agentleFS
MicrosoftKnown publishermicrosoft/cat-agent-skills/submissions/meeting-prep/SKILL.md

meeting-prep

Skill101 starsChanged 16 days agoMITView on GitHub

Prepares a seller for one upcoming customer conversation such as what to learn, say, prove, and ask, with an evidence-backed next move and a private editable brief. Use when asked to "prep my customer call", "brief me before my sales meeting", "prepare for this buyer demo", "plan my renewal conversation", or "build talking points for this opportunity meeting". Do NOT use for past-meeting recaps, broad account plans, pipeline audits, seller coaching, standalone pitch decks, or automatic outreach.

53 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use email-digest, meeting-followup and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • QuixiAISkill

    email-digest

    Digest and ingest emails into memory, surfacing important threads and action items

    Also in 3 projects that use this

  • yakatotechSkill

    meeting-followup

    Create meeting minutes and follow-up email from meeting notes in one workflow. Execute all post-meeting tasks at once

    Also in 3 projects that use this

  • vivy-yiSkill

    social-listening

    Use when needing to understand audience needs, monitor brand mentions, track competitor activities, discover trends, or gather market intelligence from Xiaohongshu conversations

    Also in 3 projects that use this

  • refly-aiSkill

    zoom

    Integrate with Zoom for video meetings. Use when you need to: (1) schedule Zoom meetings, (2) create instant meetings, or (3) manage meeting details and invitations programmatically.

    Also in 3 projects that use this

  • vijpatel7Skill

    cold-outreach

    Write highly effective cold emails and LinkedIn messages to recruiters, hiring managers, founders, and engineers at target companies. Based on Ben Lang's proven cold outreach framework (Next Play). Use when the user wants to: (1) write a cold email to someone at a company they want to work for, (2) craft LinkedIn messages or InMail to recruiters or hiring managers, (3) reach out about unadvertised positions, (4) follow up on outreach or applications, (5) network with founders or executives for job opportunities, (6) prepare an outreach campaign to multiple companies. Triggers on: cold email, outreach, reach out to, contact recruiter, email founder, write to hiring manager, job email, networking email, LinkedIn message, InMail.

    Also in 4 projects that use this

  • QuixiAISkill

    weekly-review

    Review the past week across goals, tasks, calendar, journal, and commitments, then propose the next week

    Also in 10 projects that use this

  • +1 more from QuixiAI

The file

Show its rules and text

We split this skill into the rules it gives an agent

21 rules. 0 are common, 20 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 49 edited versions we read keep these.

  • 20

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Start this procedure when the user requests preparation for an upcoming customer or sales interaction, including a general request such as …

    line 18
  2. Distinctive:

    Before a substantive brief, establish the intended interaction, its objective or agenda, and at least one relevant meeting-specific fact.

    line 20
  3. Distinctive:

    If timing or participants are unknown, produce a bounded topic-focused brief and mark those sections unknown.

    line 22
  4. Distinctive:

    Use organization-supplied qualification, messaging, approval, and risk criteria when applicable.

    line 62
  5. Distinctive:

    Use the same section headings and order in both.

    line 71
  6. Distinctive:

    Do not include detailed research, lengthy analysis, or full talking points in chat.

    line 77
  7. Distinctive:

    Use clear headings and a contents list or section navigation.

    line 83
  8. Distinctive:

    Keep internal strategy separate from any customer-ready language embedded in the artifact.

    line 87
  9. Distinctive:

    Use these sections in both chat and the artifact.

    line 92
  10. Distinctive:

    Word (.docx): Default for an editable seller reference or discussion guide.

    line 122
  11. Distinctive:

    Markdown (.md): When requested or Office is unavailable or fails.

    line 125
  12. Distinctive:

    Use authorized, format-specific workflows.

    line 127
  13. Distinctive:

    Use supplied materials, relevant internal sources, and public web searches.

    line 131
  14. Distinctive:

    Do not infer buying intent from public developments or decision authority from a job title.

    line 136
  15. Distinctive:

    Verify the save before reporting success and provide the actual link or location.

    line 141
  16. Distinctive:

    Before a write, verify the target and current affected state.

    line 150
  17. Distinctive:

    Do not manufacture a meeting, participant, customer position, outcome, or commitment when the evidence needed to establish it is absent.

    line 157
  18. Very specific:

    Not for recording the outcomes of a completed meeting.

    line 160
  19. Distinctive:

    Not for planning engagement phases across an account over a longer horizon.

    line 161
  20. Distinctive:

    Not for a seller's work review or coaching agenda.

    line 162
  21. Distinctive:

    Not for a broad question-led investigation unrelated to preparation for one interaction.

    line 163

“Common” is measured: kept by at least 6 in 10 of the 49 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Meeting Prep for upcoming customer conversations

Domain: Sales.

Purpose

Prepare the seller a concise sales meeting brief for one upcoming customer interaction: what matters going in, who is expected, what remains owed or unresolved, which questions to ask, and what outcome to seek without presenting a planned conversation as an agreement.

For full preparation, proactively create meeting materials tailored to the upcoming conversation. Follow the Output section for artifact selection and the Research rules for gathering context. Include account or competitive research only when useful for that call and provide clear value to the seller.

Applicability

Start this procedure when the user requests preparation for an upcoming customer or sales interaction, including a general request such as "prepare me for a meeting" whose target is not yet specified. Do not guess a meeting.

Before a substantive brief, establish the intended interaction, its objective or agenda, and at least one relevant meeting-specific fact. If the interaction or objective cannot be established, return only focused preparation questions.

If timing or participants are unknown, produce a bounded topic-focused brief and mark those sections unknown. An objective or agenda can frame proposed questions and desired outcomes; it does not establish customer history.

Potential Data Sources

These are particularly important for this workflow; use your best judgment to use relevant material already supplied or available through applicable tools or sources you can access. These are options, not a mandatory checklist. If needed information is missing, ask the user to provide the input or context needed.

  • Calendar for meeting identity, invite context, agenda, timing, and attendees.
  • Meeting Transcripts for prior decisions, objections, commitments, and continuity.
  • Email for prior meeting notes, recent questions, and customer-facing context.
  • Internal Messaging for internal strategy, blockers, owners, and dependencies.
  • Knowledge & Files for prior meeting notes, strategy documents, and assets.
  • Record Snapshots & Exports for account, opportunity, renewal, and contact context.
  • Sales Intelligence for additional context only when it materially improves preparation.
  • Public web sources for the customer's account, company, and industry context, if not available through internal sources.

Usage situations

  • "Prepare me for a meeting."
  • "Brief me before my next customer call."
  • "Prep me for this customer meeting using the agenda and messages below."
  • "What should I know and ask before my call with this account?"
  • "Which prior commitments and objections should we address in the next discussion?"
  • "Build talking points and a desired outcome for this opportunity meeting."

Procedure

  1. Establish the interaction, customer or deal scope, objective, intended audience, meeting date/time and duration when known, and evidence cut-off. Distinguish a stated objective from a proposed one; do not infer a scheduled event from an intention to meet.
  2. Assemble only context that can affect this interaction: customer priorities, relevant deal state, decision process, solution or commercial constraints, recent substantive conversation, and unresolved questions.
  3. Identify known and expected participants, their evidenced roles and interests, and any decision coverage gap. Keep confirmed participation, invited or expected participation, and suggested participants separate. Record unknown authority rather than inferring it from a title or copied message.
  4. Reconcile relevant dated communications into a short chronology, deduplicating the same interaction across sources. Separate customer statements, seller reports, administrative updates, and interpretations; preserve contradictions and source dates.
  5. Build a commitment check: action, party, source, requested date, proposed date, accepted date when evidenced, current status, and dependency. Distinguish an accepted promise, an attempted action, and a verified outcome. If completion is unknown, make it a question to check, not a claim that the action failed or remains undone.
  6. Prioritize the discussion by the objective, material customer need, timing, dependencies, and supplied organization priorities. Include a service, delivery, competitive, or trust issue only when evidence connects it to this conversation. Do not include unrelated issue history or infer exposure from a shared account alone.
  7. Propose an agenda that moves from shared context to unresolved decisions and next-step agreement. For each material topic, provide the evidence-backed talking point, an open question, why it matters, and the desired outcome. Offer time allocations only when meeting duration is known and label them proposals.
  8. Identify objections or sensitivities to prepare for, claims needing validation, and questions whose answer would change the approach. Separate an evidenced objection from a possible objection; do not script unsupported assurances.
  9. Deliver the brief, highlighting the few issues that most change how to approach the meeting. Keep internal hypotheses and sensitive context separate from any requested customer-shareable agenda or draft.
  10. Include account or competitive research only when it helps with this call's questions, positioning, proof, or decisions.

Judgment

  • An invitation or attendee list is evidence of planned participation, not attendance, decision authority, customer intent, or acceptance of the proposed agenda.
  • A topic discussed is not a decision; a requested or proposed date is not an accepted commitment; an accepted commitment is not proof of completion or a secured deal outcome.
  • Substantive customer evidence outweighs administrative activity for interpreting needs. A recent informal update does not automatically displace an authoritative agreement. Retain conflicting sources unless applicable evidence or a supplied policy resolves them.
  • Missing, inaccessible, stale, conflicting, and verified negative evidence are distinct. No returned communication does not prove disengagement or the absence of commitments. State which sources and periods were actually examined.
  • Use organization-supplied qualification, messaging, approval, and risk criteria when applicable. Without them, explain qualitative priorities and validation needs; do not invent a methodology, score, threshold, probability, or customer promise.
  • Preserve dates, time zones, units, currency, and billing periods when they affect the discussion. Do not combine incompatible commercial amounts or invent prices, conversion rates, deadlines, or a meeting time.

Output

Deliver both a concise chat summary and one saved primary editable artifact, following the sections below. The artifact must contain the complete internal meeting-preparation brief, not just talking points.

Use the same section headings and order in both. The chat summarizes the most important takeaways; the artifact contains the supporting detail. Do not create additional artifacts unless the user requests them.

Chat summary

Aim for maximum 100 words overall, using one short takeaway per section. Prioritize the meeting objective, the recommended approach, the biggest risk, and the next action.

Do not include detailed research, lengthy analysis, or full talking points in chat. Link to the saved artifact and identify any sections that deserve particular attention.

Full preparation artifact

Include all preparation in one artifact, organized so the seller can choose where to spend more time.

  • Use clear headings and a contents list or section navigation.
  • Begin each substantive section with a brief takeaway, followed by supporting detail.
  • Expand where useful; do not apply the chat's brevity limits to the artifact.
  • Include actionable preparation rather than exhaustive background.
  • Keep internal strategy separate from any customer-ready language embedded in the artifact.
  • Label the artifact as internal seller preparation.

Shared output structure

Use these sections in both chat and the artifact. For the Appendix, chat only needs a short pointer to the available research.

  1. Meeting goal Explain why the meeting matters, the buyer's priority, and the outcome the seller should seek. Distinguish confirmed priorities from hypotheses and desired outcomes from agreements.
  2. Relevant context Cover the account, participants, opportunity, prior conversations, outstanding commitments, and seller readiness. Highlight research findings that change the meeting approach; place detailed supporting research in the Appendix.
  3. Conversation plan Provide the proposed agenda, opening, discovery questions, tailored value proposition, proof or demo points, and objections to prepare for. Include a pitch when useful—not automatically. Suggest timing only when meeting duration is known.
  4. Risks and open questions Identify missing information, assumptions, conflicting evidence, and sensitivities. Explain how each material gap could affect the conversation and what would resolve it.
  5. Recommended next actions Specify what the seller should prepare before the meeting, the buyer ask to make during it, and a fallback if the preferred outcome is premature. Label suggested owners and timing as proposals unless already agreed.
  6. Prepared materials In chat, link to the single full-preparation artifact. In the artifact, identify embedded materials and link to useful existing assets. Include newly prepared talking points, pitch outlines, demo guidance, or working matrices within this artifact—not as separate files.
  7. Appendix Include only research useful for this call; omit either or both sections when they do not bring clear value to the seller for meeting preparation.
    • Account research: Relevant business priorities, developments, stakeholder context, and account findings, with their implications for the meeting.
    • Competitive analysis: Identify the potential competitor to the seller, research competitor information that will help seller prepare for customer conversations such as objection handling and product differentiation.

Artifact selection

Choose one format for the complete meeting preparation, respecting the user's requested format:

  • Word (.docx): Default for an editable seller reference or discussion guide.
  • PowerPoint (.pptx): For a pitch or demo rehearsal; retain detailed preparation without making internal strategy customer-facing.
  • Excel (.xlsx): For requirements, evaluation, stakeholder or commitment matrix-led preparation; retain the narrative sections.
  • Markdown (.md): When requested or Office is unavailable or fails; retain complete preparation and disclose limitations, using explicitly unsaved chat content if no authorized save works.

Use authorized, format-specific workflows. Keep content concise and styling simple. Plan changes together and apply them in as few supported batches as practical. Update authorized existing artifacts without creating duplicates or changing unrelated content. Follow Delivery and control for saving and reporting.

Research and competitive-analysis rules

  • Use supplied materials, relevant internal sources, and public web searches.
  • Research proactively when missing, stale, or conflicting information could change the questions, message, proof, or recommended ask.
  • Include account research to help prepare for this customer conversation—not as a generic company profile.
  • Include competitive analysis when a competitor is named, credible evidence indicates alternatives, or competitive positioning materially affects the meeting.
  • Compare alternatives against the buyer's relevant criteria. Cover supported differentiators, strengths and tradeoffs, potential objections, suggested responses, and questions to validate.
  • Do not infer buying intent from public developments or decision authority from a job title. Do not invent competitor weaknesses or superiority claims.
  • Cite sources and dates, distinguish facts from hypotheses, and mark unresolved gaps. Never include confidential information in public research queries.

Delivery and control

Verify the save before reporting success and provide the actual link or location. If saving fails, disclose it and provide clearly labeled unsaved preparation in chat.

Guardrails

Preparation and drafting do not update records, record a completed meeting, schedule an interaction, assign work, send messages, or make commitments. Creating and saving the requested file artifact is permitted in authorized locations. Other consequential actions, including saves or draft creation in business records, sharing, sending, and scheduling, require separate, specific approval of the exact content, target, recipients, and timing as applicable. Before a write, verify the target and current affected state; materially changed content or state for an approval-gated action requires renewed approval. Recheck sharing restrictions and required contact permission before outreach; operator approval does not replace recipient consent or internal authority. Verify each actual effect before reporting completion. Keep proposed, approved, completed, and unconfirmed actions separate; reconcile an uncertain effect before any retry.

  • Do not manufacture a meeting, participant, customer position, outcome, or commitment when the evidence needed to establish it is absent.

When NOT to Use

  • Not for recording the outcomes of a completed meeting; use post-meeting-follow-up.
  • Not for planning engagement phases across an account over a longer horizon; this brief prepares one interaction.
  • Not for a seller's work review or coaching agenda.
  • Not for a broad question-led investigation unrelated to preparation for one interaction.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.