什么"
}
status为ready：所有必检项通过，可以发布status为not_ready：存在阻塞问题，列出待修复项
执行步骤
Step 1 — 识别内容形态与目标平台
- 判断输入是产物目录还是单篇文案
- 如果有
meta.json，读取其中的platform、type（图文/视频）、title、tags等字段 - 如果有 Profile 上下文，读取
platform字段确定目标平台 - 无法确定平台时，使用通用检查清单
Step 2 — 逐项检查（通用清单）
按以下维度逐项检查，标记 pass / fail / warn：
必检项（fail 则阻塞发布）：
| # | 检查项 | 检查内容 |
|---|---|---|
| 1 | 标题 | 是否有标题；标题长度是否在平台限制内 |
| 2 | 正文/内容 | 是否有实质内容；是否为空或占位符 |
| 3 | 封面/首图 | 图文帖是否有封面图；视频是否有封面帧 |
| 4 | 格式完整 | Markdown 结构是否完整；图片引用是否有效；链接是否可访问 |
建议项（warn 但不阻塞）：
| # | 检查项 | 检查内容 |
|---|---|---|
| 5 | 标签/Hashtags | 是否有标签；数量是否在 3-10 个合理区间 |
| 6 | CTA（行动号召） | 是否有引导互动的语句（点赞、收藏、关注、评论等） |
| 7 | 链接有效性 | 正文中的 URL 是否格式正确 |
| 8 | 图片规格 | 图片尺寸是否符合平台要求（竖版/横版/正方形） |
| 9 | 文案长度 | 字数是否在平台推荐范围内 |
| 10 | Emoji 使用 | 是否有适当 emoji 增强可读性（视平台而定） |
Step 3 — 平台特有检查（有平台信息时追加）
根据目标平台追加检查项：
小红书：
- 卡片数量是否在 3-9 张
- 每张卡片文字是否 ≤ 80 字
- 是否有 caption（发布配文）
- 封面是否为 3:4 竖版（1080×1440，小红书标准比例）
抖音/视频号：
- 视频时长是否在限制内
- 是否有字幕文案
- 封面是否有吸引力标题
微博：
- 正文是否 ≤ 2000 字
- 话题标签格式是否正确（#话题#）
公众号：
- 是否有摘要/导语
- 是否有原文链接
- 封面图尺寸是否为 2.35:1
X/Twitter：
- 单条是否 ≤ 280 字符
- 是否需要拆分为 thread
What ships with it
1 file 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.
- 7d ago First seen · 146 lines · 143 tokens per session scan A 3b1b4427487d
skill-publish-checklist is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 143 tokens to every session and 1,604 once invoked, about $0.0007 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
bootstrap
Onboarding conversation to generate a user profile.
life-design
Walk you through the Stanford Designing Your Life method and write your Personal Life Design Blueprint — three Odyssey plans and the prototypes to test them.
starfleet-timer
Set timers instead of blocking a session with sleep/watch-loops (e.g. waiting for a GitHub Actions run): the timer fires a comms directive into the fleet at the scheduled time, and the poller injects it into the owning ship's next turn — no background process, no blocking, survives a session restart.
starfleet-sessions
Ship session and workspace management — spawning ships, session attach/stop, git worktrees, web console, deployment. Load when launching/administering ships or managing the fleet web console.
apple-notes
Read Apple Notes content and execute checklist-driven automations in order. Use when a user asks to run tasks from an Apple Note (especially a checklist note like "AGENT TODO LIST"), or to fetch a specific note body for automation.
confetti
Trigger a two-step confetti celebration by opening the Raycast confetti URL and speaking a phrase with the Alex voice. Use when the user asks to run confetti, celebrate, or trigger the confetti sequence.