AB legal-doc-summarizer
Read contracts, NDAs, terms of service, employment agreements, leases, and SaaS MSAs and produce a structured summary that flags risk, surfaces hidden obligations, and gives plain-language explanations. Identifies indemnification, limitation of liability, IP assignment, non-compete, auto-renewal, choice-of-law, arbitration, termination, and payment-terms clauses. Compares clauses to market norms and flags deviations. Outputs a redline checklist of what to push back on. NOT a substitute for licensed counsel — provides general information only. Use when asked to summarize a contract, review an NDA, explain an employment agreement, audit a SaaS MSA, check a lease, prepare for negotiation, redline a contract, or understand what a clause means. Triggers on "summarize this contract", "review this NDA", "explain this clause", "redline", "review my offer letter", "lease review", "MSA review", "DPA review", "ToS summary", "what does this mean".
Read contracts, NDAs, terms of service, employment agreements, leases, and SaaS MSAs and produce a structured summary that flags risk, surfaces hidden…
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, failures and branches, running it twice
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 65/100
- 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. 6 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 42 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3497 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 949: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Structure: 21 headings
- +3Step-by-step instructions: 42 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.