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 agentmods add skills/ryanzhao1011/workframe/user-feedback-analysisnpx skills add ryanzhao1011/workframe --skill user-feedback-analysisgit clone --depth 1 https://github.com/ryanzhao1011/workframeWrote 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/ryanzhao1011/workframe/user-feedback-analysis)<a href="https://agentmods.dev/skills/ryanzhao1011/workframe/user-feedback-analysis"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/user-feedback-analysis.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 | $0.00031 | $0.01981 |
| Opus 5 | $0.00015 | $0.00991 |
| Sonnet 5 | $0.00006 | $0.00396 |
| Haiku 4.5 | $0.00003 | $0.00198 |
Grade A, and why
user-feedback-analysis 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 3d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用户反馈分析技能
数据来源识别
支持四类标准数据源：
| 来源类型 | 示例 | 分析侧重 |
|---|---|---|
| 客服记录 | 工单、在线对话历史 | 问题频率 + 痛点严重度 |
| 平台评论 | 应用市场评价、G2/Capterra | 情感倾向 + 公开声誉 |
| 调研问卷 | NPS/CSAT 开放题 | 满意度趋势 + 改进建议 |
| 用户访谈 | 访谈记录、录音文字稿 | 深度动机 + JTBD 发现 |
三阶编码流程
第一阶：开放编码
不预设分类，通读全部反馈，为每条反馈打标签：
操作步骤：
- 逐条阅读原始反馈
- 提取关键信息，打 1-3 个标签
- 标签格式：
[对象]+[评价]
标签示例：
"处理结果不太满意" → [输出质量]-[不达标]
"每个月只能用20次太少了" → [配额]-[不够用]
"提交后一直没有响应" → [系统稳定]-[超时]
"能不能加个新模板" → [功能模板]-[新模板需求]
第二阶：主题聚合
将相似标签合并为候选主题：
操作步骤：
- 将标签按相似度分组
- 为每组命名一个主题
- 验证主题质量
主题验证三标准：
| 标准 | 检查问题 |
|---|---|
| 独立性 | 每个主题不与其他主题重叠？ |
| 穷举性 | 所有反馈都被至少一个主题覆盖？ |
| 代表性 | 主题名称能准确代表其包含的反馈？ |
输出格式：
### 主题 1：{主题名称}（{N} 条反馈）
- 代表性引语："{原始反馈摘录}"
- 包含标签：[标签1]、[标签2]、...
- 情感分布：正面 {N}% | 中性 {N}% | 负面 {N}%
第三阶：机会提炼
将主题转化为 JTBD（Jobs to Be Done）格式的机会陈述：
### 机会 OPP-{序号}
**JTBD 陈述**：
当 {情境} 时，{用户角色} 想要 {动机}，
以便 {预期结果}，
但目前存在 {阻碍}。
**来源主题**：{主题名称}
**反馈条数**：{N} 条
**严重度**：P0 / P1 / P2
情感分析维度
对每条反馈进行情感标注：
情感极性（1-5 分）
| 分值 | 含义 | 关键词信号 |
|---|---|---|
| 1 | 强烈不满 | 垃圾、骗人、退款、投诉 |
| 2 | 不满意 | 差、不好用、失望、浪费 |
| 3 | 中性 | 一般、还行、凑合 |
| 4 | 满意 | 好用、方便、不错 |
| 5 | 非常满意 | 太棒了、神器、推荐、离不开 |
情感标签
从以下标签中选取：满意 / 失望 / 困惑 / 愤怒 / 惊喜 / 焦虑 / 无感
严重度评分
| 级别 | 定义 | 行动 |
|---|---|---|
| P0 | 影响核心功能，用户无法完成主要任务 | 立即转化为需求 |
| P1 | 影响使用体验，但有替代方案 | 排入下一迭代 |
| P2 | 轻微不满，不影响核心使用 | 记录观察 |
竞品提及检测
在反馈中自动标记竞品名称：
## 竞品提及记录
| 竞品名称 | 提及次数 | 对比维度 | 情感倾向 |
|---------|---------|---------|---------|
| {竞品1} | {N} 次 | {功能/价格/质量} | 正面/负面 |
| {竞品2} | {N} 次 | {功能/价格/质量} | 正面/负面 |
竞品提及频率表同步至 competitive-analysis skill 作为输入。
严重度 × 频率矩阵
将所有提炼出的问题按两个维度排布：
低严重度 高严重度
高频率 │ 快速修复（P2） │ ★ 优先解决（P0） │
│ 体验优化，快速迭代 │ 核心问题，立即响应 │
├─────────────────────┼────────────────────┤
低频率 │ 监控观察 │ 深度调研（P1） │
│ 记录但暂不行动 │ 用户访谈跟进 │
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.
- 3d ago First seen · 189 lines · 31 tokens per session scan A dd74f3f71b6d
user-feedback-analysis is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 16d ago), licensed MIT. It adds 31 tokens to every session and 1,981 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
check-understanding
Phase quiz for AI Engineering from Scratch. Trigger with "quiz me", "test phase", "check my understanding", "do I know phase 3", or /check-understanding .
find-your-level
Interactive quiz that maps your AI/ML knowledge to a starting point in the 260-lesson, 20-phase AI Engineering from Scratch curriculum. Trigger phrases: "where should I start", "find my level", "what do I know", "which phase", "assess my knowledge", "placement test", "skip ahead".
agent-memory-mcp
A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).
audit-agents-skills
Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice templates.
eval-agents
Audit Claude Code agents defined in .claude/agents/ for description specificity, model tier appropriateness, tools scoping, and system prompt quality. Detects dispatch ambiguity between agents, flags over-permissive tool grants, and checks for human-in-the-loop patterns that break programmatic orchestration. Use when…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.