Prioritising deal team attention
Ranks agreements by assessed deal risk and identifies the ten most material contracts, helping the deal team focus its legal review where the findings matter most.
— Legal & Contracts
Scores every agreement in a data room on the same diligence criteria and ranks them, so the deal team reads the ten that matter first alongside a red-flag schedule for the SPA discussion.
3–4 weeks → ~25 minutes
For a typical multi-document review workflow
No coding required
— USE CASES
Ranks agreements by assessed deal risk and identifies the ten most material contracts, helping the deal team focus its legal review where the findings matter most.
Highlights change-of-control, assignment and termination provisions that may affect contract continuity, alongside exclusivity and non-compete restrictions that could constrain the buyer.
Assesses liability, indemnity exposure and material ongoing obligations across the contract set. Presents an exposure chart that makes concentrations of contractual risk easier to discuss.
Produces a red-flag schedule covering material risks and unusual terms, providing a structured basis for advisers’ disclosure discussions.
— HOW IT BEHAVES
The mechanics behind this specific template — what it reads, what it calculates, and where a human stays in the loop.
All of your contracts and agreements is processed as one set, so patterns across documents surface instead of being read one file at a time.
Movement across the contract portfolio is visualised from the computed data, so the trend is legible at a glance.
Findings on the contract portfolio are written up as a document that reads like professional output, with each claim tied back to a clause.
Derived columns are added row by row, keeping your source data and the judgement about each clause side by side.
Detail rows are summarised into the grouped view of the contract portfolio without losing the underlying clauses.
Contract diligence can leave deal teams with uneven assessments, buried obligations and limited clarity on which agreements deserve attention. Prioritising deal team attention is the typical trigger — ranks agreements by assessed deal risk and identifies the ten most material contracts, helping the deal team focus its legal review where the findings matter most. Done properly it is defensible; done at pace it becomes a judgement call nobody can retrace. And "properly" usually means 3–4 weeks of manual work.
Skillsize turns that work into a Skill: you supply the material, and what comes back is contract assessment table scored against consistent diligence criteria, with risk-ranked shortlist of the ten most material agreements. The criteria, ordering and review points that make the answer trustworthy are encoded in the Skill itself — which is the difference between a structured method and a prompt someone pastes in. In effect, 3–4 weeks of senior time compresses into ~25 minutes — and the output is comparable across clients, quarters and colleagues instead of shaped by whoever ran it.
Legal Due Diligence Review exports as a structured SKILL.md file and is MCP-ready, so the same method runs in ChatGPT, Claude, Copilot or your own AI products. Adapt it to your methodology, and the intelligence stays yours — not locked to one vendor.
Reads each contract in your register for renewal dates, notice windows and standing obligations, then returns a timeline and an alert list of everything that must be actioned inside 90 days.
Identifies every material change between two versions of an agreement and reads it commercially — what moved, in whose favour, and what must be accepted, pushed back or escalated before signature.
Grades every clause in an incoming NDA against your saved house positions and returns a single verdict — sign, mark up (with the drafting done) or escalate.
Merges a client brief with the scoping-call transcript to extract scope, deliverables, fees and exclusions, pausing for review before drafting the SOW.
Enriches every row of a contracts export with parties, value, term, renewal basis and governing law, turning a messy list into a queryable contract database with the outliers named.
Compares an executed agreement clause by clause against the approved template, logs each exception with severity and approval status, and flags the deviations that keep recurring.