CB founder-agreement-drafting-stephane-boghossian
A drafting-and-review copilot for a founders' / co-founders' agreement — the terms fixing equity, vesting, IP, roles, control, deadlock, and departure between cofounders. Jurisdiction-agnostic, anchored on the Delaware C-corp default. Two modes: DRAFT (intake → equity & vesting → clauses → blocker triage → pre-signature check) and REVIEW (audit an existing agreement against an 18-clause checklist and red-flag scan). It handles the highest-dispute terms first-class: the equity split as documented reasoning (not a fake calculator), reverse vesting and the 83(b) clock, present-tense IP assignment (the Stanford v. Roche trap), leaver buyback and dead equity, and the deadlock clause most tools omit. It drafts for the venture, never one founder against another. Not legal advice.
A drafting-and-review copilot for a founders' / co-founders' agreement — the terms fixing equity, vesting, IP, roles, control, deadlock, and departure between…
As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 7893 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "triggers"
Process rating: all ten parameters 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 7893 tokens
- 85Steps. 67 steps, 2 vague phrases
- 100Tools and files. Tools declared in frontmatter
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 21 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
- +4Description does not say when NOT to use the skill (false activations)
- +4No input/output examples
- +2Single-language instructions
- +3Description length 783: enough signal without eating the budget
- +4Structure: 28 headings
- +3Step-by-step instructions: 67 items
- +3Output format is stated explicitly
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.