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-comment-insightsgit 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-comment-insights)<a href="https://agentmods.dev/skills/zju-real/easel/skill-comment-insights"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-comment-insights/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-comment-insights"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-comment-insights.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 | $0.00147 | $0.00919 |
| Opus 5 | $0.00073 | $0.00460 |
| Sonnet 5 | $0.00029 | $0.00184 |
| Haiku 4.5 | $0.00015 | $0.00092 |
Grade A, and why
skill-comment-insights 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.
What it actually says
评论区量化分析（comment-insights）
对评论做量化洞察：情感分布、高频词/短语、需求与吐槽挖掘。走
scripts/comment_insights.py（jieba + SnowNLP + 社媒情感词典）。
和 skill-community-ops 的分工：community-ops 是"怎么回评论 + 危机应对"（运营动作）； 本 SKILL 是"评论区在说什么"（量化数据）。评论抓取见 skill-xhs-analyzer。
⚠️ 依赖
pip install jieba snownlp（首次 jieba 会构建词典缓存）。
输入
评论数据，三种格式：
.txt：每行一条评论.json：字符串数组，或对象数组（--column指定字段，默认 content）.csv：--column指定评论列（默认首列/content）
输出（outputs/主题名/）
- 报告 JSON：情感分布/占比 + 正负代表评论 + 高频词 + 高频短语 + 需求/吐槽/提问计数与例子
- 终端可读摘要
执行
脚本路径（相对项目根）：skills/openclaw/skill-comment-insights/scripts/comment_insights.py。
python <skill>/scripts/comment_insights.py analyze -i comments.txt --top 20 \
-o outputs/主题名/report.json
# CSV 指定列
python <skill>/scripts/comment_insights.py analyze -i comments.csv --column 评论内容
结果怎么用
- 情感占比：负面偏高 → 结合负面代表评论定位问题；配合 skill-community-ops 做回应/危机。
- 高频词/短语：用户关注点与话题；可喂 chart-visualization/infographic 出词云图。
- 需求（demands）：求链接/求教程/求同款 → 直接转化为下一条选题（配合 community-ops 选题反哺）。
- 吐槽（complaints）：产品/服务问题信号 → 复盘改进（配合 skill-content-postmortem）。
规则
- 情感为 SnowNLP 基线 + 社媒词典修正的近似值，用于看趋势与占比，非逐条精判； 关键决策需人工核对代表评论，或让 LLM 对存疑评论精读。
- 高频词已做词性过滤（保留名/动/形）+ 停用词剔除，聚焦有信息量的词。
- 数据量小（<20 条）时占比参考意义有限，如实说明样本量。
- 只做分析不做回复；回复/危机用 skill-community-ops。
参考来源
沿用社媒评论分析常用组合：jieba 中文分词（#131 高频词）+ SnowNLP 情感（#130），并叠加 社媒情感词典（绝绝子/yyds/避雷/翻车等网络用语）修正 SnowNLP 在社交文本上的偏差。诉求挖掘 用规则匹配（求购/疑问/吐槽），确定可复现。
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.
- 10d ago First seen · 66 lines · 147 tokens per session scan A cac062ad1ddf
skill-comment-insights is a skill published in the GitHub repository ZJU-REAL/Easel (710 stars, last pushed yesterday), licensed Apache-2.0. It adds 147 tokens to every session and 919 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 2026-08-30.
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.