verification-foundation

Plugin verification-foundation from marketplace matematic-skills-en in matematicsolutions/awesome-matematic-skills-en. Commands read from the repo's manifest — 17 days ago.

Skills (10)

• adversarial-legal-review-en

  A red team for a high-stakes deliverable - takes a finished, high-stakes document (a legal opinion, a DD/M&A memo, a court/board submission, a recommendation) and runs an adversarial debate: a builder constructs the strongest version of the thesis, an attacker tears it apart with counter-arguments a

• citation-extraction-en

  Extracts the legal citations from an English-language text by pattern and rule, with no LLM in the extraction step, so the same text yields the same list every run - ECLI (CJEU and national), EU act identifiers (CELEX, Official Journal references, Regulation and Directive numbers), case names, and c

• clause-checklist-en

  A clause checklist for a single contract - walks the contract against 41 clause categories (the CUAD taxonomy), assesses which of them this deal needs, and marks each applicable one present / absent / risky, so the clause that should be there but is missing does not slip through. Extractive (quotes

• deliverable-fidelity-en

  Checks whether the final document still carries what the analysis actually found. Takes the list of findings with their severities and the finished deliverable, runs a mechanical coverage check with a bundled zero-dependency script, then an LLM spot-check on the RED findings for tone-downgrading, an

• intake-sufficiency-en

  Scores whether an instruction or brief is complete enough to start work on. Before any legal analysis begins, checks that the purpose, scope, parties, facts, constraints and success criteria are actually present; lists the gaps and ambiguities; turns each gap into a question ready to send to the cli

• judicial-first-impression-en

  Assesses a legal submission or structured argument from the perspective of a judge reading it COLD, under time pressure, with a docket of several hundred cases. Returns a structured seven-part assessment: what the case appears to be about, immediate points of confusion, what feels strong, what feels

• legal-request-router-en

  Triage for a legal request. Looks at the question (and optionally the finished deliverable) and decides which verification path to run: plain answer, citation checking, adversarial review, or the full route. Scores complexity and risk and returns a routing decision with its reasoning and an ordered

• legal-syllogism-en

  Builds the explicit legal syllogism for an issue - lays out the major premise (the rule and its interpretation), the minor premise (the material facts), the application (subsuming facts under each element of the rule), and the conclusion, then flags the weak links: unstated assumptions, contested fa

• opposing-counsel-attack-en

  Single-pass opposing counsel attack on a legal argument - takes on the role of experienced counsel for the other side who has been handed your submission and told "find every way to beat this". Produces a six-section result: core theory of attack ("this case stands or falls on [assumption]"), a reco

• output-scoring-en

  Scores the quality of an AI legal output before it goes out, in two layers: objective (mechanically checkable - do the citations exist, are the provisions and dockets real) and subjective (LLM-as-judge on a 1-5 rubric: legal correctness, completeness, clarity, jurisdiction fit, grounding/anti-halluc

Similar plugins