agentsclimarketplace
Sign in

Forecasting

Skill m-binimran/finance-pack/skills/forecasting

Build a financial forecast (revenue, P&L, cash) from drivers and assumptions, with a clear method and ranges. Use when projecting performance for planning, valuation, or fundraising.From its SKILL.md

Install
npx -y skills add m-binimran/finance-pack --skill forecasting

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.4 KB, 268 tokens by cl100k_base, as published. Nobody here has run it

forecasting

A forecast is a driver tree plus assumptions. Make the drivers and the method explicit.

Process

  1. Pick the method: driver-based (units x price, funnel, cohorts) > naive growth %. Bottom-up where possible.
  2. Anchor to sourced historicals and a base rate; don't extrapolate a recent spike blindly.
  3. Build the drivers: revenue drivers, margin assumptions, cost structure (fixed vs. variable), working capital, capex. State each assumption and where it came from.
  4. Project the P&L (and cash if needed) over the horizon; keep it consistent with the drivers.
  5. Ranges + scenarios: base/bull/bear, and the 2-3 assumptions that matter most (scenario-analysis).
  6. Reality-check against capacity, market size, and history - flag anything that implies the impossible.

Output

  • The forecast (driver assumptions + projected P&L), a base/bull/bear range, and the key swing assumptions - all labeled as estimates.

Guardrails

  • Projections labeled with assumptions (projection-guard); historicals sourced (data-integrity).
  • Give ranges, not false precision; sanity-check against base rates (methodology).

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most finance skills give in 268 tokens

Counted across 469 of the 469 authors here whose files we hold, read 2026-08-07

  • Extract date vendor amount and descriptionin 15 of 469, across 3 files
  • Scan folder for invoice filesin 14 of 469, across 2 files
  • Rename files to standard formatin 14 of 469, across 2 files
  • Show organization plan before movingin 14 of 469, across 2 files
  • Generate summary CSVin 14 of 469, across 2 files
  • Organize files by categoryin 13 of 469, across 1 file
  • Preserve original filesin 13 of 469, across 1 file
  • Flag files missing critical infoin 13 of 469, across 1 file
  • Produce the requested output filein 9 of 469, across 4 files
  • Build best, base, and worst case scenariosin 9 of 469, across 5 files
  • Implement backoff if rate limit errors occurin 8 of 469, across 3 files
  • Determine the weighted average cost of capitalin 8 of 469, across 4 files

Said here and by no other author read

  • label all projections
  • use driver-based bottom-up forecasting methods over naive growth percentages
  • build revenue, margin, cost, working capital, and capex drivers
  • project the profit and loss over the required horizon
  • identify the two or three key swing assumptions
  • reality-check projections against capacity and market size

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.