due-diligence
Skill62 starsChanged 12 days agoMITView on GitHub
Investigate commercial, operational, financial, strategic, and technology claims for acquisition, investment, partnership, or vendor decisions. Use for M&A targets, data-room analysis, quality of earnings, customer concentration, working capital, synergies, and diligence recommendations.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- Nimbleway/agent-skillstheir own version, first seen Nov 1, 2026
- pengasuzie/claude-skillstheir own version, first seen Mar 2, 2026
- pengasuzie/claude-code-startertheir own version, first seen Feb 27, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- Nimbleway/agent-skills★ 61same name
- pengasuzie/claude-code-starter★ 1same name
- pengasuzie/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository16 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- change-managementSkill
- client-deliverablesSkill
- engagement-pricingSkill
- engagement-setupSkill
- financial-modelingSkill
- implementation-planningSkill
- org-designSkill
- process-excellenceSkill
- project-closeoutSkill
- project-governanceSkill
- proposal-developmentSkill
- strategic-analysisSkill
- thought-leadershipSkill
- workshop-facilitationSkill
- writing-styleSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 23
Use commercial and operational diligence for customers, market, management, technology, vendors, and operating feasibility.
- Distinctive: line 31
Test funding and integration feasibility separately from valuation.
“Common” is measured: kept by at least 6 in 10 of the 3 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.
Files
Due Diligence
Determine whether the opportunity is viable, what remains unverified, and which findings change value, terms, conditions, or the operating decision. Adapt to the transaction: an acquisition needs price and funding implications; a vendor assessment may turn on service continuity, switching cost, or exit rights.
Establish the decision, materiality, deadline, access, and scope from the brief. Use available materials before requesting more. Prioritize unknowns that could change the decision, and continue independent work while access is incomplete. A data gap is a limitation or risk to investigate, not proof of concealment. Do not invent data, interviews, benchmarks, or assurances.
Investigate the thesis
State the propositions that must hold for the opportunity to work and the evidence that would disprove them. Focus effort on concentration, renewal, earnings quality, cash requirements, capabilities, and other drivers material to this case. Do not require every diligence stream for a narrow assignment.
For each consequential finding, record the claim, source and period, test performed, result, limitation, and decision implication. Preserve conflicts between management accounts, presentations, contracts, and customer records. Reconcile dates, entities, definitions, and populations before selecting or combining figures. Source agreement is meaningful only if the evidence is sufficiently independent.
Use commercial and operational diligence for customers, market, management, technology, vendors, and operating feasibility. Use financial diligence and integration for QoE, working capital, cash conversion, deal adjustments, synergies, and Day 1 readiness.
Translate findings into the decision
Distinguish a deal killer or unacceptable operating exposure, a condition to clear before commitment, an adjustment to price or terms, and an issue that can be managed after commitment. An unquantified risk can still determine the choice. Do not discard a finding because it cannot yet be converted into a dollar amount.
Quantify an adjustment only where its basis is defensible. Avoid double-counting the same exposure in earnings, cash flow, valuation multiple, and a separate discount. Generic concentration thresholds, EBITDA-adjustment percentages, or synergy haircuts are not transaction facts. Use the client's risk appetite and comparable evidence; otherwise show case-specific scenarios and limitations.
Test funding and integration feasibility separately from valuation. A price adjustment does not cure a continuity, consent, or capability problem. Mitigation changes risk only if it is feasible, funded, owned, and tied to the exposure; an earn-out or escrow does not automatically replace lost customers.
Deliver
Lead with proceed, proceed subject to specific conditions, defer, or decline as the evidence supports. Explain the thesis, strongest supporting evidence, material concerns, value or term implications, unresolved tests, and decision-changing conditions. State what was and was not verified. Do not claim audit, legal, security, or technical assurance beyond the work performed.
For further work, give a prioritized request or test with purpose, owner by role if unknown, and timing relative to the deadline. Draft customer questions or outreach when useful; contact people or use restricted systems only within the user's authorization. Keep numerical cells compact and reasoning near the finding it supports.
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
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.

