Document Derive
Drafts the clinical artefacts that follow a signed note - referral letter, after-visit summary, care-plan update - each cited to the note and marked draft. It never sends, faxes or files, and if the note indicates no referral it says so instead of drafting one. Use when the user says "draft the referral letter", "write the after-visit summary", "AVS for this visit", "send the patient home with instructions" or "update the care plan from today's note". Do NOT use for Word/PDF formatting or letterhead on an existing document - use the built-in docx instead; do NOT use for coding evidence - use c
Install
npx skills add microsoft/cat-agent-skills --skill document-derivegit clone --depth 1 https://github.com/microsoft/cat-agent-skills.git /tmp/cat-agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/cat-agent-skills/submissions/clinical-documentation-companion/document-derive ~/.claude/skills/document-derivePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Document Derive
## Purpose
Produce the downstream documents that follow the signed note, as cited drafts for clinician signature.
## When to use
After note-context, for an encounter whose signed note indicates a referral, AVS or care-plan update - triggered by
"draft the referral letter", "write the after-visit summary", "AVS for this visit", "update the care plan". Also
when the request mixes drafting with sending ("draft it and fax it"): draft, and decline the send.
## When NOT to Use
- Formatting, letterhead or Word/PDF production of an existing document - use the built-in docx skill instead.
- Coding evidence - use coding-rationale instead.
- Quality-measure status - use quality-gap-check instead.
- A clinician-to-clinician handoff - use handoff-draft instead.
## Inputs
note_signature (signed must be true); encounter; note_facts with citations from note-context, including
`referral_indicated`, `active_medications`, `patient_instructions` and `follow_up_plan`, each with its
`statements[]` (one cited entry per documented medication, instruction or follow-up statement).
## Steps
1. Confirm `note_signature.signed` is true; if not, write `halt{halted: "unsigned_note"}` and escalate - never
draft from an unsigned note (clinical-doc-rules.md #5).
2. If a note_fact needed for a sentence is missing from the contract - or one of `active_medications`,
`patient_instructions`, `follow_up_plan` or a true `referral_indicated` has `value: true` but no `statements[]` -Details
- Skill name
document-derive- Repository
- microsoft/cat-agent-skills
- Path
submissions/clinical-documentation-companion/document-derive/SKILL.md- License
- MIT
- Repo updated
- 15 November 2026
FAQ
What does the Document Derive skill do?
Drafts the clinical artefacts that follow a signed note - referral letter, after-visit summary, care-plan update - each cited to the note and marked draft. It never sends, faxes or files, and if the note indicates no referral it says so instead of drafting one. Use when the user says "draft the referral letter", "write the after-visit summary", "AVS for this visit", "send the patient home with instructions" or "update the care plan from today's note". Do NOT use for Word/PDF formatting or letterhead on an existing document - use the built-in docx instead; do NOT use for coding evidence - use c
How do I install the Document Derive skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add microsoft/cat-agent-skills --skill document-derive. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Document Derive popular?
It lives in microsoft/cat-agent-skills, which has 110 GitHub stars and 122 forks.
Related skills
3 Statements
110microsoft/cat-agent-skills
Completes existing income statement, balance sheet and cash flow templates while preserving layout, grounding historical inputs and linking forecast formulas with reconciliation checks. Use for "fill in a 3-statement template", "complete an IS/BS/CF framework", "populate my integrated financial model", "link statements in this template", or "finish the forecasts in my three-statement workbook". Do NOT use for blank-slate models or general workbook edits (use xlsx), DCF valuation (use dcf-valuation), or buyout modeling (use lbo-model).
Accessibility Pass
110microsoft/cat-agent-skills
Use this skill whenever the user asks to check, review, or fix the accessibility of a PowerPoint deck, Word document, HTML page, or Markdown file, and before handing over any deck or document this agent just generated, so it does not ship with missing alt text, untitled slides, or unreadable colour contrast.
Accessible Learning Materials
110microsoft/cat-agent-skills
Maintains instructionally equivalent, accessible variants of a set of learning materials — lessons, readings, slides, and handouts — with parity checks against the original learning goals and recorded approvals. Use when the user asks to "make these materials accessible", "audit this lesson set for accessibility", "create an accessible version of this reading", "check reading level and alt text", or "keep my accessible variants in sync". Do NOT use for individual student accommodation or support-plan decisions (IEP, EHCP, or local equivalent), and do NOT use for generic document formatting (us
Enforcement Action Review
110microsoft/cat-agent-skills
Reads a public enforcement action, complaint, settlement, or consent order and produces a read-across against the firm's controls covering alleged conduct, cited rules, and corrective actions. Exposure is framed as hypotheses for human review, never admissions. Use when the user says "could this happen here", "what does this consent order mean for us", "lessons learned from this enforcement action", "read this across to our controls", or "which controls does this implicate". Do NOT use for customer or counterparty research (use kyc-research-pack), new rules, bulletins, SR letters, or proposed
Compare Across Jurisdictions
110microsoft/cat-agent-skills
Produces a cited side-by-side comparison of one legal question across two or more named jurisdictions, using a framework frozen before research, one evidence status per cell (such as Stated or Not located) and one divergence label per row. Neutral comparative research for counsel review — never legal advice, a forum recommendation or an outcome prediction. Use when the user asks to "compare paid leave rules across these states", "how is this point litigated in France versus England", "what does each country say about X", "prepare a per-jurisdiction position table", or "where do these jurisdict
Identify Regulatory Gaps
110microsoft/cat-agent-skills
Identifies gaps against a standard: builds a requirement inventory from retrieved legislation, regulator rules, standards or internal policy text, traces every requirement into every supplied document, and reports each pair in one state with citations on both sides. Use when the user asks to "check this against the new regulations", "run a gap analysis against the rulebook", "does this policy meet the guidance?", "which live deals does this rule change affect?", "check these contracts against our internal policy", or "which of our agreements cite the old article?". Do NOT use for the same fiel
Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.