agentleFS
peterbamuhigirepeterbamuhigire/business-plan-skills/skills/meta-strategy/meta-operational-readiness-due-diligence/SKILL.md

meta-operational-readiness-due-diligence

Skill4 starsChanged 19 days agoMITView on GitHub

Use when testing whether a business plan's operating model is locally executable across banking, tax, licensing, payroll, FX, compliance, logistics, privacy, government interface, and partnerships; use section skills for prose drafting.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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
  1. Distinctive:

    Test the consequence of each gap in the operating model, cash flow, margin, runway, schedule, risk register, and funding ask.

    line 67
  2. Distinctive:

    Run a compact red-team: ask what would stop launch, freeze cash, invalidate a proposal, create an employee liability, expose customer data, …

    line 69
  3. Distinctive:

    No plan is called bankable, investor-ready, or achievable while a material readiness blocker is unassessed.

    line 90

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Operational Readiness Due Diligence

<!-- dual-compat-start -->

Use When

  • A plan must demonstrate that its operating model can work in a named country or market.
  • Banking, tax, licences, payroll, FX, compliance, logistics, privacy, public-sector interface, or local-partner assumptions affect viability.
  • A plan needs one cross-section readiness matrix before operations, financial projections, risk, or investor review is finalised.

Do Not Use When

  • The request is only to draft the operations, financial-projections, or risk section; route to that section skill and add this route when cross-section readiness is material.
  • The work contains current legal, tax, payroll, regulatory, privacy, banking, or FX claims but has not been routed to Digital Research and Chwezi Accounting Doctrine where applicable.

Required Inputs

ArtefactSource/providerRequired?If absent
Country, operating sites, business model, transaction flows, currencies, regulated activities, and launch decisionClient intake and approved plan briefYesStop and return the missing context questions
Staffing model, payroll assumptions, vendors, logistics paths, data flows, and technology architectureManagement evidence, discovery, or approved assumptionsYesMark the affected point NOT_ASSESSED
Tax, licensing, privacy, banking, FX, and compliance evidenceDigital Research source register, Chwezi doctrine, and qualified reviewersConditional but required for final claimsKeep the claim qualified and block certification
Integrated model, risk register, milestones, and funding/use-of-funds logicPlan owners and finance modelYes for releaseReturn contradictions to the owning section

Outputs

ArtefactConsumerAcceptance condition
Ten-point operational-readiness matrixPlan owner, investor/lender reviewer, and section ownersEach point has status, evidence, owner, next action, timing, and consequence
Banking, tax, licensing, payroll, FX, and compliance action registerOperations and finance ownersCurrent claims are source-linked; planning assumptions have a review date and sensitivity
Vendor/data/stakeholder/partnership readiness mapOperations, risk, technology, and governance ownersDependencies, service expectations, decision rights, and fallback paths are explicit
Cross-section reconciliation noteOrchestrator and release reviewerOperations, model, risk, timeline, funding ask, and assumptions agree or remain blocked

Evidence Produced

EvidenceFormatAcceptance condition
Readiness matrix and evidence registerMarkdown or structured project recordA reviewer can reproduce each status without treating a generic statement as proof
Assumption and sensitivity logModel/workpaperCurrency, payroll loading, payment costs, compliance timing, and logistics effects are visible
Blocker and handoff logStage register or release bundleEvery missing or failed point has an owner, consequence, recovery action, and restart condition

Workflow

  1. Freeze the jurisdiction, launch scope, business model, transaction flows, and decision audience. Do not start with a generic country checklist.
  2. Translate the ten readiness points into observable tests:
    • banking: account, rails, limits, settlement, multi-currency, integration, reconciliation, and fallback;
    • tax: entity activity, tax classification, indirect-tax treatment, invoicing, filing surface, and reviewer route;
    • licensing: regulated activity, responsible authority, approval dependency, lead time, and launch hold point;
    • payroll: employee/contractor model, fully loaded cost, statutory source dependency, leave/termination exposure, and payment route;
    • FX: billing currency, cost currency, exposure, pricing/reset mechanism, cash buffers, and sensitivity;
    • compliance calendar: registration, filing, renewal, reporting, data, insurance, and contract milestones with owners;
    • logistics: suppliers, last-mile route, service levels, lead times, failure handling, and alternate source;
    • data protection: data classes, residency/transfer, security controls, retention, processor chain, incident route, and reviewer;
    • government interface: policy-monitoring owner, legitimate engagement channels, escalation, and conflict safeguards;
    • local partnerships: role, evidence of standing, due diligence, incentives, deliverables, and exit or substitution path.
  3. Classify every item as verified, context-bound, planning-assumption, partial, or NOT_ASSESSED. A user-provided framework is a hypothesis source, not proof of a current rule.
  4. Route current legal, tax, licensing, privacy, payroll, FX, and banking claims to Digital Research source evaluation and verification. Route money-flow, payroll, tax, banking, FX, and reporting treatment to Chwezi Accounting Doctrine and the required professional reviewer. Never hardcode a rate, deadline, exemption, or regulator outcome in this skill.
  5. Test the consequence of each gap in the operating model, cash flow, margin, runway, schedule, risk register, and funding ask. Add a downside case where the gap can delay launch, increase cost, or reduce collections.
  6. Reconcile the matrix with 08-operations-plan, 10-financial-projections, 12-risk-analysis, implementation timing, and funding/use-of-funds. Return contradictions to the owning skill; do not silently choose the most favourable value.
  7. Run a compact red-team: ask what would stop launch, freeze cash, invalidate a proposal, create an employee liability, expose customer data, or make a local partner unusable. Record the smallest evidence or experiment that would retire each blocker.
  8. Release only when every material point is evidenced or explicitly accepted as a dated, owned, risk-bearing assumption. Otherwise keep the plan's readiness state blocked or NOT_ASSESSED.

Decision Rules

FindingActionFailure or risk avoided
A point is described generically, such as “open a corporate account”Specify the operational requirement, evidence, owner, and fallbackHidden transaction or settlement bottleneck
A current statutory or regulatory claim lacks a usable source entryQuarantine it, narrow the wording, and assign a reviewerFalse compliance or stale planning
A gap affects launch, cash, margin, data, or legal exposureAdd a hold point, downside case, owner, and recovery actionOptimistic plan that cannot execute
A local partner or vendor is named without role or evidenceTreat it as an unconfirmed dependency and define substitution criteriaName-dropping and single-counterparty failure
Readiness improves but control, cash, privacy, or delivery quality worsensReject or revise the experiment and restore the safe baselineLocal optimisation

Quality Standards

  • The matrix is country- and business-model-specific; it does not substitute for legal, tax, banking, privacy, or professional advice.
  • Banking, tax, licensing, payroll, FX, and privacy entries state scope, source status, reviewer, review date, uncertainty, and decision consequence.
  • Fully loaded payroll includes employer costs and contract/termination exposure without inventing statutory values.
  • FX treatment connects price, settlement, cost currency, cash timing, and sensitivity to the model.
  • The compliance calendar names owners and triggers; it is not a list of vague “ongoing” tasks.
  • Vendor, data, government, and partnership assumptions have evidence, fallback, and exit logic.
  • No plan is called bankable, investor-ready, or achievable while a material readiness blocker is unassessed.

Capability Contract

Read, search, calculate, and draft within the authorised workspace. This skill is read-only for audit and review by default. It must not open accounts, register taxes, obtain licences, hire staff, sign vendors, lobby officials, certify compliance, submit a plan, or change approved model assumptions without explicit authority and qualified review.

Degraded Mode

If country, source, model, reviewer, or vendor evidence is unavailable, produce only the supported matrix, return a qualified result, mark the affected item NOT_ASSESSED, state the exact evidence needed, and keep release blocked where the point is material. Never convert a missing check into a pass.

Anti-Patterns

  • Generic “local compliance” language. Fix: name the activity, authority, evidence, owner, and hold point.
  • Base salary-only budgeting. Fix: show the loaded cost and source-dependent statutory fields.
  • One exchange-rate assumption with no exposure logic. Fix: show currencies, observation date/source, reset rule, buffer, and sensitivity.
  • Naming a bank, vendor, regulator, or adviser as proof. Fix: record the operational requirement and corroborating evidence.
  • Treating a calendar or stakeholder list as control. Fix: add owner, trigger, evidence, escalation, and review cadence.

Worked Example

For a proposed health-data platform in a new country, the plan may say that banking, privacy approval, a hosting route, and a local implementation partner are required. Until current authority evidence, data-flow review, partner due diligence, and a cash/timeline impact are recorded, each item remains NOT_ASSESSED; the model carries a launch hold point and the funding ask does not assume early revenue.

<!-- dual-compat-end -->

References

  • Uganda formalisation and lender-document checklist — read when a Ugandan plan must show registration, tax, NSSF, licensing, sector approvals, record-keeping and lender documents; all fees and thresholds are checks to verify.
  • skills/pipeline/08-operations-plan/SKILL.md
  • skills/pipeline/10-financial-projections/SKILL.md
  • skills/pipeline/12-risk-analysis/SKILL.md
  • skills/meta-strategy/meta-due-diligence/SKILL.md
  • Digital Research Engine: source-evaluation, source-verification, and docs/continuous-improvement/kaizen-currentness-gate.md
  • Chwezi Accounting Doctrine: tax-statutory-source-register-and-country-packs, payroll-and-statutory-postings-east-africa, fx-management-and-hedging, and bank-and-mobile-money-reconciliation

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.