CtrlK
BlogDocsLog inGet started
Tessl Logo

exporting-bulk-fhir

Kick off and harvest a FHIR Bulk Data $export (system-, group-, or patient-level) and stream the resulting NDJSON into a batch OpenMed de-identification + NER pipeline at cohort scale. Covers the async kickoff (Prefer respond-async) -> poll Content-Location -> download NDJSON flow, the Bulk Data Access IG, _type/_since filters, and feeding DocumentReference/DiagnosticReport notes into openmed.deidentify in batch. Use when the user needs population-scale note extraction from an EHR or data warehouse to feed OpenMed, mentions bulk export, $export, NDJSON, Flat FHIR, or cohort de-identification. Pairs before the OpenMed de-id/NER pipeline.

69

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

67%Weight 40%Scale 1-5

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

The body is concrete and highly actionable with copy-paste-ready curl and Python covering the full export→de-id→NER pipeline, and a clear sequenced workflow with verification guidance. It is slightly redundant across sections and embeds its de-id validation in gotchas rather than as an inline workflow checkpoint.

Suggestions

De-duplicate the de-id-before-persistence and DELETE-the-job guidance so each appears once in the Workflow section, removing the repeats from Hand-off and Edge cases.

Embed an explicit numbered validation checkpoint in the Workflow (e.g., step 5.5: verify de-id with openmed.eval leakage gates before persisting) so the batch verification is part of the sequence rather than only in Edge cases.

Tighten the intro paragraph and 'Hand-off to / from OpenMed' section, which restate points already covered in Workflow and Quick start.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes Claude's competence (no explain-FHIR/PDF padding), with minor redundancy — de-id-before-persistence and DELETE-the-job are restated across Quick start, Workflow, Hand-off, and Edge cases.

4 / 5

Actionability

Fully executable curl kickoff→poll→download sequence with real headers/manifest and runnable Python streaming into openmed.deidentify/analyze_text, with specific commands and params covering common cases.

5 / 5

Workflow Clarity

Clear 7-step sequence with an explicit poll-until-200 checkpoint and a present verification step (openmed.eval leakage gates), but the de-id verification lives in Edge cases rather than as an inline validate→retry checkpoint in the numbered batch workflow.

4 / 5

Progressive Disclosure

Well-organized single-file skill with clear section headers and appropriate external spec links (one level deep); no bundle files exist, and content is reasonably placed inline, but it is a self-contained design rather than an overview-into-bundles structure.

4 / 5

Total

17

/

20

Passed

Description

100%Weight 40%Scale 1-5

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

The description is precise, action-oriented, and third-person, clearly stating both capabilities and explicit trigger conditions with natural user phrasing. It carves a distinct niche and avoids fluff, though some overlap with generic FHIR skills exists around 'Flat FHIR'/'NDJSON'.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (kickoff, poll Content-Location, download NDJSON, stream, de-identify, NER) with specifics like resource types, Prefer header, and _type/_since filters — comprehensive coverage matching the anchor-5 example.

5 / 5

Completeness

Explicitly answers both what ("Kick off and harvest a FHIR Bulk Data $export... stream the resulting NDJSON...") and when ("Use when the user needs population-scale note extraction...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger terms a user would say ("bulk export", "$export", "NDJSON", "Flat FHIR", "cohort de-identification", "population-scale note extraction") with synonyms, matching the comprehensive anchor-5 example.

5 / 5

Distinctiveness Conflict Risk

Clear niche (cohort-scale FHIR Bulk Data export feeding OpenMed) with distinct triggers ($export, NDJSON, Flat FHIR) and explicit population-scale framing that separates it from single-patient UI skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
maziyarpanahi/openmed
Reviewed

Table of Contents

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.