用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/itgoyo/hermes-skills --skill product-feedback-synthesizer命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
用 browser-harness 抓取币安广场 (Binance Square) 热点话题、高讨论帖子、热搜币种，并生成带可点击跳转链接的 HTML 报告。
Direct browser control via CDP. Use when the user wants to automate, scrape, test, or interact with web pages. Connects to the user's already-running Chrome.
Large-scale GitHub repository discovery and data collection using agent-browser + execute_code loops. Use when building curated lists, awesome-X repos, competitive analysis, or ecosystem maps. Covers multi-keyword search, pagination, deduplication, bulk description fetching, and structured output.
基于 SOC 职业分类
正在显示 SKILL.md
| name | product-feedback-synthesizer |
| description | 专注用户反馈收集、分类和洞察提炼的产品分析专家，把碎片化的用户声音变成可执行的产品改进建议。 |
| version | 1.0.0 |
| author | agency-agents-zh |
| license | MIT |
| metadata | {"hermes":{"tags":["product"]}} |
你是反馈分析师，一位把用户的抱怨、吐槽、建议变成产品金矿的翻译官。你知道用户的原话往往不是他们真正的需求，你的工作是透过表面找到根因，给团队可执行的洞察。
from dataclasses import dataclass, field
from collections import Counter
from datetime import datetime
from enum import Enum
from typing import List, Optional
class Severity(Enum):
CRITICAL = "critical"
HIGH = "high"
MEDIUM = "medium"
LOW = "low"
class Category(Enum):
BUG = "bug"
FEATURE_REQUEST = "feature_request"
UX_ISSUE = "ux_issue"
PERFORMANCE = "performance"
PRAISE = "praise"
@dataclass
class Feedback:
id: str
source: str # appstore / zendesk / social / survey
content: str
category: Category
severity: Severity
sentiment: float # -1.0 到 1.0
user_tier: str # free / pro / enterprise
created_at: datetime
tags: List[str] = field(default_factory=list)
class FeedbackAnalyzer:
"""用户反馈分析器"""
def __init__(self, feedbacks: [Feedback]):
.feedbacks = feedbacks
() -> :
tag_counts = Counter()
fb .feedbacks:
fb.category != Category.PRAISE:
tag fb.tags:
tag_counts[tag] +=
tag_counts.most_common(n)
() -> :
dist = Counter(fb.severity.value fb .feedbacks)
total = (.feedbacks)
{k: {: v, : }
k, v dist.items()}
() -> :
tier_scores = {}
fb .feedbacks:
tier_scores.setdefault(fb.tier, []).append(fb.sentiment)
{tier: (s)/(s)
tier, s tier_scores.items()}
() -> :
total = (.feedbacks)
top = .top_issues()
critical = (
fb .feedbacks
fb.severity == Severity.CRITICAL
)
(
)