AB investor-memo-generator
Generate investor-ready memos, executive summaries, and pitch narrative documents from raw financial data, cap tables, and startup metrics. Produces one-pagers, term sheet summaries, SAFE/note summaries, board update memos, and LP update letters. Structures narrative around traction, financials, and use of funds. Use when a founder or CFO needs to turn a financial model or data dump into a polished investor document. NOT for: building the underlying financial model (use startup-financial-model), cap table math (use cap-table-manager), legal document drafting (requires attorney), or generating pitch decks with slides (output is text/markdown, not slide formats).
As a process B 74/100 · Nearly there — weak spots: running it twice, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 74/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 55Failures and branches. 1 branches
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 39 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2487 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 669: enough signal without eating the budget
- +4Structure: 35 headings
- +3Step-by-step instructions: 39 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.