/Catalogue/Prompt/mohitagw15856/mohitagw15856-pm-claude-skills-acquirer-red-team

Origin: github

acquirer-red-team

Simulate the acquirer's diligence team hunting for reasons to cut your price — their internal red-flags memo with a price-chip estimate per finding. Use when asked to red-team my company before a sale, how will an acquirer attack our valuation, pre-diligence audit, or what will DD find. Produces the acquirer's internal memo (revenue quality, key-person, tech debt, concentration, legal) and a debrief on which flags are fixable before a process.

by mohitagw15856 · updated 5h ago · imported from GitHub

Installs0+0/7d
Security score75/100
Retention 14d0%
GitHub stars1.4K

Skill logic

Execution graph
User message
Prompt rewrites behaviour
Response

SKILL.md

View on GitHub ↗

Acquirer Red Team Skill

Every acquisition has two diligence processes: the polite one in the data room, and the internal one where the deal team lists reasons to retrade the price. This skill runs the second one early. (The mirror-image skill is financial-due-diligence — that's you examining others; this is them examining you.)

What This Skill Produces

  • The internal red-flags memo — what the acquirer's team flags, category by category, with a price-chip estimate per finding
  • The retrade script — the sentence they'll use to reopen price for the biggest flag
  • The debrief — out of character: which flags are fixable pre-process, in what order, and which you must simply pre-disclose

Required Inputs

Ask for these if not provided:

  • The business — revenue (recurring vs one-time), growth, team size, customer count and concentration, stack age, anything sensitive the user already knows about
  • The deal frame (optional) — strategic vs PE buyer, rough multiple expectation; default to a strategic acquirer
  • Skeletons (optional but powerful) — the things the user hopes nobody asks about; the simulation is only as useful as this input is honest

Framework: The Five Hunting Grounds

CategoryWhat chips priceTypical chip size
Revenue qualityNon-recurring dressed as recurring, discount-bought renewals, related-party revenue, pilot revenue counted as land-and-expandMultiple compression — the biggest lever
ConcentrationAny customer >15–20%, channel dependence, one geographyEscrow/earnout territory
Key-person riskFounder-held relationships, single-maintainer systems, no second-in-commandRetention packages carved from YOUR proceeds
Tech & IPUn-transferable licenses, unclear IP assignment (contractors!), tech debt that implies post-close spendDollar-for-dollar price cuts
Legal & complianceOpen disputes, data-protection exposure, misclassified contractors, missing customer consents for assignmentIndemnities, holdbacks, or walk-aways

Per finding, estimate the chip as a range and mechanism (multiple compression / holdback / earnout shift / retention carve-out). Ranges must be defensible from the input; label all assumptions.

Output Format


Project [codename]: Diligence Red Flags — INTERNAL

Simulation — a plausible adversarial reading, not a prediction or financial advice.

Summary Box

Asking frame · our current view · total identified chips (range) · walk-away risks: [n]

Findings

#CategoryFindingEvidence we'd requestPrice mechanismChip estimate

The Retrade Script

[The exact paragraph the corp-dev lead says on the call for finding #1.]

Debrief — out of character

FindingFixable pre-process?Fix and time-to-fixOr: pre-disclose how

One paragraph: the order of operations for the next two quarters, and the one finding to pre-disclose rather than fix (credibility is also an asset).

Route through your M&A counsel and banker before a real process — this is a stress test, not deal advice.


Quality Checks

  • Every finding traces to the supplied facts or a labeled assumption — no invented skeletons
  • Chip estimates carry a mechanism, not just a number
  • Revenue quality is examined first and hardest — it moves the multiple
  • The debrief distinguishes fixable / disclose-and-frame / structural honestly
  • Retention-package math is called out as coming from the seller's proceeds

Anti-Patterns

  • Do not pull punches — the user can get cheerleading from their banker
  • Do not produce findings without price mechanics; "risk" without a chip is noise
  • Do not recommend hiding anything — the debrief may only fix or pre-disclose; concealment discovered in DD kills deals and worse
  • Do not treat PE and strategic buyers identically if the frame is known — they chip differently
  • Do not stay in character in the debrief

Discussion

No comments yet — start the thread.

Sign in to join the discussion.

/More from mohitagw15856/pm-claude-skills

mohitagw15856· 5h agoSandbox
agent-readiness-audit

Prompts · HTML · v0.1.0

Audit whether AI agents can actually use your product — docs, APIs, onboarding, errors, and discoverability, evaluated from a non-human user's perspective. Use when asked if a product is agent-ready, to audit a site or API for AI usability, to prepare for agentic traffic, or when agents keep failing against your product. Produces a scored readiness report with per-surface findings and a prioritised fix list. For optimising a single article for AI citation use aeo-optimizer; for designing the MCP server itself use mcp-server-spec.

#agent-skills#agents#ai-agents

0 1.4K
mohitagw15856· 5h agoSandbox
agm-in-a-box

Prompts · HTML · v0.1.0

Run a club, PTA, or association AGM that finishes on time and holds up later — the notice and agenda done right, a quorum plan, minutes that capture decisions not conversations, elections without awkwardness, and the follow-up that makes decisions real. Use when a volunteer says 'I have to run the AGM', 'what goes in the agenda', 'nobody comes to our meetings', or 'our elections are a mess'. Produces the notice, agenda, chair's script, minutes template, and quorum rescue plan.

#agent-skills#agents#ai-agents

0 1.4K
mohitagw15856· 5h agoSandbox
ai-eval-plan

Prompts · HTML · v0.1.0

Design an evaluation plan for an LLM or AI feature before shipping it. Use when asked how to evaluate a prompt/model/agent, set up an eval harness, define quality metrics for an AI feature, or build a regression gate. Produces an eval plan — task definition, datasets, metrics & rubrics, baselines, automated + human evals, a pass bar, and a regression gate.

#agent-skills#agents#ai-agents

0 1.4K
mohitagw15856· 5h agoSandbox
ai-feature-prd

Prompts · HTML · v0.1.0

Write a PRD for an AI-powered feature, covering the things normal PRDs miss. Use when asked to spec an AI/LLM feature, write a PRD for a feature that uses a model, or plan an AI capability (assistant, summarizer, generator, classifier). Produces an AI feature PRD — problem & UX of uncertainty, model approach, eval criteria, guardrails, fallback behaviour, the data flywheel, and cost/latency budget.

#agent-skills#agents#ai-agents

0 1.4K