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-topic-evaluatorWrote 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-topic-evaluator)<a href="https://agentmods.dev/skills/zju-real/easel/skill-topic-evaluator"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-topic-evaluator/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-topic-evaluator"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-topic-evaluator.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 | $0.00173 | $0.01828 |
| Opus 5 | $0.00086 | $0.00914 |
| Sonnet 5 | $0.00035 | $0.00366 |
| Haiku 4.5 | $0.00017 | $0.00183 |
Grade A, and why
skill-topic-evaluator 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 5d 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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
选题可行性评估
用户给一个选题,多维度打分评估值不值得做,输出"做/不做/改方向"建议。
评分口径:本 SKILL 与
skill-content-matrix共用../../shared/scoring-dimensions.md的统一七维 + 标尺 + 权重。matrix 做批量池快评,本 SKILL 做单条深评(逐维展开详细分析)。两者维度、标尺、综合分阈值完全一致。
输入
| 参数 | 必填 | 说明 |
|---|---|---|
| 选题 | 是 | 用户想做的选题标题或描述 |
| 目标平台 | 否 | 小红书 / 抖音 / 微博 / 知乎 / B站 / 公众号(有 Profile 时自动提取) |
| 补充背景 | 否 | 选题来源、灵感、竞品参考等 |
输出
# 选题评估报告
## 选题: {用户给出的选题}
目标平台: {platform}
评估时间: {date}
## 七维评分
按 `../../shared/scoring-dimensions.md` 的统一维度和标尺打分,逐维带详细依据:
| 维度 | 得分 | 说明 |
|------|------|------|
| 流量潜力 | X/10 | {痛感强度 + 平台话题热度 + 搜索需求} |
| 账号匹配 | X/10 | {与定位、受众、内容体系的契合度} |
| 竞争差异化 | X/10 | {同类饱和度 + 能否切差异化角度,高分=竞争低} |
| 时效价值 | X/10 | {常青 vs 一次性热点,高分=常青} |
| 变现空间 | X/10 | {能否自然接广告/带货/引流} |
| 制作成本 | X/10 | {资源与技能门槛,反向,高分=易做} |
| 合规风险 | X/10 | {敏感度风险,反向,高分=低风险} |
综合得分: XX/100(按 scoring-dimensions.md 的推荐权重加权换算)
## 结论: {做 / 不做 / 改方向}
{一句话总结判断理由}
## 详细分析
### 流量潜力分析
{该选题在目标平台的搜索热度、话题讨论量、同类爆款情况}
### 竞争差异化
{头部玩家是否占位、中腰部突围空间、差异化切入点}
### 时效价值
{常青还是短期热点、最佳发布窗口}
### 变现路径
{可接的商业合作类型、引流转化链路}
### 制作可行性
{需要的素材/设备/专业知识/时间投入}
### 账号契合度
{与创作者内容体系和粉丝画像的匹配程度}
### 合规风险
{敏感赛道标注 ⚠️ 及合规建议}
## 优化建议(改方向时提供)
1. {角度调整建议}
2. {形式调整建议}
3. {时机调整建议}
## 替代选题推荐(不做时提供)
1. {替代选题 A} — {推荐理由}
2. {替代选题 B} — {推荐理由}
评分标尺
统一的七维标尺(1-3 / 4-6 / 7-8 / 9-10 分档)见 ../../shared/scoring-dimensions.md,本 SKILL 直接套用,不另立口径。
执行步骤
-
解析选题意图
- 提取用户给出的选题核心关键词和主题方向
- 识别选题类型:知识干货、情绪共鸣、热点追踪、人设展示、带货种草、争议讨论
- 如未指定平台,根据选题类型推断最适合的平台,或询问用户
-
逐维深度评估
按
../../shared/scoring-dimensions.md的七维逐一展开,每维给分并写明具体依据:- 流量潜力 — 平台话题热度、搜索需求、同类历史表现、传播性、算法偏好
- 账号匹配 — 与定位/人设/赛道、已有内容承接、粉丝画像兴趣、长期成长影响
- 竞争差异化 — 同类饱和度、头部是否占位、中腰部突围空间、可切的新角度
- 时效价值 — 常青 vs 时效;常青评估长期搜索价值,时效评估衰减速度和最佳窗口
- 变现空间 — 商业价值(品牌/带货/知识付费/引流)、受众付费意愿、变现路径是否自然
- 制作成本(反向)— 所需素材/设备/专业知识/周期,创作者现有能力能否覆盖
- 合规风险(反向)— 敏感赛道标注 ⚠️ 及合规建议
-
综合判断与输出
- 按 scoring-dimensions.md 的推荐权重计算综合得分(满分 100)
- 按统一阈值给结论:
- ≥ 70:做,立刻排期
- 50-69:改方向,调整后再评估(附至少 2 条优化建议)
- < 50:不做,附至少 2 个替代选题
- 输出完整评估报告
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.
- 5d ago First seen · 144 lines · 173 tokens per session scan A 0e1d24d42650
skill-topic-evaluator is a skill published in the GitHub repository ZJU-REAL/Easel (494 stars, last pushed 2d ago), licensed Apache-2.0. It adds 173 tokens to every session and 1,828 once invoked, about $0.0009 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.
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
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.…
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.