What does this skill do, and when should you use it?
This Agent Skill supports private-equity diligence meeting preparation. It collects the meeting type, attendees, focus area, existing knowledge, and key concerns, then turns them into a prioritized question list. It covers management presentations, expert network calls, customer references, advisor check-ins, and site visits. It also identifies relevant benchmarks, discrepancies to clarify, red flags to probe, and follow-up requests in a one-page preparation document.
Collects meeting type, attendees, topic focus, prior materials, and concerns from the user; generates questions grouped by priority and topic; provides context for industry growth rates, margin profiles, comparable-company metrics, CIM or data-room points, and discrepancies across sources; flags inconsistencies in financials or the CIM, customer concentration or churn signals, management gaps or departures, unusual accounting treatments, and missing data-room items; and structures the result into logistics, three objectives, a prioritized question list, benchmarks, red flags, and follow-up items.
- A private-equity team preparing for a management presentation needs focused questions on revenue growth, competition, operations, financials, and the forward plan.
- An investor preparing an expert network call needs questions about market positioning, secular trends, competitors, and investor risks.
- A deal team conducting a customer reference call needs to test vendor selection, alternatives, renewal and expansion likelihood, improvement areas, and price sensitivity.
- A diligence team reviewing a CIM or data room needs to convert inconsistencies, concentration, personnel changes, and missing documents into meeting probes.
- An investor needs a disciplined 15-to-20-question agenda for a 60-to-90-minute session, with open-ended prompts and a consistent closing question.
How do you install this skill?
- Do not treat generated questions, benchmarks, or red flags as verified facts; qualified professionals should validate them against the CIM, data room, and independent sources.
- The skill specifies no redaction, access-control, or retention policy for confidential transaction materials; institutional data-governance controls should be added before use.
- The instruction to note body language and confidence levels can introduce subjective judgments and should follow applicable privacy, anti-discrimination, and recordkeeping policies.
- No Chinese localization or mainland-China network reachability is documented.
The skill is located at plugins/vertical-plugins/private-equity/skills/dd-meeting-prep/SKILL.md. The README documents collection installation through Claude Cowork: open Settings → Plugins → Add plugin, paste https://github.com/anthropics/financial-services, and choose the desired verticals from the marketplace list. The README also documents installing the broader plugin collection through its marketplace commands. No standalone installation command for this individual skill is provided in the source.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/anthropics/financial-services.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/plugins/vertical-plugins/private-equity/skills/dd-meeting-prep" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- What haven't we asked about that we should?
After installing the private-equity vertical plugin, invoke it with a prompt such as prep for management meeting, diligence call prep, expert call questions, customer reference questions, or meeting prep for [company]. Provide the meeting type, attendees, focus, known information, and concerns. The skill produces questions, benchmarks, red flags, and follow-up requests. During the meeting, it recommends recording body language and confidence levels and ending with: “What haven't we asked about that we should?”
What are this skill's strengths and limitations?
- Supports management presentations, expert calls, customer references, advisor sessions, and site visits.
- Organizes questions by priority and topic and keeps the list to 15–20 items for a 60–90-minute meeting.
- Combines questions, benchmarks, red flags, and post-meeting requests in one structured output.
- Encourages open-ended, neutral questioning rather than leading the witness.
- The repository is licensed under Apache License 2.0 and maintains skills as Markdown files.
- The skill does not supply external industry data, comparable-company data, or data-room access; benchmarks depend on information already available in the session.
- It does not replace the user's judgment during the interview; the user must observe and record body language and confidence.
- The source does not document a standalone installation flow for this individual skill.
- The source provides no test suite, platform-coverage validation, or detailed failure-handling guidance.
- The README states that repository outputs are not investment, legal, tax, or accounting advice and require qualified professional review.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Diligence Meeting Prep this page ✓ Anthropic · Official | 48 · Use with care | ★ 40k | 1mo ago | Apache-2.0 |
| Buyer Eval — B2B Vendor Evaluation for Claude | 50 · Use with care | ★ 66 | 26d ago | MIT |
| MBB Management Consultant Skill | 46 · Use with care | ★ 145 | 1mo ago | NOASSERTION |
| Client Review Prep ✓ Anthropic · Official | 44 · Not recommended | ★ 40k | 1mo ago | Apache-2.0 |
| Digital Brain Personal OS | 38 · Not recommended | ★ 18k | 13d ago | MIT |
How did FollowSkills review this skill?
The skill only drafts meeting-preparation material and performs no external action or transaction, while requesting meeting context; however, it does not address confidential diligence data handling, least privilege, data flow, user confirmation, retention, or rollback, so trust is materially deducted.
The workflow is internally coherent and covers inputs, question generation, red flags, and output; however, it lacks abnormal-input handling, failure feedback, dependency notes, tests, and key-path reproduction evidence, so the static-review cap limits this score to 8.
It clearly covers management presentations, expert calls, customer references, and advisor meetings, with trigger phrases, inputs, and an output structure; non-fit boundaries, regional or industry variation, and Chinese-language support are unspecified, warranting deductions.
The document has clear information architecture, examples, output guidance, and usage notes; the repository supplies an Apache-2.0 license and official provenance, but the skill lacks its own versioning, changelog, maintenance owner, installation notes, and troubleshooting guidance.
It can produce a usable question list, benchmarks, red flags, and follow-up items, matching the core task; however, it is largely a generic template, benchmarks depend on materials already available in-session, and no representative output or execution evidence shows that only light review is needed.
The skill text is auditable and makes its workflow and outputs explicit; however, it provides no third-party sources, test suite, sample results, or independent reproduction evidence, and the repository CI does not test this skill's behavior, so evidence remains limited.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →