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.
git clone --depth 1 https://github.com/killvxk/pm-skills-zhWrote 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/commands/killvxk/pm-skills-zh/analyze-feedback)<a href="https://agentmods.dev/commands/killvxk/pm-skills-zh/analyze-feedback"><img src="https://agentmods.dev/badge/commands/killvxk/pm-skills-zh/analyze-feedback.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00019 | $0.01017 |
| Opus 5 | $0.00010 | $0.00508 |
| Sonnet 5 | $0.00004 | $0.00203 |
| Haiku 4.5 | $0.00002 | $0.00102 |
Grade A, and why
analyze-feedback 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.
What it actually says
/analyze-feedback -- 用户反馈分析
将大量用户反馈(评论、问卷、支持工单、NPS 回复)处理为结构化洞察,包含情感分析和细分市场层面的规律。
调用方式
/analyze-feedback [上传 NPS 回复的 CSV 文件]
/analyze-feedback [粘贴应用商店评论或问卷回复]
/analyze-feedback [上传支持工单导出文件]
工作流程
第一步:接收反馈数据
支持以下任意格式:
- 包含反馈文本的 CSV/Excel(可选元数据:日期、细分、评分)
- 粘贴的文本(评论、问卷回复、Slack 消息)
- 上传的文档或反馈工具导出文件
询问用户:
- 这是哪类反馈?(NPS、评论、支持工单、问卷等)
- 是否需要单独分析某些细分市场?(用户层级、套餐、地区)
- 你想了解什么?(整体主题、具体问题、随时间变化的趋势)
第二步:分析
应用 sentiment-analysis 技能:
- 情感评分:对每条反馈进行分类(正面、中性、负面)
- 主题提取:识别反复出现的话题,将相关反馈归类
- 频率分析:统计每个主题出现的次数
- 细分分析:按用户细分拆解情感与主题(如有数据)
- 趋势检测:如有日期数据,识别情感随时间的变化
第三步:生成分析报告
## 反馈分析报告
**日期**:[今天]
**分析反馈量**:[数量] 条
**来源**:[NPS 问卷 / 应用评论 / 支持工单 / 其他]
**时间段**:[如有日期范围则填写]
### 整体情感
- 正面:[X%] | 中性:[Y%] | 负面:[Z%]
- 平均情感评分:[X/10]
- 趋势:[改善中 / 稳定 / 下滑]
### 主要主题
| # | 主题 | 提及次数 | 情感倾向 | 影响最大的细分市场 |
|---|------|----------|----------|------------------|
### 主题深度分析
#### 主题 1:[名称] — [X] 次提及,[情感倾向]
- **用户怎么说**:[摘要及代表性引用]
- **根本原因**:[是什么驱动了这些反馈]
- **影响**:[对留存、满意度或营收的影响]
- **建议**:[应对措施]
[对排名前 5-8 的主题重复上述结构]
### 细分市场分析
| 细分市场 | 数量 | 平均情感 | 首要主题 | 关键差异 |
|----------|------|----------|----------|---------|
### 典型引用
> "[引用内容]" — [细分市场,情感倾向]
### 随时间变化的趋势
[如有日期数据:可用于图表的情感变化数据]
### 可行洞察
1. [洞察 + 建议行动]
2. ...
### 盲点
[这批反馈未能回答的问题——建议跟进的调研方向]
保存为 markdown 格式。如果输入是结构化数据(CSV),同时保存附有情感评分的增强版 CSV 文件。
第四步:提供后续建议
- "要我基于这些反馈规律创建用户画像吗?"
- "要我将主要主题整理为功能需求吗?"
- "要我设计访谈提纲,针对某个具体主题深入挖掘吗?"
注意事项
- 情感分析具有一定误差——对边缘情况(反讽、混合情感、非英语文本)需标注说明
- 主题提取应挖掘需求背后的深层诉求,而非仅停留在表面话题
- 若每个细分市场的样本量较小,需注明置信度有限
- 对于 NPS 数据,需单独分析批评者(0-6 分)、被动者(7-8 分)和推荐者(9-10 分)
- 当输入为结构化数据时,输出增强版 CSV,方便用户在自己的工具中使用
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 · 104 lines · 19 tokens per session scan A b1c3b863b31e
analyze-feedback is a command published in the GitHub repository killvxk/pm-skills-zh (154 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 1,017 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.