Community生产力与协作github.com

wind-alice/conference_call_takeaway_skill

提炼业绩会中的新信息、管理层语气变化、问答焦点与潜在警讯。适用于听完业绩会、阅读纪要后快速更新观点等场景。

conference_call_takeaway_skill 是什么?

conference_call_takeaway_skill is a Claude Code agent skill that 提炼业绩会中的新信息、管理层语气变化、问答焦点与潜在警讯。适用于听完业绩会、阅读纪要后快速更新观点等场景。.

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/wind-alice/alicemarket/tree/main/skills/conference_call_takeaway_skill

Installed? Explore more 生产力与协作 skills: steipete/gemini, steipete/gh-issues, steipete/skill-creator · View all 6 →

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Conference Call Takeaway Skill

Data Dependencies & Prerequisites

It is recommended to use the Wind wind-mcp-skill to obtain underlying data. Before executing, check if wind-mcp-skill is already available locally; if not, prompt the user to install it:

# GitHub
npx skills add Wind-Information-Co-Ltd/wind-skills --skill wind-mcp-skill -g -y

# Gitee Mirror (Domestic)
npx skills add https://gitee.com/wind_info/wind-skills.git --skill wind-mcp-skill -g -y

Skill Positioning

This skill is designed to extract truly valuable new information from earnings calls or similar management communication materials. It focuses on answering: "What new things did management actually say, what tone and wording should be viewed with caution, what did analysts press hardest on, and what content will change the focus of subsequent research?" The output is not a paragraph-by-paragraph recap of the meeting, but rather an aid to help users grasp the most important judgments to update after the call.

Execution Process

Step 1: Confirm the Meeting Scope & Reading Objective

First, confirm which specific earnings call, investor day, or operational update this refers to, and clarify the user's primary use case:

  • Quick review of meeting highlights
  • Determine if management's statements reinforce existing views
  • Distill key takeaways for the team
  • Identify risk points needing further verification after the call

If the user does not specify, default to "rapidly update research judgment after the call."

Step 2: Prioritize New Information, Then Repeated Statements

Meeting materials often contain a large amount of repeated statements. First, screen for parts that provide genuinely new value:

  • Marginal updates on performance, demand, order backlog, profit margins, etc.
  • Supplementary answers to previously unresolved questions
  • Direct responses or evasions on market contentious issues
  • Latest statements on future pace, priorities, and capital allocation

If a section merely reiterates publicly available information, it should be deprioritized and not occupy the core summary.

Step 3: Identify Management Tone & Signal Changes

Beyond literal content, pay attention to changes in expression, including:

  • More optimistic, more cautious, or more defensive compared to the last call
  • Willingness to elaborate on certain topics versus deliberately shrinking away from them
  • Describing risks in more specific terms versus using vague language to obscure uncertainty
  • Inconsistencies, obfuscation, or shifts in focus

The goal of this step is to capture the difference between "what was said" and "how it was said."

Step 4: Distill the True Focus of the Q&A Session

Topics that analysts or investors repeatedly press on during Q&A are usually closer to core market divergences. Focus on summarizing:

  • Which variable was repeatedly questioned?
  • Were management's answers direct, sufficient, and verifiable?
  • Which questions were answered strongly, and which remained vague?
  • Did any question reveal management's lack of preparation or deepening market concerns?

Step 5: Document Post-Call Updates & Red Flags

After finishing the call, clarify:

  • Which pre-existing views were reinforced
  • Which new information requires revising the research framework
  • Which risks are not yet fully exposed but have shown early signs
  • Which operational variables most urgently need further verification

Step 6: Synthesize into a Final Post-Call Summary

The final output should be a refined summary suitable for direct sharing or internal discussion. It should not show the step-by-step reading process or a pile of raw excerpts.

Output Structure


{Stock Name} Earnings Call Takeaways ({YYYY-MM-DD})

1. 30-Second Conclusion

  • Most Important New Information from This Call: {One sentence}
  • Overall Management Tone: {More Positive / Basically Stable / Turning Cautious}
  • Most Worthy Signal to Watch: {One sentence}
  • Post-Call Judgment: {Logic Reinforced / Pending Verification / Risk Rising}

2. New Information from the Call

  • New Information 1: {Content}
  • New Information 2: {Content}
  • New Information 3: {Content}

3. Management Tone Changes

Observation PointThis Call's PerformanceImplication
Demand Statements{Content}{Explanation}
Margin/Cost Statements{Content}{Explanation}
Future Pace Statements{Content}{Explanation}

4. Q&A Focus and Response Quality

  • Market's top concern: {Content}
  • Most thoroughly answered question: {Content}
  • Most vague answer given: {Content}

5. Post-Call Red Flags & Follow-up Verification

  • {Red Flag 1}
  • {Red Flag 2}
  • {Follow-up Verification Point}

6. Research Update Recommendations

  • Judgments that should be updated: {Content}
  • Parts to defer judgment on: {Content}

Quality Requirements

  1. New information must be presented with the highest priority; do not treat repeated meeting content as key points.
  2. Do not merely excerpt management's exact words; translate them into implications for research.
  3. The focus of the Q&A session and the quality of responses must be handled separately, as they are usually closest to market divergences.
  4. Tone changes should be assessed in context, avoiding mistaking normal wording differences for trend shifts.
  5. The output should serve the purpose of "updating views after the call," not becoming a lengthy meeting minutes document.

Individual skills in this repo

This repo contains 19 individual skills — each has its own dedicated page.

wind-alice/add_to_winner_decision_skill

判断盈利仓是否适合继续加仓,并给出加仓前提、节奏安排、保护规则与停止扩张边界。适用于趋势延续、核心持仓滚动放大与强势股二次进攻场景。

wind-alice/after_close_watchlist_recap_skill

在收盘后总结自选股当日表现、驱动因素、强弱分化与次日观察点。适用于每日收盘复盘、维护自选股观察节奏、为次日盘前准备提供输入等场景。

wind-alice/a-share-primary-theme-identification

用于A股市场主线识别,聚焦市场结构 / 题材周期 / 资金行为。本skill主要用户问题回答、撰写报告、撰写金融类文章等场景。本报告输出内容较多,不适合简单对话场景。各类信息与数据的获取,可以使用wind.financial.data工具,以合理的关键字或关键字组合进行获取。每天开盘后、午盘、收盘后,用户都需要快速知道: 今天市场到底在交易什么,真正的主线是什么,情绪在什么位置,明天应该盯哪里。

wind-alice/avatar-charlie-munger-thinking

使用查理·芒格式的逆向思考、激励分析、认知偏误叠加和多学科模型检验复杂决策。用于评估商业与投资判断、组织行为、政策效果、重大选择、全民共识、失败风险,或识别论证中的单一视角和心理盲区。

wind-alice/avatar-nassim-taleb-risk

使用纳西姆·塔勒布式的尾部风险、利益共担、减法、林迪效应和杠铃策略分析不确定性。用于投资、商业、政策、职业、产品或个人决策中的出局风险、不可逆损失、脆弱性、代理问题、新旧方案比较和资源配置。

wind-alice/avatar-naval-ravikant-thinking

使用纳瓦尔·拉维坎特式的重新定义、欲望审计、特定知识和杠杆框架澄清职业、创业、财富、幸福、自由与人生选择。用于识别错误问题、冲突欲望、独特竞争力、AI替代风险、许可依赖、边际成本和长期复利方向。

wind-alice/avatar-warren-buffett-investing

使用沃伦·巴菲特式的能力圈、护城河、管理层诚信、所有者收益和资本配置框架分析企业与长期投资。用于研究公司商业模式、竞争优势、现金质量、管理层、估值、安全边际,或判断一项投资应继续研究、等待还是放弃。

wind-alice/backtest-expert

Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.

wind-alice/breakout_candidate_finder_skill

批量识别突破形态成熟、量价结构健康、催化配合较好的候选股,并输出优先级、触发条件与失效边界。适用于短中线选股、盘前候选池整理、板块轮动中筛选领涨预备股等场景。

wind-alice/breakout_trade_execution_skill

围绕突破交易制定从观察、触发、跟进到失效处理的落地执行方案,兼顾量价确认、环境配合与失败撤退。适用于盘前预案、盘中突破跟踪与强势股首日执行场景。

wind-alice/bull_bear_case_builder_skill

同时搭建看多与看空逻辑,比较证据强弱、关键变量与情景路径,帮助识别核心分歧。适用于防止确认偏误、研究前辩论、投资观点校验等场景。

wind-alice/business_model_decoder_skill

把公司如何获客、交付、定价、赚钱和扩张的逻辑拆解清楚,帮助快速理解业务运转方式。适用于看不懂公司业务、研究前补基础、业务结构梳理等场景。

wind-alice/buyback_program_reviewer_skill

判断回购计划的规模、动机、执行约束与真实利好程度。适用于公司宣布回购、估值争议期、资本配置分析等场景。

wind-alice/canslim_growth_scan_skill

依据成长股框架批量筛选业绩、预期、相对强度与供需结构共振的强势标的,并输出候选分层与跟踪重点。适用于成长股猎手、趋势成长选股、候选池批量扫描等场景。

wind-alice/daily_watchlist_morning_brief_skill

为自选股生成盘前简报,汇总隔夜公告、新闻、价格变化、事件日程与今日观察重点。适用于开盘前快速浏览重点、晨会准备、盘前设定观察顺序等场景。

wind-alice/dcf-model

Real DCF (Discounted Cash Flow) model creation for equity valuation. Retrieves financial data from SEC filings and analyst reports, builds comprehensive cash flow projections with proper WACC calculations, performs sensitivity analysis, and outputs professional Excel models with executive summaries. Use when users need to value a company using DCF methodology, request intrinsic value analysis, or ask for detailed financial modeling with growth projections and terminal value calculations.

wind-alice/dip_buy_decision_skill

判断下跌或回调中的个股是否值得承接,并给出观察区、试错条件、分批节奏与放弃标准。适用于趋势回踩、事件后回落、震荡低吸与左侧谨慎试错场景。

wind-alice/dividend_change_explainer_skill

解读分红提升、削减、暂停或恢复背后的原因、持续性与投资含义。适用于收益型投资判断、公告复盘、长期现金流跟踪等场景。

wind-alice/dividend_growth_entry_skill

寻找股息持续增长、经营质量稳定且估值回落到合理区间的候选股,并输出入场观察区、成长支撑与失效边界。适用于收益成长双目标选股、长期配置、回调布局等场景。

相关技能