AF medical-record-structuring
EN: Convert unstructured Chinese clinical narratives (admission notes, progress notes, discharge summaries, outpatient records) into structured JSON aligned with HL7 FHIR R4 and Chinese national EMR standards (WS 445-2014, ICD-10, ICD-9-CM-3). Use when the user provides medical text and asks to "结构化 / 抽取 / 解析病历 / 转 FHIR / extract diagnoses / parse EMR". 中文：将非结构化中文临床文本（入院记录、病程记录、出院小结、门诊病历）转换为符合 HL7 FHIR R4 与国家电子病历共享文档规范（WS 445-2014、ICD-10、ICD-9-CM-3）的结构化 JSON。当用户提供病历文本并要求"结构化/抽取实体/解析病历/转FHIR"时触发。
EN: Convert unstructured Chinese clinical narratives (admission notes, progress notes, discharge summaries, outpatient records) into structured JSON aligned…
As a process F 51/100 · Will not run — References files that are not bundled: templates/extraction_prompt.md
How to improve
- The text references files that are not there: add them or drop the references.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: templates/extraction_prompt.md
Process rating: all ten parameters 51/100
- 0Tools and files. 1 referenced file(s) missing: templates/extraction_prompt.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 44 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1671 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 500: enough signal without eating the budget
- +4Structure: 19 headings
- +3Step-by-step instructions: 44 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
- +3All 6 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.