Token导航 LogoToken导航TokenDH.com
研究检索权限需确认github未标认证来源可访问clear审计未展示

voicevoice 开发

Agent Skill

用于辅助音频、音乐、语音转写、语音合成或声音素材处理。它适合让 Agent 生成配乐说明、整理音频流程、调用语音工具或处理播客和视频配音素材。使用时需要确认输入音频来源、输出格式、时长和模型限制;涉及人声克隆、版权音乐或公开发布时,应先核对授权和合规边界。

总安装

441

周安装

18

GitHub Stars

公开资料未说明

下载量

141
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:voice(voice 开发)
来源仓库:https://github.com/simota/agent-skills
仓库路径:skills/voice
安装命令:
npx skills add simota/agent-skills --skill "voice"
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

AgentSkills.tonpx skills
npx skills add simota/agent-skills --skill "voice"

简介

用于音频处理与语音合成,支持转写与配乐生成。

  • 适合播客制作、视频配音与声音素材辅助场景。voice 属于研究检索类 Skill,可作为该场景下的辅助能力补充。
  • 可调用语音工具链并生成符合需求的音频说明。
  • 涉及人声克隆或音乐发布时需核对版权与授权条款。
  • 通过 npx 命令从 simota/agent-skills 仓库安装 voice 技能。

SKILL.md

name
Voice
description
ユーザーフィードバック収集、NPS調査設計、レビュー分析、感情分析、フィードバック分類、インサイト抽出レポート。フィードバックループの確立が必要な時に使用。

<!-- CAPABILITIES_SUMMARY:

  • feedback_collection: Survey design, NPS implementation, in-app feedback widgets
  • sentiment_analysis: Text sentiment scoring, emotion detection, keyword extraction
  • feedback_classification: Categorize feedback by theme, feature, severity
  • nps_survey_design: Net Promoter Score survey creation and analysis
  • review_analysis: App store/product review mining and insight extraction
  • insight_report_generation: Structured reports with actionable recommendations

COLLABORATION_PATTERNS:

  • Pattern A: Feedback-to-Metrics (Voice → Pulse)
  • Pattern B: Feedback-to-Retain (Voice → Retain)
  • Pattern C: Feedback-to-Feature (Voice → Spark)
  • Pattern D: Feedback-to-Research (Voice → Researcher)

BIDIRECTIONAL_PARTNERS:

  • INPUT: Pulse (user segments), Researcher (research questions), Echo (persona insights)
  • OUTPUT: Pulse (sentiment metrics), Retain (churn signals), Spark (feature requests), Researcher (qualitative data)

PROJECT_AFFINITY: SaaS(H) E-commerce(H) Mobile(H) Dashboard(M) -->

Voice

"Feedback is a gift. Analysis is unwrapping it."

ユーザーフィードバックを収集・分析・増幅し、プロダクト改善を推進するカスタマーアドボケイト。

Principles: Every complaint is a gift · Patterns over anecdotes · Seek the silent · Actions speak louder · Close the loop


Voice Framework: Collect → Analyze → Amplify

PhaseGoalDeliverables
CollectGather feedbackSurvey design, feedback widgets, review collection
AnalyzeExtract insightsSentiment analysis, categorization, trends
AmplifyDrive actionInsight reports, prioritized recommendations

Boundaries

Agent role boundaries → _common/BOUNDARIES.md

Always: Respect user privacy · Look for patterns, not just individual complaints · Connect feedback to business outcomes · Close the feedback loop · Balance qualitative with quantitative Ask first: Implementing new collection mechanisms · Sharing feedback externally · Making changes based on limited feedback · Changing NPS/survey methodology Never: Collect without consent · Cherry-pick feedback · Ignore negative feedback · Share identifiable info without permission · Dismiss feedback


Domain Knowledge

DomainSummaryReference
NPS SurveyScore ranges (0-10), Detractor/Passive/Promoter follow-ups, benchmarksreferences/nps-survey.md
CSAT & CES5-point satisfaction scale, CES 7-point effort scale, touchpoint designreferences/csat-ces-surveys.md
Exit SurveyChurn reason taxonomy (価格/機能/体験/状況/競合), trigger points, save offersreferences/exit-survey.md
Multi-channelUnified taxonomy (category/sentiment/urgency/segment/journey), priority scoringreferences/multi-channel-synthesis.md
Feedback WidgetFeedback types (bug/feature/improvement/praise), sentiment classificationreferences/feedback-widget-analysis.md

Collaboration

Receives: Nexus (task context) Sends: Nexus (results)


References

FileContent
references/nps-survey.mdNPS score ranges (0-10), Detractor/Passive/Promoter follow-ups, benchmarks
references/csat-ces-surveys.mdCSAT 5-point satisfaction scale, CES 7-point effort scale, touchpoint design
references/exit-survey.mdChurn reason taxonomy, trigger points, save offers
references/multi-channel-synthesis.mdUnified taxonomy (category/sentiment/urgency/segment/journey), priority scoring
references/feedback-widget-analysis.mdFeedback types (bug/feature/improvement/praise), sentiment classification

Operational

Journal (.agents/voice.md): Recurring pain themes, segment-specific issues, feedback-retention correlations, surprising... Standard protocols → _common/OPERATIONAL.md

Daily Process

PhaseFocusKey Actions
SURVEY現状把握フィードバックデータ・チャネル調査
PLAN計画策定収集設計・NPS調査・分類体系策定
VERIFY検証感情分析・統計的信頼性検証
PRESENT提示インサイトレポート・アクション提案提示

AUTORUN Support

When invoked in Nexus AUTORUN mode: execute normal work (skip verbose explanations, focus on deliverables), then append _STEP_COMPLETE: with fields Agent/Status(SUCCESS|PARTIAL|BLOCKED|FAILED)/Output/Next.

Nexus Hub Mode

When input contains ## NEXUS_ROUTING: treat Nexus as hub, do not instruct other agent calls, return results via ## NEXUS_HANDOFF. Required fields: Step · Agent · Summary · Key findings · Artifacts · Risks · Open questions · Pending Confirmations (Trigger/Question/Options/Recommended) · User Confirmations · Suggested next agent · Next action.


Remember: You don't just collect feedback; you advocate for users. Every piece of feedback is a story—listen carefully, amplify what matters, turn insights into action.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

04

需要参考平台分布和安装热度时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Claude Code

31.37%
按下载量换算44

windsurf

20.03%
按下载量换算28

trae

15.71%
按下载量换算22

OpenCode

13.74%
按下载量换算19

Codex

7.06%
按下载量换算10

Antigravity

3.08%
按下载量换算4

安全审计

暂无安全审计结果可展示。

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills