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-strategy-advisorgit 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-strategy-advisor)<a href="https://agentmods.dev/skills/zju-real/easel/skill-strategy-advisor"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-strategy-advisor/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-strategy-advisor"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-strategy-advisor.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 | $0.00142 | $0.01695 |
| Opus 5 | $0.00071 | $0.00847 |
| Sonnet 5 | $0.00028 | $0.00339 |
| Haiku 4.5 | $0.00014 | $0.00169 |
Grade A, and why
skill-strategy-advisor 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
策略迭代建议
基于现有内容数据与画像，给出下一阶段的内容策略优化建议。
输入
| 字段 | 必填 | 说明 |
|---|---|---|
| 内容数据摘要 | 是 | 过去一段时间的内容表现数据（至少包含标题、平台、核心指标），或复盘报告 |
| 时间范围 | 推荐 | 数据覆盖的时间段（如"最近 30 天"、"6 月"） |
| 当前策略描述 | 推荐 | 现行的内容方向、赛道、发布节奏、主要形式等 |
| 目标变化 | 可选 | 近期目标是否有变化（如从涨粉转向变现、从单平台转向多平台） |
| 行业/赛道信息 | 可选 | 所在行业的近期变化、竞品动向 |
| 复盘报告 | 可选 | 若已运行过 skill-content-postmortem，可直接引用其输出 |
若用户仅提供模糊描述（如"最近数据不太好"），引导补充具体数据，但不阻断流程。基于可用信息给出建议，标注置信度。
输出
# 策略迭代建议：[账号/主题] — [时间段]
## 现状诊断
### 数据总览
| 指标 | 当前值 | 趋势（↑↓→） | 健康度 |
|------|--------|-------------|--------|
| 发布频率 | | | |
| 平均阅读/播放 | | | |
| 平均互动率 | | | |
| 粉丝增长 | | | |
| 爆款率 | | | |
### 核心问题识别
- 问题 1：[具体问题 + 数据支撑]
- 问题 2：...
- 积极信号：[做得好的方面，不能只说问题]
## 策略建议（按优先级排序）
### 1. [最高优先级建议标题]
- **现状**：当前怎么做的
- **问题**：数据说明了什么
- **建议**：具体怎么调整
- **预期效果**：调整后预期的变化
- **执行要点**：落地时的注意事项
### 2. [次优先级建议标题]
...
（共 3-5 条建议）
## 内容方向调整
### 保持的方向
- [表现好的方向 + 原因]
### 加强的方向
- [有潜力但投入不足的方向 + 依据]
### 减少或放弃的方向
- [表现差或 ROI 低的方向 + 替代方案]
### 新赛道探索建议
- [基于数据和趋势推荐的新方向 + 试水方案]
## 内容形式优化
- 格式建议（图文 / 视频 / 直播 / 混合）
- 长度建议
- 发布节奏建议（频率 + 最佳时段）
## 画像微调建议（如有 Profile）
- 定位描述是否需要更新
- 目标受众是否需要调整
- 内容风格是否需要迭代
- 具体修改建议（给出修改前后对比）
## 下一步行动清单
1. 本周立即执行：[1-2 个动作]
2. 两周内完成：[2-3 个调整]
3. 持续观察：[需要跟踪验证的指标]
## 数据局限与假设
- 分析基于的数据范围和质量说明
- 关键假设（如平台算法未大幅变化）
执行步骤
-
数据摄入与清理
- 接收用户提供的内容数据（CSV、截图、文字描述、复盘报告均可）
- 标准化为统一格式：内容标题、平台、发布时间、核心指标
- 若引用了 skill-content-postmortem 的输出，直接复用其分析结论
-
现状诊断
- 计算核心指标的均值、趋势、波动
- 识别表现异常点（突增突降）
- 对照 references/platform-benchmarks.md 判断账号健康度
- 标记正面信号和问题信号
-
归因分析
- 交叉分析：哪些内容方向 x 内容形式的组合表现最好/最差
- 时间维度：趋势是在好转还是恶化
- 外部因素：是否有平台规则变化、行业热点、季节因素的影响
-
趋势与机会扫描
- 基于赛道信息，判断行业内容趋势变化
- 识别用户数据中的潜在增长方向（有苗头但未放大的信号）
- 结合平台最新的流量倾斜方向（如平台近期推什么格式）
-
策略生成
- 生成 3-5 条策略建议，每条包含：现状、问题、建议、预期效果、执行要点
- 按预期影响力排序（高影响 + 低执行难度优先）
- 确保建议具体可执行，不写"提高内容质量"这类空话
-
方向调整矩阵
- 将现有内容方向分为四象限：保持 / 加强 / 减少 / 新增
- 每个方向的调整都有数据支撑
- 新赛道建议附带低成本试水方案（如"先发 3 条测试反馈"）
-
画像微调（有 Profile 时）
- 比对数据表现与 Profile 中的定位描述
- 若数据显示受众/风格/方向与 Profile 不符，给出微调建议
- 提供修改前后对比，而非只说"需要调整"
What ships with it
2 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 · 158 lines · 142 tokens per session scan A 8a8e73323b87
skill-strategy-advisor is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 142 tokens to every session and 1,695 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
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.