Use when asked to compare two annual reports, put two companies from the same sector side by side, or check whether two companies' adjusted numbers mean the same thing. Takes two uploaded annual reports from one sector and compares them on five ratios computed with identical definitions from audited figures, flagging every place the companies define a metric differently. Produces a page-referenced comparison table, a definitions-differ section (adjusted vs statutory, inside vs outside the audited statements), and three questions to ask before believing either company's highlights. Educational, not financial advice.
“Compare these two annual reports on the same basis”“Both companies say their margin is 20% — is that the same 20%?”“Put these two retailers side by side using the same ratios”“Which of these two reports should I trust more, and why?”
What to give it
▸Two uploaded annual report PDFs. — Hard requirement: if fewer than two are attached, ask and stop.
▸Same sector. — Confirm from each report's own business description `(p. N)`. If the sectors differ, say so, state that the ratios will not be comparable, and proceed only if the learner insists; keep the warning at the top of the artifact.
▸Optional(optional) — which five ratios, if the learner has a preference (default: the sector menu below).
✅ The bar it holds itself to
Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.
✓Two reports uploaded and the sector confirmed from both, with pages — pass/fail
✓Every ratio uses one written formula applied to both companies — pass/fail
✓No company-reported ratio appears in the comparison table — pass/fail
✓Every input cell for both companies carries a page — pass/fail
✓Every missing input yields a not-computable row naming the company and input — pass/fail
✓The definitions-differ table covers the highlighted profit, cash, and growth measures of both companies — pass/fail
✓Every definitions-differ row states the effect on the comparison with an amount or "not quantifiable from the report" — pass/fail
✓Exactly three questions, each with a page or not-disclosed marker per company — pass/fail
⚠️ What it refuses to do
Do not compare absolute amounts across different currencies or year lengths
Do not accept either company's free cash flow definition, even if both claim the same name
Do not average, blend, or "adjust for comparability" — flag the difference and leave both figures as computed
Do not omit a metric from the definitions-differ table because the two definitions look similar; similar is not identical
Do not rank the companies
Install
npx pm-claude-skills add --agent claude # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp