{"id":4339,"external_id":"plugins_6a76351e505c819197fb58a36fa1e8b1","name":"verify","display_name":"Rohas Legal AI: Verify","developer":"Rohas Nagpal","category":"Productivity","listing_language":"en","listing_language_details":{"method":"cld-0.13.0/listing-v1","reliable":true,"detected_at":"2026-10-01T13:22:04Z","input_sha256":"710d6eac3c115bf5e15f00bfe7363a5ad9c6e0b5b974ce464e37c79a3e36a827","source_fields":["release.description","release.interface.short_description","release.interface.long_description"]},"version":"0.2.1","skill_count":4,"first_seen_at":"2026-09-30T22:02:35.000Z","last_seen_at":"2026-10-03T06:00:00.871Z","last_changed_at":"2026-09-30T22:02:35.000Z","install_count":null,"search_matches":[],"research_summary":null,"research_reviewed_at":null,"metadata":{"canonical_app_id":null,"connector_id":null,"created_at":"2026-08-07T19:47:57.203019Z","discoverability":"UNLISTED","id":"plugins_6a76351e505c819197fb58a36fa1e8b1","is_template":false,"name":"verify","release":{"app_ids":[],"app_manifest":null,"app_templates":[],"description":"Adversarial review, assumption flagging, citation integrity checking, and cross-document consistency skills — a quality-control pass for a finished draft from any practice area.","display_name":"Rohas Legal AI: Verify","id":"pluginrel_bbe7496694b88191b7cf0a826e855ff0","interface":{"brand_color":"#0F172A","capabilities":["Read","Write"],"category":"Productivity","composer_icon_dark_url":null,"composer_icon_url":"https://files.openai.com/content?id=file_00000000c5488208a72b3b6f3d9ba7e4","default_prompt":"Attack this draft the way opposing counsel would before we send it.","default_prompts":["Attack this draft the way opposing counsel would before we send it.","Surface every assumption this opinion depends on.","Check every citation in this document for integrity."],"developer_name":"Rohas Nagpal","logo_url":"https://files.openai.com/content?id=file_0000000040fc8208a3ab9073a3c4e181","logo_url_dark":null,"long_description":"Four reusable quality-control workflows: attacking a draft the way opposing counsel would, surfacing every assumption it depends on, checking every citation for integrity, and cross-checking a document set for internal consistency.","plugin_category_id":"productivity","privacy_policy_url":null,"screenshot_urls":[],"short_description":"Legal quality-control checks","terms_of_service_url":null,"website_url":"https://github.com/rohasnagpal/legal-ai-skills"},"keywords":["legal","verify","quality-control","citations","review"],"onboarding_skill_name":null,"requires_local_executor":false,"skills":[{"description":"Attacks a finished draft the way opposing counsel, a skeptical judge, or a regulator would — hunting for exploitable ambiguity, gaps, internal inconsistency, and unsupported assertions, and writing out the strongest counter-argument to the document's own conclusions. Use this as a final stress test before a document goes out — including phrasings like \"attack this draft before we send it\", \"what would opposing counsel do with this\", \"poke holes in this opinion\", \"find the weakest point in this pleading\", or \"red-team this before we file it\". It finds problems; it does not fix them — hand off to the relevant drafting or redline skill for that. Fires on any finished draft in any practice area — contracts, pleadings, opinions, notices.","interface":{"brand_color":null,"default_prompt":"Use $adversarial-reviewer to attack this draft the way opposing counsel would before we send it.","display_name":"Adversarial Reviewer","icon_large_url":null,"icon_small_url":null,"iconography":"radar","short_description":"Attack a draft the way opposing counsel would"},"name":"adversarial-reviewer","plugin_release_skill_id":"pluginrsk_6a7635203624819189b65910e25e37bf"},{"description":"Surfaces every assumption a draft depends on — factual, legal, definitional, about another party's future conduct, or about scope — whether the document states them or not, so they can be verified or challenged before anyone relies on it. Use this as an independent audit pass on any document — including phrasings like \"what is this opinion actually assuming\", \"surface every assumption in this risk assessment\", \"what would have to be true for this conclusion to hold\", \"audit this draft for unstated premises\", or \"check what this document is taking for granted\". Works on documents from any source, not just this practice pack's own outputs — an opinion received from other counsel, a judgment, an external draft. Fires on any document whose conclusions rest on premises worth checking before relying on it.","interface":{"brand_color":null,"default_prompt":"Use $assumption-flagger to surface every assumption this draft depends on.","display_name":"Assumption Flagger","icon_large_url":null,"icon_small_url":null,"iconography":"radar","short_description":"Surface every assumption a draft depends on"},"name":"assumption-flagger","plugin_release_skill_id":"pluginrsk_6a7635203e2c8191a87c4dd2db56f970"},{"description":"Extracts every citation in a document — statute, case, rule, regulation, quotation, or cross-reference — and states exactly what needs verifying about it and how, attempting live verification where research tools are available this session and producing a structured checklist where they are not. Use this whenever a document's citations need checking before anyone relies on them — including phrasings like \"check every citation in this opinion before we send it\", \"verify these case references are real\", \"does this quote actually say what we're attributing to it\", \"audit the citations in this pleading\", or \"make sure none of these sections are made up\". Directly responsive to the risk this whole practice pack warns about — an AI-assisted draft can produce a citation that looks correct and is not. Fires on any document containing legal citations, quotations, or cross-references, in any practice area.","interface":{"brand_color":null,"default_prompt":"Use $citation-integrity-checker to check every citation in this document before we rely on it.","display_name":"Citation Integrity Checker","icon_large_url":null,"icon_small_url":null,"iconography":"search","short_description":"Check every citation for integrity before relying on it"},"name":"citation-integrity-checker","plugin_release_skill_id":"pluginrsk_6a76352060b48191a157f11b0f25957f"},{"description":"Checks a document or a set of documents for internal consistency — the same fact stated the same way everywhere, dates that don't contradict each other, defined terms used consistently, and figures that match across every mention — and flags every discrepancy found without silently resolving which version is correct. Use this whenever a document set needs a consistency audit — including phrasings like \"check these documents for consistency before we file them\", \"do the dates in this bundle actually line up\", \"make sure this defined term is used the same way throughout\", \"check the figures in this agreement match the schedule\", or \"cross-check this document set for contradictions\". Distinct from citation-integrity-checker, which is about external authority, and assumption-flagger, which is about unstated premises — this is about internal self-consistency of what is actually stated. Fires on any single long document or document set, in any practice area.","interface":{"brand_color":null,"default_prompt":"Use $consistency-checker to check these documents for consistency before we file them.","display_name":"Consistency Checker","icon_large_url":null,"icon_small_url":null,"iconography":"radar","short_description":"Check facts, dates, and figures across a document set"},"name":"consistency-checker","plugin_release_skill_id":"pluginrsk_6a7635202318819192dd2f5adf384045"}],"version":"0.2.1"},"scope":"GLOBAL","status":"ENABLED"},"research":null,"package_metadata":{"name":"verify","author":{"url":"https://rohasnagpal.com","name":"Rohas Nagpal"},"license":"MIT","sources":[{"path":".codex-plugin/plugin.json","sha256":"b14bd46d0ced769fbe894583b1207332cfc6e27c1a9bea69df45cf52f4b2deac"}],"version":"0.2.1","homepage":"https://github.com/rohasnagpal/legal-ai-skills","keywords":["legal","verify","quality-control","citations","review"],"repository":"https://github.com/rohasnagpal/legal-ai-skills","artifact_id":16866,"observed_at":"2026-10-03T06:31:28Z","capabilities":["Read","Write"],"field_sources":{"name":0,"author":0,"license":0,"version":0,"homepage":0,"keywords":0,"repository":0,"capabilities":0},"extraction_version":1,"conflicts_or_errors":[]}}