Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ZJU-REAL/Easelnpx agentmods add skills/zju-real/easel/skill-post-scorerWrote 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-post-scorer)<a href="https://agentmods.dev/skills/zju-real/easel/skill-post-scorer"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-post-scorer/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-post-scorer"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-post-scorer.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 | $0.00129 | $0.01642 |
| Opus 5 | $0.00064 | $0.00821 |
| Sonnet 5 | $0.00026 | $0.00328 |
| Haiku 4.5 | $0.00013 | $0.00164 |
Grade A, and why
skill-post-scorer 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.
How it starts
The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
帖子表现评分
对社媒帖子草稿进行互动潜力评分，基于历史表现数据输出结构化评分卡。
加载后立即开始评分流程，不做摘要或等待确认。
输入
用户 prompt 中提供待评分的帖子草稿，支持以下形式：
- 文本内容：直接粘贴帖子文案
- 文件路径：指向
outputs/中的草稿文件 - 平台指定：可选，指定目标平台（小红书、抖音、微博、知乎、公众号、B站等）
示例 prompt：
Execute /skill-post-scorer
帖子：
我花了3年时间才明白一个道理：
最好的内容不是"写"出来的，而是"提炼"出来的。
以下是我总结的5个内容提炼方法...
输出
输出代码块格式的评分卡：
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
帖子表现评分卡
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
钩子强度 ██████████ 8/10
声音匹配度 ███████░░░ 7/10
价值密度 ████████░░ 8/10
结构与格式 ███████░░░ 7/10
发布就绪度 ██████░░░░ 6/10
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
总分 36/50
判定 值得发布，建议优化钩子
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
改进建议：
1. [最弱维度] 具体修改建议
2. ...
执行步骤
第一步：获取帖子
读取用户粘贴的帖子内容。如果 prompt 中没有帖子文本，主动询问用户提供。
第二步：加载评分数据
按优先级获取表现数据：
- Profile 中的历史数据：检查
=== EASEL ACCOUNT PROFILE ===标记，读取performance_data路径指向的历史帖子数据 - 用户提供数据：询问用户是否有历史帖子导出数据（各平台创作者中心/后台可导出 CSV/Excel，或整理成 JSON 数组）
- 通用基准：以上都没有时，使用
references/fallback-benchmarks.md中的基准数据
第三步：分析高表现帖子
互动分与 Top 10% 筛选交给脚本，LLM 只做特征提炼。 由
scripts/score.py完成（复用../../shared/scripts/social_stats.py的engagement_score）。
有历史/用户数据时，把帖子整理成 JSON 数组（每条含点赞与评论字段），调用：
python3 skills/openclaw/skill-post-scorer/scripts/score.py top --input history.json
python3 skills/openclaw/skill-post-scorer/scripts/score.py top --input history.json --top-pct 5
脚本自动：按 互动分 = 点赞 + 评论×3 逐条计算（字段兼容 likes/reactions/点赞、
comments/评论）、按互动分降序、算出 Top N% 门槛与分布（均值/中位数/最高/最低）、
样本量不足警告。LLM 拿到脚本输出的 Top 帖子后，提取其共性特征：
- 开头钩子类型（提问、数据、故事、反常识）
- 文本长度和段落节奏
- 格式特征（列表、分隔、emoji 使用）
- 行动号召（CTA）类型
- 主题分类
- 句式节奏（长短交替、断句频率）
无历史数据时跳过本步，直接用 references/fallback-benchmarks.md 的通用模式特征。
第四步：五维评分
按 5 个维度打分，每项 1-10 分，总分 50 分。
评分标准详见 references/scoring-criteria.md。
| 维度 | 评判重点 |
|---|---|
| 钩子强度 | 前两句是否能阻止滑动，制造好奇或共鸣 |
| 声音匹配度 | 是否契合账号一贯的语气、人设和表达习惯 |
| 价值密度 | 每段是否提供具体洞察，而非空泛陈述 |
| 结构与格式 | 排版是否适配目标平台的阅读习惯 |
| 发布就绪度 | 能否直接发布，还是需要润色或补充 |
评分纪律：
- 诚实评分，不做讨好
- 除非帖子确实匹配 Top 10% 的模式特征，否则不给 8 分以上
- 有真实数据时用数据说话，没有时明确标注"基于通用基准"
What ships with it
4 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 · 154 lines · 129 tokens per session scan A 3042e344ee8d
skill-post-scorer is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 129 tokens to every session and 1,642 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.