AC due-diligence-dataroom
Organize, audit, and generate investor or acquirer due diligence data rooms for startups and SMBs. Maps required documents by category (financial, legal, HR, technical, commercial), identifies gaps, generates checklists, drafts document summaries, and produces a readiness score. Supports both fundraising DD (Series A/B, SAFE rounds) and M&A DD (sell-side, buy-side). Outputs structured folder structure, gap report, and investor-ready index. NOT for: tax filing, bookkeeping, smart contract audits, or legal advice on documents flagged as risky (escalate those to counsel). Do not use for public-company SEC filings.
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 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
- 100Tools and files. No external tools needed
- 100Steps. 37 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3649 tokens
- low 11 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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 618: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 37 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.