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-social-performance-reviewgit 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-social-performance-review)<a href="https://agentmods.dev/skills/zju-real/easel/skill-social-performance-review"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-social-performance-review/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-social-performance-review"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-social-performance-review.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 | $0.00106 | $0.02476 |
| Opus 5 | $0.00053 | $0.01238 |
| Sonnet 5 | $0.00021 | $0.00495 |
| Haiku 4.5 | $0.00011 | $0.00248 |
Grade A, and why
skill-social-performance-review 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 9d 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 — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.
月度效果复盘
分析上月社媒内容表现，找出有效模式与失败原因，输出客户可读的复盘报告和下月可执行建议。
数据层定位
本 SKILL 是归因链的消费层，不新建数据底座：
- 粉丝 / 时序数据的权威来源是
skill-data-tracker快照底座（outputs/_analytics/snapshots/）；发布事件底座是skill-publish-log（outputs/_analytics/publish-log.json）。有对应底座数据时优先取用做环比与粉丝趋势。 - 本 SKILL 的临时文件与产物不是底座 — 阶段 3 的
outputs/复盘主题/.tmp-{月份}.json是标准化输入（用完即删），context/best-performers.md、context/review-history.md是复盘沉淀，均不重复存储粉丝时序或发布事件本身。 - 当底座数据缺失时，退到 CSV / 截图 / 口述输入（见「数据质量」），不阻断复盘。
输入
用户 prompt 中提供以下信息：
- 复盘月份：哪个月的数据
- 平台：小红书 / 抖音 / B站 / 微博 / 公众号（可多选）
- 数据来源（按优先级）：
- CSV 导出（小红书创作者中心 / 抖音创作者服务平台 / B站创作中心 / 微博数据中心）
- 截图（各平台后台数据概览）
- 口述（用户描述哪些帖子表现好/差）
- 业务背景（可选）：当月是否有特殊事件、促销、付费推广
示例 prompt：
Execute /skill-social-performance-review
月份：2025年6月
平台：小红书
数据：附上后台截图
背景：6月中旬做了一次好物分享合集
输出
结构化月度复盘报告，保存到 outputs/复盘主题/[客户名]-social-review-[月份]-[年份].md。
报告包含：月度概览、表现最佳/最差帖子分析、内容支柱与格式拆解、关键洞察、下月建议。
完整报告模板见 references/report-template.md。
数据质量
SKILL 适配三种数据质量等级，缺数据不中断分析：
| 等级 | 数据来源 | 分析深度 |
|---|---|---|
| 完整 | CSV 导出 + 账号概览截图 | 逐帖评分，完整指标对比 |
| 部分 | 截图或 Top/Bottom 帖子列表 | 模式分析，标注数据缺口 |
| 最少 | 用户口述表现好/差的帖子 | 定性分析 + 基于最佳实践的建议 |
在报告开头明确标注数据来源和质量等级。
执行步骤
阶段 0 — 环境准备
读取以下上下文文件（存在则读，不存在则跳过并记录）：
context/brand-style.md— 内容支柱、平台定位、目标context/content-calendar.md— 上月排期计划context/best-performers.md— 历史高表现帖子context/review-history.md— 历史评分趋势outputs/复盘主题/最新文件 — 上月复盘（用于环比）
阶段 1 — 信息收集
收集复盘月份、平台、数据来源、业务背景和当月目标。
若用户未准备导出数据，提供导出步骤指引：
- 小红书：创作者中心 → 数据中心 → 内容分析 → 选时间范围
- 抖音：创作者服务中心 → 数据看板 → 作品分析
- B站：创作中心 → 数据中心 → 稿件分析
- 微博：微博数据中心 → 内容分析
- 公众号：公众号后台 → 统计 → 内容分析
若无法导出，请用户提供：Top 3 帖子 + Bottom 3 帖子 + 粉丝变化 + 意外表现帖子。
阶段 2 — 数据标准化
接受 CSV / 截图 / 口述，统一提取：帖子日期、类型、文案摘要、触达、互动、保存/点击、分享、互动率。
清洗规则：
- 付费推广帖子排除出有机基准，单独标注
- Reels/短视频触达天然膨胀，对比格式时注明
- 发帖空白期单独记录
阶段 3 — 效果分析
先把标准化数据落成 JSON，交给 scripts/review.py 做确定性计算，再由你解读。
不要手算互动率、不要心排 Top/Bottom、不要心算环比和加权评分。
把阶段 2 标准化后的数据写成输入 JSON（outputs/复盘主题/.tmp-{月份}.json）：
What ships with it
5 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.
- 9d ago First seen · 192 lines · 106 tokens per session scan A 879037433e79
skill-social-performance-review is a skill published in the GitHub repository ZJU-REAL/Easel (841 stars, last pushed yesterday), licensed Apache-2.0. It adds 106 tokens to every session and 2,476 once invoked, about $0.0005 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.…
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.
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.