financial-statement-analysis
Reads a set of financial statements and establishes what changed and why — fluctuation analysis against prior period and against budget, profitability, liquidity, solvency and efficiency ratios, benchmarking, and the non-GAAP measures presented alongside them. Use this to interpret results, review a counterparty's or target's financials, diagnose a deteriorating trend, explain a variance to someone who will act on it, or test whether an adjusted number is honest.
git clone --depth 1 https://github.com/cbrock84/headcount /tmp/financial-statement-analysis && cp -r /tmp/financial-statement-analysis/plugins/finance/skills/financial-statement-analysis ~/.claude/skills/financial-statement-analysisSKILL.md
# Financial statement analysis The statements tell you what happened. Analysis tells you why, and whether it continues. ## Read the three statements against each other A single statement is almost never enough. The income statement reports profit, the cash flow statement reports cash, and the gap between them is usually the story. - **Net income rising while operating cash flow falls** is the signal worth chasing first. It means working capital is absorbing the growth, or revenue is being recognized ahead of collection. - **The balance sheet is a point in time**; the other two cover a period. Comparing a period figure to a point-in-time balance without averaging the balance overstates efficiency ratios. - **Read the notes.** Concentration of customers, debt maturities, commitments, related parties, and subsequent events routinely matter more than anything on the face of the statements. ## Do fluctuation analysis before you compute a single ratio Compare against the prior period **and** against budget. They answer different questions: prior period tells you what changed, budget tells you whether you understood your own business. - **Set a threshold in both currency and percent.** Percent alone sends you chasing large swings on small accounts; currency alone hides a small account that doubled. - **Explain with a driver, not a restatement.** "Revenue up 12%" is the observation, not the explanation. Volume, price, mix, timing, and one-off items are explanations. - **Track how many variances you cannot explain.** A close where three material movements have no owner is telling you something about the underlying records, not about performance. ## Compute ratios against the question you actually have - **Profitability** — gross margin, operating margin, net margin, return on invested capital. - **Liquidity** — current and quick ratio, and the one that usually matters more in practice, days of cash on hand. - **Leverage and solvency** — debt to EBITDA, interest coverage, debt to equity. - **Efficiency** — days sales outstanding, days payable outstanding, days inventory outstanding, and the cash conversion cycle they combine into. Ratios are comparative instruments. One ratio at one date means close to nothing; the trend across periods and the comparison to peers are where the information is. ## Benchmark within industry and roughly within scale Gross margin compared across industries is noise. So is comparing a company at $5M to one at $500M on cost structure — the second has fixed costs the first cannot carry and buying power the first cannot access. Internal benchmarking across segments, regions, or product lines is often more useful than external comparison, because the accounting policies are already consistent. ## Test non-GAAP measures before you repeat them EBITDA, adjusted EBITDA, free cash flow, core earnings, adjusted net income, annual recurring revenue. These exist for a real reason — statutory profit includes items that obscure operating performance — and also because management chooses the adjustments. - **Ask what was added back, and whether it recurs.** A restructuring charge that appears every year is an operating expense wearing a different label. - **Ask whether the adjustment would survive good results.** Adjustments that only appear in bad quarters are presentation, not measurement. - **Reconcile to the nearest statutory measure and show the reconciliation.** A number that cannot be tied back is not a measure, it is an assertion. ## Diagnosing a deteriorating trend Work from the top down and stop at the first level that explains it. Revenue, then gross margin, then operating expense, then working capital, then financing cost. Most deterioration that looks like a demand problem is a margin or working capital problem, and the two call for different responses. ## Never - Present a ratio with no trend and no comparison. A number standing alone is decoration. - Explain a variance by restating it in different words. - Repeat an adjusted measure without seeing what was added back. - Annualize a partial period without saying you did, or apply a seasonal quarter as a run rate.
Concentrates marketing and sales effort on a named set of accounts rather than on volume — qualifying whether the model fits your economics at all, building the account list and the buying group inside each, tiering effort against account value, coordinating so the account experiences one campaign rather than several, and measuring account progression instead of leads. Use this to decide whether to run an account-based program, build one, or work out why an existing one produces activity and no pipeline.
Designs orchestrator-and-subagent hierarchies for a repository — splitting agents by exclusive write surface, pairing every producer with an independent auditor, and enforcing the split with a script that runs in CI. Use this whenever the user wants to set up, expand, audit, or fix a multi-agent or subagent structure for a codebase; asks how to divide work between agents; wants agent charters, roles, or a surface map written; or is hitting agents that collide on the same files, review their own work, or drift from their remit. Also use when sizing a roster or deciding whether a new agent is justified.
Governs models and AI systems in production — intended use, evaluation, monitoring, human oversight, documentation, and the decision to deploy or retire. Use this before deploying a model or AI feature, when defining evaluation criteria, when a model's behavior has drifted, when assessing AI risk or regulatory exposure, or when deciding whether an AI system is fit for a consequential decision.
Produces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grounded in cited sources with the confidence in each claim made explicit. Use this to analyze a market or industry, map competitors, evaluate a market-entry or build-versus-buy decision, produce a research brief, or assemble evidence for a decision. Also use when comparing options that need a structured, evidence-based verdict rather than an opinion.
Optimizes for AI assistants and AI-generated answers — being retrievable, being cited, and being represented accurately when a model answers on your behalf. Use this when traffic is shifting from links to AI answers, when a brand is misrepresented or absent in AI responses, when planning content for retrieval rather than ranking, or when deciding how AI search changes an existing SEO program.
Improves visibility and conversion in the App Store and Google Play — metadata, keywords, screenshots, ratings, and the listing experience that turns an impression into an install. Use this to audit or optimize an app listing, plan a launch listing, diagnose poor install conversion, or improve store search visibility.
Protects and restores data — backup coverage and scope, retention, immutability against ransomware, and proving restores actually work. Use this to design a backup regime, verify restores, plan retention, protect backups from ransomware, or recover from data loss.
Runs the planning cycle — annual budget, rolling forecast, consolidation of business unit inputs, and the variance analysis that explains actuals against plan. Use this to build or challenge a budget, run a forecast cycle, consolidate departmental submissions, explain why results diverged from plan, or improve forecast accuracy.