메뉴
Drive the contracts engine's runtime surface (the stdio MCP server) to verify changes end-to-end. Scoped to public-plugins/plugins/healthcare/skills/contracts/ and ../../servers/documents/.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Answer a question across a corpus of contract documents with verified citations. Use when the user asks what a contract says, which contracts have a clause, what changed between amendments, or any question that needs reading and citing across a set of contract files. The corpus must be on the local filesystem (see README).
Extract plain text from a document file - PDF, DOCX, XLSX, PPTX, RTF, or plain text/markdown/HTML. Use when a binary document needs to be turned into text, for example a contract PDF or an EHR DocumentReference attachment. Other skills (fhir) invoke scripts/extract.ts directly; the contracts MCP server bundles its own copy (servers/documents/src/extract.ts) so its bundle stays self-contained — port fixes to both.
Connect to a hospital's FHIR R4 server (Epic, Oracle Health/Cerner, MEDITECH, athenahealth, or any SMART-on-FHIR endpoint), pull a patient's clinical data and notes, and extract structured findings. Use when users say "connect to the EHR", "connect to Epic/Cerner", "pull notes for patient X", "what do the last 6 months of notes say about Y", or any task that starts from a live EHR rather than pasted text.
Assign CPT and HCPCS Level II procedure codes from clinical documentation the way a professional coder builds the claim. Use when users say "code this encounter for procedures", "what CPT codes apply", "assign HCPCS codes", "code this op note", or when turning visit notes or operative reports into claim-ready procedure codes.
Extract structured data from clinical notes with span-level provenance and null-safety. Use when users say "extract [variables] from this note", "abstract this chart", "pull structured data from these notes", "what does this note say about [field]", or when building a chart-abstraction, registry, or cohort dataset from unstructured clinical text.
Screen a Medicare/Medicaid claims corpus for fraud, waste, and abuse and produce ranked, fully-cited investigation referrals for an SIU / program-integrity team. Use when asked to run a fraud sweep, screen claims for FWA, find billing anomalies, or generate investigation referrals over a claims dataset.
| name | verify |
| description | Drive the contracts engine's runtime surface (the stdio MCP server) to verify changes end-to-end. Scoped to public-plugins/plugins/healthcare/skills/contracts/ and ../../servers/documents/. |
The engine is the MCP server at ../../servers/documents/src/index.mjs — plain runnable .mjs, no build step; the source IS the shipped artifact. Most changes are drivable without a full /contracts session by speaking JSON-RPC to the server over stdio.
cd ../../servers/documents && bun run check (tsc over the .mjs via checkJs). There is no bundle; edits to src are live immediately.~/.claude/data/healthcare/documents/data.sqlite (shared across checkouts; safe to delete — schema v-check tells users to do the same). For throwaway runs point CLAUDE_HEALTHCARE_DATA at a scratch PARENT dir (the server appends documents/) — never drive tests against the live db. Corpus names live in corpus_documents.corpus; query before assuming.node ../../servers/documents/src/index.mjs <tool> '<json-args>' runs one tool call without MCP — result JSON on stdout, exit 1 + stderr on error. Bare invocation is MCP stdio.& under /bin/bash (zsh backgrounding under the CC sandbox emits bogus nice(5) failures), fresh AND warm db, ≥60 trials each. Desktop-side repro evidence: ~/Library/Logs/Claude/main.log, grep LocalMcpServerManager.z.tuple([...]) (array-form items → use z.array().length(n)) and z.union([...])/.nullish() on primitives (type: [...] → use .optional() or one type). servers/documents/test/schema.test.ts guards this; run bun test after touching any tool's inputSchema, and spawn a real agent (claude --plugin-dir <plugin> -p "spawn subagent_type 'healthcare:contracts-reader' …" --allowedTools Agent) after changing agent tool lists.initialize → notifications/initialized → tools/list / tools/call lines into node ../../servers/documents/src/index.mjs and read the JSON-RPC replies. A sequential client (write line, read reply) avoids out-of-order confusion. Core chain worth driving after engine changes: corpus_register (temp dir with a .txt) → ingest → write runs/briefs → find with a verbatim quote (expect kind:"exact") AND a bogus quote (expect the cite error) → export_report.getMaxToolUseConcurrency), deliberately NOT a Workflow — a workflow caps agents at min(16, cores−2), which is 2 on a cloud container and serializes the sweep. To check parallelism after a real run: sql "SELECT worker, min(created_at), max(created_at) FROM findings WHERE run_id='<id>' GROUP BY worker" — the windows should overlap, not chain end-to-start.tools/list, step file paths exist) and, for protocol changes, drive at least the mechanical tool calls the prose mandates exactly as written.