cite-check

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.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced skill body with strong validation checkpoints and clean one-level-deep references. Its main weakness is length — motivational prose and extended comparison examples could be trimmed for token efficiency.

Suggestions

Trim the opening motivational sentence ("AI-drafted briefs invent cases…") — the value proposition is already implied by the checks.

Compress the "Too long / Right" comparison blocks into a single concise "Right" example per case, since the surrounding rules already state the target.

Consider moving the full comment-format examples into references/ if the skill grows, keeping only the status-prefix rule and one example inline.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and dense with actionable legal guidance, but it carries motivational prose ("AI-drafted briefs invent cases, misstate holdings…") and verbose "Too long / Right" comparison blocks that could be tightened without losing clarity.	2 / 3
Actionability	Provides exact tool calls (analyzeOpinion, analyzeDocketReport, analyzeDocketFiling, findInOpinion) and a copy-paste-ready code example using D.review(), B.p, R.comment, R.del, R.ins, and B.write with its real signature — fully executable, not pseudocode.	3 / 3
Workflow Clarity	Clear numbered sequence (Intake → five checks → build .docx → report) with explicit validation checkpoints ("Never assert a cite is good until a tool confirms it this session") and exhaustive accounting for this batch operation, avoiding the missing-validation cap.	3 / 3
Progressive Disclosure	Keeps the core workflow inline while clearly signaling one-level-deep references to real files (references/citations.md and references/legal-docx.md), with the rendering detail correctly split out rather than reproduced in the body.	3 / 3
	Total	11 / 12 Passed

Description

82%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, well-scoped description with strong natural trigger terms and a distinct legal niche. Its only gap is the absence of an explicit "Use when…" trigger clause, which caps completeness.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to cite-check a brief, motion, or memo or to verify that cited cases are real, good law, and accurately quoted."

Keep the existing concrete action list but pair it with the trigger phrasing users actually say ("check my citations", "verify the cases in my brief").

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "verifies each cited case is real, supports the proposition, is good law, and quoted accurately" and "Returns one marked-up .docx with comments and redlines" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly states what the skill does, but there is no explicit "Use when…" clause or equivalent trigger guidance naming what the user would mention; per the guidelines a missing explicit trigger caps completeness at 2, not 3.	2 / 3
Trigger Term Quality	Uses natural terms a user would say — "brief, motion, or memo", "PDF/Word", "cite-check", "case" — giving good coverage of common phrasings rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear legal cite-checking niche with distinct triggers (brief/motion/memo, case citations, marked-up .docx), making it unlikely to fire for an unrelated skill.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/midpage/skills/cite-check/SKILL.md
Commit: 11c74d6

Reviewed: about 9 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.