By midpage-ai
Litigation skills built on the Midpage MCP: draft briefs, research memos, and litigation updates; cite-check filings — every citation verified against primary law.
Cite-checks a brief, motion, or memo (PDF/Word): verifies each cited case is real, supports the proposition, is good law, and quoted accurately. Returns one marked-up .docx with comments and redlines.
Drafts court filings — motions, memoranda of law, appellate briefs — as court-ready .docx, with Midpage research behind every citation. Use to "draft a motion to dismiss," "write the brief."
Writes a formal objective legal research memo (Questions Presented, Brief Answers, Facts, IRAC Discussion, Conclusion) as a .docx. Use to "draft a research memo on whether…" Predicts, never advocates.
Writes public-facing litigation updates — blog posts, client alerts, LinkedIn/X posts — on a federal case or legal development. Use to "write a blog post about…," "draft a client alert on…"
External network access
Connects to servers outside your machine
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A suite of litigation skills for Codex, built on the
Midpage MCP. Each skill is a finished-deliverable workflow: the model
researches against Midpage's case-law tools (search, analyzeOpinion, findInOpinion,
analyzeDocketReport, analyzeDocketFiling) and never asserts law, rules, or record facts
from memory — every citation links to ground truth.
| Skill | Deliverable |
|---|---|
draft-brief | A court-ready filing (brief, motion, appellate brief — not complaints), research-led, rule-compliant, every cite linked |
draft-long-form-memo | The classic objective research memorandum — predicts, doesn't advocate |
litigation-update-post | A public firm-style blog post, client alert, or social post, public sources only, with disclaimer |
cite-check | PDF/Word in → a marked-up .docx out: cover page, the document recreated exactly, every finding as a Word comment or redline |
Each skill folder is self-contained: its SKILL.md, shared method guides under references/
(citations, litigation writing, court rules, Word rendering), and scripts/legal_docx.js —
the single Word renderer all skills use (requires the docx npm package; the skills install
it with npm install docx in the working directory, Node 18+).
.codex-plugin/plugin.json plugin manifest
.mcp.json Midpage MCP server config
skills/<name>/ one self-contained skill per folder
SKILL.md
references/ shared method guides + skill-specific references
scripts/ legal_docx.js (+ skill-specific scripts)
This repo is the distribution artifact for Codex. The skills are developed and exported from Midpage's internal repository; edits land there first and are re-exported here.
npx claudepluginhub midpage-ai/litigation-skills --plugin midpage-litigationUpstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Production-grade vibe coding suite. Structured workflows from discovery to deployment: start, build, ship, fix, refactor.
Semantic search for Claude Code conversations. Remember past discussions, decisions, and patterns.