janderscience-skills 0.0.0-stage → 1.0.0

package/sources/headcount/plugins/finance/skills/capital-structure-and-covenants/SKILL.md

@@ -0,0 +1,72 @@
+---
+name: capital-structure-and-covenants
+description: Decides how the business is financed and what that financing then requires of it — debt versus equity, weighted average cost of capital as a hurdle rate, how much leverage cash flow can carry, and the financial, affirmative and negative covenants, definitions, test dates and cure rights that come attached. Use this to evaluate a financing option, set an investment hurdle, check whether a planned decision will trip a covenant, or work out what a lender can do when one breaks.
+---
+
+# Capital structure and covenants
+
+Financing is not only where the money comes from. It is a set of ongoing constraints that will
+shape operating decisions for as long as the facility exists, and most of those constraints are
+discovered late.
+
+## Cost of capital sets the hurdle, so compute it rather than choosing a round number
+
+Weighted average cost of capital blends the after-tax cost of debt and the cost of equity in the
+proportions actually used. It is the rate an investment has to clear before it creates value.
+
+Debt is cheaper than equity — the rate is lower, the interest is deductible, and the claim is
+senior. That cheapness is exactly why leverage is tempting, and why the temptation needs a limit
+set in advance. Equity has a cost even though nobody writes a check for it; treating it as free
+is how capital gets consumed by projects that never earned their keep.
+
+## Size leverage to the bad case, not the plan
+
+Leverage amplifies returns on equity and amplifies losses, and the losses arrive first because debt
+service does not wait for recovery.
+
+Capacity is governed by the stability of cash flow, not by an industry average ratio. A predictable
+subscription business carries debt that a project business with lumpy collections cannot. The
+question is never "can we service this at plan" — it is "can we service this at the plan we would
+be embarrassed to show anyone."
+
+## Covenants are where financing becomes an operating constraint
+
+- **Financial covenants** — leverage ratio, interest coverage, fixed charge coverage, minimum
+  liquidity, sometimes a minimum earnings floor. Tested quarterly in most agreements.
+- **Affirmative covenants** — what you must do: reporting by a deadline, audited statements,
+  insurance, notice of material events.
+- **Negative covenants** — what you may not do without consent: additional debt, liens, asset
+  sales, distributions, acquisitions, change of control.
+
+**The definitions matter more than the levels.** Earnings in a credit agreement is a defined term
+with its own permitted add-backs and its own caps, and it will not equal the figure in your
+management accounts. Two facilities at the same headline ratio can allow very different behavior.
+
+**Model covenants forward at every material decision.** A hiring plan, a capex commitment, or an
+acquisition can trip a ratio two quarters out while looking affordable this quarter. Headroom at
+each future test date belongs in the forecast, not in a separate spreadsheet nobody opens.
+
+## When a breach is coming, the timing of the conversation is the whole outcome
+
+Approach the lender before the test date. A waiver requested in advance is a negotiation; a breach
+discovered afterward is a default, and the difference in leverage between those two positions is
+enormous.
+
+Know what the agreement gives you before you need it: cure periods, grace periods, whether an
+equity cure is permitted and how often, and whether cross-default provisions pull other agreements
+in behind this one. Consequences escalate rather than arriving all at once — a fee, then a rate
+step-up, then tightened covenants, then a cash sweep, then acceleration.
+
+## Sources
+
+`references/sources.md` in this skill lists the outside authorities that settle the questions
+here — what each one is authoritative for, and what you may do with it. Check them before
+answering on anything they cover, and cite what you used. Most are free to read and not free
+to reproduce; the use note on each is binding.
+
+## Never
+
+- Sign a facility without modeling its covenants against the downside case.
+- Read a covenant level without reading the definitions it depends on.
+- Arrive at a test date without already knowing the number.
+- Treat equity as costless because no payment leaves the account.

package/sources/headcount/plugins/finance/skills/capital-structure-and-covenants/references/sources.md

@@ -0,0 +1,25 @@
+# Sources — `finance:capital-structure-and-covenants`
+
+<!-- Generated by scripts/build-sources.py from sources/*.toml. Do not edit. -->
+
+Check these before answering on anything they cover, and cite what you used. The use note on each one is binding: most of what a professional cites is free to read and not free to reproduce.
+
+## Interagency Guidance on Leveraged Lending, SR 13-3
+
+Board of Governors of the Federal Reserve System · US · public domain (US government) — quote freely
+
+<https://www.federalreserve.gov/supervisionreg/srletters/sr1303.htm>
+
+**Authoritative for:** What regulators treat as a leveraged transaction and the repayment-capacity, covenant and valuation analysis they expect behind a credit agreement. Supervisory guidance rather than a rule — the analytical lens, not binding law.
+
+## Non-GAAP financial measures — compliance and disclosure interpretations
+
+US Securities and Exchange Commission, Division of Corporation Finance · US · public domain (US government) — quote freely
+
+<https://www.sec.gov/corpfin/non-gaap-financial-measures>
+
+**Authoritative for:** When a non-GAAP measure becomes misleading and therefore prohibited — individually tailored recognition, excluding normal operating costs, improper labeling, and the equal-prominence requirement.
+
+---
+
+Sources are maintained in `sources/` upstream, not here. If one is wrong, out of date, or missing, fix it there — this file is regenerated and an edit to it is lost.

package/sources/headcount/plugins/finance/skills/chief-financial-officer/SKILL.md

@@ -0,0 +1,135 @@
+---
+name: chief-financial-officer
+description: Owns the financial position: planning, budgeting, forecasting, unit economics, cash, and the numbers the business is run and reported on. Use this to build or challenge a budget, model a decision's financial consequence, assess unit economics or runway, evaluate an investment or spend request, set financial controls, or when a plan's numbers do not reconcile. Also use to decide whether the business can afford something.
+---
+
+# Chief Financial Officer
+
+## Why this role exists
+
+The executive accountable for this function. It exists so that one agent — not the orchestrator, and not whichever specialist happens to be in the conversation — owns the call when the specialists disagree or when a decision crosses their boundaries.
+
+## Remit
+
+- Plan, budget, and forecast
+- Unit economics and margin
+- Cash, runway, and capital allocation
+- Financial controls and reporting integrity
+
+## The forecast is a management tool, not a prediction
+
+A forecast's value is not its accuracy — it is that it makes assumptions explicit early enough to
+act on. A forecast nobody revisits has produced a number and no information.
+
+Build it so the drivers are visible and separately wrong. Revenue as one line cannot be diagnosed;
+revenue as volume times price times retention can. When the quarter misses, the useful question is
+which driver moved, and a model that cannot answer it will send the organization looking for the
+problem in the wrong place.
+
+Hold a variance conversation on a fixed cadence and make it about the driver rather than the
+result. Missing on volume while beating on price is a completely different business situation from
+the reverse, and the aggregate hides both.
+
+**Re-forecast when the assumptions break, not when the number moves.** Continuous re-forecasting
+destroys the accountability the original plan created; refusing to re-forecast after a genuine
+change produces a plan everyone privately ignores.
+
+## Cash and profit fail independently
+
+Profitable companies run out of cash, and the mechanism is almost always working capital rather
+than the income statement. Growth consumes cash — inventory bought before it sells, receivables
+extended to close deals, payroll that lands before the collections do. The faster the growth, the
+larger the hole.
+
+Watch the cash conversion cycle, not just the margin: how long between paying for something and
+being paid for it. A pricing or terms change that shortens it can be worth more than a cost
+reduction of the same nominal size, and it is usually available faster.
+
+Runway is a decision variable, not a fact. It moves with hiring pace, collection discipline, and
+payment terms, and each of those is something someone chooses. Know the runway under the current
+plan and under a plan where revenue lands twenty percent short, and know which decisions you would
+take at which trigger — before you are at the trigger.
+
+## Controls exist for the failure nobody is watching for
+
+Financial controls feel like bureaucracy because they mostly prevent things that then never
+happen. The three that earn their cost in almost any organization: separation between whoever
+approves a payment and whoever executes it, a second pair of eyes on any new payee or changed bank
+detail, and reconciliation of the bank to the ledger by someone who cannot post entries.
+
+The most common real-world loss is not sophisticated fraud. It is a convincing email asking for a
+payment redirection, which succeeds when one person can both authorize and pay.
+
+Approval thresholds should reflect what an error costs, not seniority theater. A threshold low
+enough that everything needs approval trains people to approve without reading, which is worse than
+a higher threshold that gets genuine attention. See `finance:internal-controls-and-audit` for the
+design and `security:access-and-identity` for the system permissions that enforce it.
+
+## Being the credible no
+
+Finance is the function that can say a thing is not affordable and be believed, and that credibility
+is an asset that depletes. Say no to everything and the organization stops asking — which does not
+stop the spending, it just moves it where you cannot see it.
+
+Spend the credibility on the decisions that are hard to reverse: headcount, multi-year commitments,
+anything that raises the fixed cost base. Fixed costs are the ones that hurt, because a downturn
+does not reduce them and removing them means removing people.
+
+When you do say no, say what would have to be true for the answer to be yes. "Not at this
+conversion rate" is a negotiation the other side can act on; "it's not in the budget" is a wall
+they will route around.
+
+## What this role owns
+
+These are the artifacts of record. Where two of them disagree, this one is right:
+
+- The budget of record
+- The financial model
+- Spend authority and approval thresholds
+
+## Escalation
+
+Escalate to Chief Executive when the plan is not fundable as written; to Legal & Risk on anything touching financial reporting obligations.
+
+## Sources
+
+`references/sources.md` in this skill lists the outside authorities that settle the questions
+here — what each one is authoritative for, and what you may do with it. Check them before
+answering on anything they cover, and cite what you used. Most are free to read and not free
+to reproduce; the use note on each is binding.
+
+## Tooling
+
+The stack a CFO is accountable for, by layer: the ledger (QuickBooks or Xero at small
+scale, NetSuite, Sage Intacct, or Dynamics 365 in the middle, SAP or Oracle at the top),
+planning (Anaplan, Pigment, Adaptive Planning, Cube), close (BlackLine, FloQast, Numeric),
+payments and spend (Bill.com, Ramp, Brex, Tipalti), and cap table (Carta, Pulley) — and
+similar in each.
+
+Know which system is the record for a number before you report it. Two systems that both
+hold a version of revenue will disagree, and the one you quoted will be the wrong one.
+
+## Never
+
+- Never present a forecast without stating its assumptions and what breaks it
+- Never approve spend that has no owner accountable for the return
+- Do not re-forecast every time the number moves
+- Do not set approval thresholds so low that approval becomes reflexive
+- Do not say no without saying what would make it yes
+
+## Works with
+
+Pairs with Revenue on pricing and recognition; with Operations on cost structure; with every chief on their budget.
+
+## Return contract
+
+End every engagement with these sections, in this order:
+
+1. **Decision or recommendation** — one sentence, stated plainly.
+2. **Reasoning** — the two or three things that actually drove it.
+3. **What this costs** — money, time, capacity, or optionality given up.
+4. **Assumptions** — what must hold for this to be right.
+5. **What would change my mind** — the specific evidence that would reverse this.
+6. **Handoffs** — who does what next, by when.
+
+If any section is empty, say so rather than padding it.

package/sources/headcount/plugins/finance/skills/chief-financial-officer/references/sources.md

@@ -0,0 +1,25 @@
+# Sources — `finance:chief-financial-officer`
+
+<!-- Generated by scripts/build-sources.py from sources/*.toml. Do not edit. -->
+
+Check these before answering on anything they cover, and cite what you used. The use note on each one is binding: most of what a professional cites is free to read and not free to reproduce.
+
+## FASB Accounting Standards Codification
+
+Financial Accounting Standards Board · US · **account required — cite it; the user fetches it**
+
+<https://asc.fasb.org/>
+
+**Authoritative for:** US GAAP as it actually reads — revenue recognition, leases, impairment. The Basic View is free with an account and the text is copyrighted: cite the ASC number, do not reproduce the wording.
+
+## Internal Revenue Bulletin
+
+US Internal Revenue Service · US · public domain (US government) — quote freely
+
+<https://www.irs.gov/irb>
+
+**Authoritative for:** The IRS's own authoritative announcements — revenue rulings, revenue procedures, notices. Where a position has to be supported rather than described, this is what supports it.
+
+---
+
+Sources are maintained in `sources/` upstream, not here. If one is wrong, out of date, or missing, fix it there — this file is regenerated and an edit to it is lost.

package/sources/headcount/plugins/finance/skills/cost-accounting/SKILL.md

@@ -0,0 +1,80 @@
+---
+name: cost-accounting
+description: Establishes what something actually costs — fixed, variable and mixed cost behavior, absorption versus variable costing, job-order, process and activity-based methods, breakeven and operating leverage, and price/volume/mix decomposition. Use this to set a price floor, explain why revenue or margin moved, decide make versus buy, judge whether a product line earns its place, or work out how an allocation basis is distorting a reported margin.
+---
+
+# Cost accounting
+
+Most bad pricing decisions, bad product-line decisions, and bad margin arguments come from the same
+place: nobody agrees what the thing costs.
+
+## Classify cost behavior before you allocate anything
+
+- **Fixed** costs do not move with volume — within a relevant range. Outside that range they step,
+  and the step is usually large: another shift, another facility, another tier of licensing.
+- **Variable** costs move with each unit: materials, payment processing, per-unit fulfillment,
+  usage-based infrastructure.
+- **Mixed** costs have both, and most real accounts are mixed. Split them with high-low or a
+  regression on historical volume rather than guessing the proportion.
+
+The split is not academic. Variable cost sets the floor for one more incremental order. Fully
+loaded cost sets the floor for the business as a whole. Confusing the two is how companies price
+themselves into volume that loses money.
+
+## Know which costing basis you are looking at
+
+**Absorption costing** puts fixed production overhead into inventory and releases it when the unit
+sells. **Variable costing** expenses that overhead as incurred.
+
+Absorption is what external reporting requires. Variable is what decisions want. The consequence
+worth carrying: under absorption, producing more than you sell moves fixed cost onto the balance
+sheet and raises reported profit without a single additional sale. When margin improves and
+inventory grows in the same period, check whether that is what happened.
+
+## Match the costing method to how the work actually runs
+
+- **Job-order** — distinct, identifiable jobs. Construction, custom manufacture, print runs, agency
+  engagements. Cost accumulates per job.
+- **Process** — continuous, homogeneous output. Chemicals, food, high-volume components. Cost
+  accumulates per period and divides across equivalent units.
+- **Activity-based** — worth the overhead when indirect cost is large and consumed unevenly. Its
+  value is rarely precision; it is discovering that a low-volume product consumes a
+  disproportionate share of support, setup, or handling.
+
+**Choose an allocation driver that causes the cost.** Allocating overhead on revenue is not costing,
+it is redistribution — it guarantees the largest product looks worst and tells you nothing.
+
+## Breakeven, margin of safety, and operating leverage
+
+Contribution margin is revenue less variable cost. Breakeven volume is fixed cost divided by
+contribution per unit; margin of safety is how far current volume sits above it.
+
+Operating leverage follows from the mix: a high fixed-cost structure amplifies profit on the way up
+and losses on the way down. It is a deliberate choice about how much volatility the business can
+absorb, and it should be made deliberately rather than accumulated.
+
+## Decompose price, volume and mix
+
+Revenue moved for three reasons and you cannot manage any of them until they are separated.
+
+- **Price** — the change in realized price applied at actual volume.
+- **Volume** — the change in units applied at the original price.
+- **Mix** — the shift in what sold, toward or away from higher-margin items.
+
+This is the single most useful technique here and the one most often skipped. Without it, a mix
+shift toward an expensive product gets reported as a pricing win, and a discount gets buried under
+volume growth.
+
+## Sources
+
+`references/sources.md` in this skill lists the outside authorities that settle the questions
+here — what each one is authoritative for, and what you may do with it. Check them before
+answering on anything they cover, and cite what you used. Most are free to read and not free
+to reproduce; the use note on each is binding.
+
+## Never
+
+- Allocate overhead on revenue and present the result as a product margin.
+- Quote a long-term price off variable cost. It covers the incremental order and nothing else.
+- Compare absorbed unit cost across periods without checking whether production volume changed.
+- Attribute a revenue change to price without separating volume and mix.

package/sources/headcount/plugins/finance/skills/cost-accounting/references/sources.md

@@ -0,0 +1,27 @@
+# Sources — `finance:cost-accounting`
+
+<!-- Generated by scripts/build-sources.py from sources/*.toml. Do not edit. -->
+
+Check these before answering on anything they cover, and cite what you used. The use note on each one is binding: most of what a professional cites is free to read and not free to reproduce.
+
+## 48 CFR Chapter 99 — Cost Accounting Standards
+
+Cost Accounting Standards Board · US · public domain (US government) — quote freely
+
+<https://www.ecfr.gov/current/title-48/chapter-99>
+
+**Authoritative for:** For covered government contractors, the mandatory treatment of cost allocation — consistency in estimating and reporting, indirect and home-office allocation, and the disclosure statement. Where it applies, cost accounting stops being a matter of preference.
+
+## Federal Acquisition Regulation
+
+US General Services Administration, on behalf of the FAR Council · US · public domain (US government) — quote freely
+
+<https://www.acquisition.gov/browse/index/far>
+
+Machine-readable: <https://www.acquisition.gov/far/part-31>
+
+**Authoritative for:** What a competitive sourcing process must do to be lawful — solicitation types, evaluation criteria, competition requirements, and how contract type allocates risk. Binding for federal buying and the reference everywhere else.
+
+---
+
+Sources are maintained in `sources/` upstream, not here. If one is wrong, out of date, or missing, fix it there — this file is regenerated and an edit to it is lost.

package/sources/headcount/plugins/finance/skills/financial-modeling/SKILL.md

@@ -0,0 +1,84 @@
+---
+name: financial-modeling
+description: Builds and stress-tests financial models for forecasting, scenario planning, and decision support — revenue build, cost structure, driver logic, and the sensitivities that show where a plan breaks. Use this to model a decision's financial consequence, build a forecast or long-range plan, evaluate an investment or hire, or pressure-test someone else's model before relying on it.
+---
+
+# Financial modeling
+
+A model is an argument about how the business works, expressed in arithmetic. Its value is the
+argument, not the output precision.
+
+## Structure
+
+Three separated layers, always:
+
+1. **Inputs** — every assumption, in one place, each with a source and a date. An assumption buried
+   inside a formula is invisible and therefore never challenged.
+2. **Calculations** — no hard-coded numbers. Ever. A constant inside a formula is an untraceable
+   assumption.
+3. **Outputs** — the statements and the summary a decision-maker actually reads.
+
+One row, one calculation, carried consistently across periods. Models become unauditable through
+inconsistent rows more than through complexity.
+
+## Build revenue from drivers
+
+Never grow a top-line by a percentage. Build it: volume × price, or accounts × retention ×
+expansion. Driver-based models can be argued with, and being argued with is the point — a growth
+rate cannot be wrong, only optimistic.
+
+Cost structure separated into fixed, variable, and step-fixed. The step-fixed items are where plans
+break, because they move in jumps nobody modeled.
+
+## Sensitivities are the deliverable
+
+A single-scenario model tells you nothing about risk. For every model, produce:
+
+- **Which two or three assumptions actually move the answer.** Usually far fewer than expected.
+- **Breakeven on each** — how wrong can this be before the decision reverses?
+- **Downside case** — not a haircut on the base case, but a coherent story where things go badly.
+
+If a plan only works in the base case, that is the finding.
+
+## Reviewing someone else's model
+
+The description of a model is not evidence about the model. Check these, in this order, because
+each one invalidates everything after it.
+
+- **Trace one number end to end.** Pick an output that matters and follow it back to inputs. If you
+  cannot, nobody else has either, and the model has never actually been reviewed.
+- **Find the hard-coded constants.** Search the calculation area for typed numbers. Each one is an
+  assumption that escaped the input sheet, and they are where overrides hide.
+- **Check the row consistency.** A formula that differs partway across a row is either a deliberate
+  change nobody documented or an error, and the two look identical.
+- **Test the extremes.** Set a key driver to zero and to double. Models frequently break, go
+  negative in impossible ways, or fail to respond at all — which tells you the driver is decorative.
+- **Check that the statements tie.** Cash flow reconciles to the balance sheet movement; the
+  balance sheet balances in every period, not just the first.
+- **Ask what is missing.** Working capital, hiring lag, churn, price changes, tax, and the step
+  costs that come with growth are the omissions that flatter a plan most.
+
+**Then find the assumption doing the work.** Most models rest on one or two numbers, and those are
+usually the least evidenced. Ask where each came from and what it is based on — the answer is
+frequently that it was chosen to make the case work, which is a fine thing to know before relying
+on it.
+
+## Presenting
+
+Lead with the answer, then the two assumptions it rests on most heavily, then what would change it.
+Never present a model without stating what it is most sensitive to — the recipient will assume
+robustness you did not claim.
+
+## Sources
+
+`references/sources.md` in this skill lists the outside authorities that settle the questions
+here — what each one is authoritative for, and what you may do with it. Check them before
+answering on anything they cover, and cite what you used. Most are free to read and not free
+to reproduce; the use note on each is binding.
+
+## Never
+
+- Report a number to more precision than the assumptions support. Five significant figures from a
+  guessed growth rate is false confidence.
+- Build a model whose logic you cannot explain in three sentences.
+- Change an assumption to reach a desired output without labeling it as a target case.

package/sources/headcount/plugins/finance/skills/financial-modeling/references/sources.md

@@ -0,0 +1,27 @@
+# Sources — `finance:financial-modeling`
+
+<!-- Generated by scripts/build-sources.py from sources/*.toml. Do not edit. -->
+
+Check these before answering on anything they cover, and cite what you used. The use note on each one is binding: most of what a professional cites is free to read and not free to reproduce.
+
+## Daily Treasury Par Yield Curve Rates
+
+US Department of the Treasury · US · public domain (US government) — quote freely
+
+<https://home.treasury.gov/interest-rates-data-csv-archive>
+
+**Authoritative for:** The risk-free rate by maturity, as published — the input a discount rate is built from, rather than asserted.
+
+## FRED — Federal Reserve Economic Data
+
+Federal Reserve Bank of St. Louis · US · open data — check the terms before redistributing
+
+<https://fred.stlouisfed.org/>
+
+Machine-readable: <https://fred.stlouisfed.org/docs/api/fred/>
+
+**Authoritative for:** Reference rates, inflation series and macro indicators with a documented API — the honest input for a discount rate or an escalation assumption, in place of a remembered number.
+
+---
+
+Sources are maintained in `sources/` upstream, not here. If one is wrong, out of date, or missing, fix it there — this file is regenerated and an edit to it is lost.

package/sources/headcount/plugins/finance/skills/financial-reporting-and-close/SKILL.md

@@ -0,0 +1,75 @@
+---
+name: financial-reporting-and-close
+description: Runs the period-end close and produces reporting — close calendar, reconciliations, accruals, variance analysis, and reporting that gets read. Use this to shorten or stabilize a monthly close, design a close checklist, investigate a variance, structure management reporting, or work out why the numbers keep changing after close.
+---
+
+# Financial reporting and close
+
+A close is a manufacturing process whose output is a number people will make decisions on. Treat it
+as a process — sequence, dependencies, quality control — and it gets faster and more accurate
+together, which sounds contradictory only if you think speed comes from cutting checks.
+
+## Design the close as a critical path
+
+Map every task with its owner, its dependencies and its duration. Most closes are slow because
+independent work is running in series out of habit, not because any step is long.
+
+Move work out of the close window wherever it does not depend on period-end: reconcile subledgers
+continuously, book recurring accruals from a schedule, prepare consolidation structure in advance.
+Anything you can do on day minus three is a day you are not doing on day two.
+
+Set a **hard cutoff** and hold it. A close that stays open for late entries never finishes and
+teaches everyone that deadlines are advisory.
+
+## Reconciliations are the control
+
+Every balance sheet account gets an owner and a reconciliation. The reconciliation is not the
+schedule — it is the explanation of the difference and what will clear it.
+
+Watch aged reconciling items specifically. An unexplained item that has survived three closes is not
+a timing difference; it is an error that has been carried forward by people assuming someone else
+understood it.
+
+## Accruals and the honesty of estimates
+
+Accrue on the best available evidence and document the basis. The basis matters more than the number,
+because next period someone has to decide whether it still holds.
+
+Track how estimates resolve against actuals. Consistent bias in one direction is information about
+the estimator or the process, and it is invisible unless someone looks.
+
+## Reporting that gets read
+
+Explain variance against a stated expectation — budget, prior period, or forecast — and say which.
+A variance without a baseline is a number.
+
+Lead with the two or three things that changed and why, then supporting detail. A report that
+requires the reader to find the story does not get read, and its absence of readership is discovered
+during a crisis.
+
+Separate **timing** from **run-rate**. A miss caused by something slipping a week is a different
+business fact from a miss caused by demand falling, and conflating them produces the wrong reaction.
+
+## Sources
+
+`references/sources.md` in this skill lists the outside authorities that settle the questions
+here — what each one is authoritative for, and what you may do with it. Check them before
+answering on anything they cover, and cite what you used. Most are free to read and not free
+to reproduce; the use note on each is binding.
+
+## Tooling
+
+Ledger, by scale: QuickBooks, Xero, or FreshBooks for a single entity; NetSuite, Sage
+Intacct, or Dynamics 365 Business Central once you consolidate multiple entities; SAP
+S/4HANA or Oracle Fusion at the top end, and similar.
+
+Close management — BlackLine, FloQast, Numeric, and similar — sits on the ledger and
+tracks the checklist, the reconciliations, and the sign-offs. It buys you an audit trail,
+not discipline. A shared checklist does the same job until the trail is what you lack.
+
+## Never
+
+- Leave the ledger open for late entries after the stated cutoff.
+- Carry an unexplained reconciling item forward a second time.
+- Present a variance without saying what it is a variance from.
+- Report a number you cannot trace to a reconciliation.

package/sources/headcount/plugins/finance/skills/financial-reporting-and-close/references/sources.md

@@ -0,0 +1,35 @@
+# Sources — `finance:financial-reporting-and-close`
+
+<!-- Generated by scripts/build-sources.py from sources/*.toml. Do not edit. -->
+
+Check these before answering on anything they cover, and cite what you used. The use note on each one is binding: most of what a professional cites is free to read and not free to reproduce.
+
+## EDGAR full-text search and submissions API
+
+US Securities and Exchange Commission · US · public domain (US government) — quote freely
+
+<https://www.sec.gov/edgar/search-and-access>
+
+Machine-readable: <https://www.sec.gov/search-filings/edgar-application-programming-interfaces>
+
+**Authoritative for:** What public companies actually reported, in their own filings — the primary source for a competitor's economics, a comparable's margin structure, or how a peer disclosed an accounting policy.
+
+## FASB Accounting Standards Codification
+
+Financial Accounting Standards Board · US · **account required — cite it; the user fetches it**
+
+<https://asc.fasb.org/>
+
+**Authoritative for:** US GAAP as it actually reads — revenue recognition, leases, impairment. The Basic View is free with an account and the text is copyrighted: cite the ASC number, do not reproduce the wording.
+
+## IFRS Accounting Standards
+
+IFRS Foundation · global · **account required — cite it; the user fetches it**
+
+<https://www.ifrs.org/issued-standards/list-of-standards/>
+
+**Authoritative for:** The standards outside US GAAP, and where the two diverge on a given transaction. Free access requires an account; the text is copyrighted.
+
+---
+
+Sources are maintained in `sources/` upstream, not here. If one is wrong, out of date, or missing, fix it there — this file is regenerated and an edit to it is lost.