Explorar skills
31.375 skills encontradas
niche-signal-discovery
Discover niche first-party signals that differentiate Closed Won vs Closed Lost accounts for ICP analysis. Use when the user provides won/lost customer domain lists and wants differential signals (website content, job listings, tech stack, maturity markers) to build account scoring models and prospecting criteria. Triggers: ICP analysis, niche signals, won vs lost analysis, differential signals, s
deepline-gtm
Use to prospect, enrich, qualify, and activate outbound — especially when users mention Deepline, CSV processing, lead/account/contact research, waterfall enrichment, email or LinkedIn lookup, personalization, scoring, or campaign activation. Route CSV-heavy and provider-driven requests here, then rely on linked sub-docs and provider playbooks for execution details. Providers: adyntel, ai_ark, api
pm-aarrr
Use when: 产品上线后需要分析用户增长、制定增长策略、诊断产品健康度、优化AARRR各环节 Do NOT use when: 产品未上线、仅需单一指标分析无需全链路
pm-report
Use when: 需要生成数据报告、收集整理用户反馈、进行数据驱动的分析汇报 Do NOT use when: 数据已由BI系统自动生成、无需人工分析
ucai-patterns
Use when the user asks about Claude Code best practices, how to write agents, how to use hooks, how to manage context, or how to work effectively with Claude Code's native systems
pm-user-story
Use when: 需要将需求转化为用户故事、准备敏捷开发任务、进行需求拆分、编写验收标准 Do NOT use when: 需求已可直接进入开发、团队不使用用户故事格式
pm-data
Use when: 需要设计产品数据指标、规划数据埋点、建立数据监控体系、进行数据分析和趋势预测 Do NOT use when: 数据指标已明确、仅需简单统计无需指标体系
pm-docs
Use when: 需要输出PRD/BRD/MRD产品文档、方案文档、商业计划文档、需要文档模板 Do NOT use when: 文档已完备无需生成、仅需口头讨论无需书面输出
feishu-voice-sender
Um remetente de mensagens de voz do Feishu que envia arquivos de áudio MP3 como clipes de voz para chats privados ou em grupo do Feishu, em vez de anexos de arquivo.
workflow-hello-world
Create a cloud Deepline workflow that runs on a recurring cron schedule or via webhook, inspect it, and validate trigger behavior end to end.
pm-demand
Use when: 开始新产品规划、需要系统化收集需求、验证产品想法真伪、用户提到"我想做一个产品" Do NOT use when: 需求已明确且已验证、仅需执行而非调研
memory-optimize
Optimizes Claude Code memory files in 4 interactive steps: removes duplicates, migrates rules to CLAUDE.md/rules files, compresses remaining entries, validates with cleanup. Typical reduction: 30-50% on token count.