cohort-compare
Skill1.5k starsChanged 2 months agoApache-2.0View on GitHub
Analyze a cohort of patients from FHIR endpoints to find care gaps and patterns. Use when asked to compare patients, find quality gaps, or analyze a population.
Trending
More talk lately.about the whole repository
Who's talking about NVIDIA/dgx-spark-playbooks
- CarstVaartjes/vonk-forge-recipes“Refresh needs review: gemma-4-e4b-it-nvidia-vllm-single”GitHub · Nov 3, 2026
- CarstVaartjes/vonk-forge-recipes“Refresh needs review: gemma-4-e2b-it-nvidia-vllm-single”GitHub · Nov 3, 2026
- laxshmate/genmodelfit“すべての環境で検出できるようにする(41 通りの環境の洗い出し・GB10・WSL2 の AMD/Intel・GPU 名は表でなく文法で)”GitHub · Oct 27, 2026
- CarstVaartjes/vonk-forge-recipes“Refresh qwen3-8b-nvfp4-nvidia-sglang-single to the newest upstream pins”GitHub · Oct 13, 2026
- CarstVaartjes/vonk-forge-recipes“Refresh qwen3-8b-fp8-nvidia-vllm-single to the newest upstream pins”GitHub · Oct 13, 2026
The biggest 5 of 50 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 50
Talked about on GitHub (50 times).
On GitHub · 50
- Nov 3, 2026Refresh needs review: gemma-4-e4b-it-nvidia-vllm-single — CarstVaartjes/vonk-forge-recipes0 reactions · 1 comment
- Nov 3, 2026Refresh needs review: gemma-4-e2b-it-nvidia-vllm-single — CarstVaartjes/vonk-forge-recipes0 reactions · 1 comment
- Oct 27, 2026すべての環境で検出できるようにする(41 通りの環境の洗い出し・GB10・WSL2 の AMD/Intel・GPU 名は表でなく文法で) — laxshmate/genmodelfit0 reactions
- Oct 13, 2026Refresh qwen3-8b-nvfp4-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions · 1 comment
- Oct 13, 2026Refresh qwen3-8b-fp8-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions · 1 comment
45 more on GitHub
- Oct 13, 2026Refresh qwen3-8b-fp8-nvidia-trtllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh qwen3-8b-fp8-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh qwen3-6-35b-a3b-mtp-q4-k-xl-nvidia-llamacpp-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh qwen3-6-35b-a3b-mtp-q4-k-xl-nvidia-llamacpp-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh qwen3-32b-nvfp4-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh qwen3-32b-nvfp4-nvidia-trtllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh qwen3-32b-nvfp4-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh qwen3-30b-a3b-nvfp4-nvidia-trtllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh qwen3-14b-nvfp4-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh qwen3-14b-nvfp4-nvidia-trtllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh qwen3-14b-nvfp4-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh qwen3-14b-fp8-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh qwen3-14b-fp8-nvidia-trtllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh qwen3-14b-fp8-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh qwen2-5-vl-7b-instruct-nvfp4-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh phi-4-reasoning-plus-nvfp4-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh phi-4-reasoning-plus-nvfp4-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh phi-4-reasoning-plus-fp8-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh phi-4-reasoning-plus-fp8-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh phi-4-multimodal-instruct-nvfp4-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh phi-4-multimodal-instruct-nvfp4-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh phi-4-multimodal-instruct-fp8-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions · 1 comment
- Oct 13, 2026Refresh phi-4-multimodal-instruct-fp8-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh nemotron-3-nano-omni-30b-a3b-bf16-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh nemotron-3-nano-30b-a3b-fp8-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh nemotron-3-nano-30b-a3b-bf16-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh llama-3-3-70b-instruct-nvfp4-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh llama-3-3-70b-instruct-nvfp4-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh llama-3-3-70b-instruct-nvfp4-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh llama-3-1-8b-instruct-nvfp4-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh llama-3-1-8b-instruct-nvfp4-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh llama-3-1-8b-instruct-fp8-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh llama-3-1-8b-instruct-fp8-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh llama-3-1-8b-instruct-fp8-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh llama-3-1-405b-instruct-awq-int4-nvidia-vllm-dual to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 13, 2026Refresh gpt-oss-20b-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 12, 2026Refresh gpt-oss-20b-nvidia-trtllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 12, 2026Refresh gpt-oss-20b-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 12, 2026Refresh gpt-oss-120b-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 12, 2026Refresh gpt-oss-120b-nvidia-trtllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 12, 2026Refresh gpt-oss-120b-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 12, 2026Refresh gpt-oss-120b-nvidia-trtllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 12, 2026Refresh gpt-oss-120b-nvidia-sglang-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 12, 2026Refresh gpt-oss-120b-eagle3-nvidia-trtllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
- Oct 12, 2026Refresh gemma-4-e4b-it-nvidia-vllm-single to the newest upstream pins — CarstVaartjes/vonk-forge-recipes0 reactions
In this repository29 other files it gives its agents.
- nvidia/playbook-dgx-station-ai-skills/assets/AGENTS.mdAGENTS.md
- nvidia/station-ai-skills/assets/AGENTS.mdAGENTS.md
- nvidia/station-txt2kg/assets/.cursor/rules/nextjs.mdcCursor rule
- nvidia/txt2kg/assets/.cursor/rules/nextjs.mdcCursor rule
- dgx-station-diagnoseSkill
- dgx-station-inferenceSkill
- dgx-station-migSkill
- dgx-stationSkill
- analysis-methodsSkill
- case-summarySkill
- clinical-delegationSkill
- clinical-knowledgeSkill
- cohort-compareSkill
- fhir-basicsSkill
- molecular-vizSkill
- dgx-diagnoseSkill
- dgx-station-diagnoseSkill
- dgx-station-inferenceSkill
- dgx-station-migSkill
- dgx-stationSkill
- mig-configureSkill
- sglang-setupSkill
- vllm-setupSkill
- analysis-methodsSkill
- case-summarySkill
- clinical-delegationSkill
- clinical-knowledgeSkill
- fhir-basicsSkill
- molecular-vizSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 6 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Use your fhir-basics skill to query FHIR endpoints.
- Distinctive: line 16
Do NOT explore the workspace or list files.
- Distinctive: line 17
Write ONE Python script that does everything: FHIR queries, analysis, chart, and summary.
- Distinctive: line 18
Write the script correctly the first time.
- Very specific: line 19
Run it with python (NOT python3).
- Very specific: line 20
All HTTP calls must use subprocess.run(["curl", "-sf", "--max-time", "30", url], capture_output=True, text=True) -- the requests library …
- Very specific: line 29
Medications: Use get_all_medications_batch(patient_ids) to fetch GET /MedicationRequest?status=active&_count=500 in one call, then filter …
- Distinctive: line 42
If > 30% missing, flag as a data quality issue but continue analysis
- Distinctive: line 43
If < 5 patients have data, warn that the sample is too small for meaningful statistics
- Very specific: line 52
Use NVIDIA dark theme: plt.style.use('dark_background'), primary color #76B900, background #1a1a1a
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Analyze a patient cohort: $ARGUMENTS
Use your fhir-basics skill to query FHIR endpoints. Use your clinical-knowledge skill to identify care gaps and apply correct thresholds. Use your analysis-methods skill to write correct Python analysis code.
Execution Rules
- Do NOT explore the workspace or list files. Begin the analysis immediately.
- Write ONE Python script that does everything: FHIR queries, analysis, chart, and summary.
- Write the script correctly the first time. Do NOT write a draft and then edit it.
- Run it with
python(NOTpython3). - All HTTP calls must use
subprocess.run(["curl", "-sf", "--max-time", "30", url], capture_output=True, text=True)-- therequestslibrary does NOT work through the sandbox proxy. See the fhir-basics skill for thefhir_gethelper pattern. - Save the script to
/tmp/<name>.py, run it once, interpret the output.
Steps
- Identify the cohort -- Query
GET /Condition?code={snomed_code}&_count=200and follow pagination links to get all matching Condition resources. Extract unique patient IDs fromentry[].resource.subject.reference. Report the cohort size. - Pull clinical data in BATCHED queries (do NOT loop per-patient):
- Lab values: Use
get_latest_labs_batch(loinc_code, patient_ids)to fetch ALL observations for the LOINC code in one call and filter client-side. This queriesGET /Observation?code={loinc_code}&_count=500&_sort=-datewithout a patient filter, then builds a dict keyed by patient ID. Handle bothvalueQuantity(numeric) andvalueString(text) formats. For blood pressure, query the BP panel code85354-9in batch and parse components. - Medications: Use
get_all_medications_batch(patient_ids)to fetchGET /MedicationRequest?status=active&_count=500in one call, then filter to cohort patients client-side. - NEVER write a
for pid in patient_ids:loop that makes FHIR HTTP calls inside the loop. The sandbox proxy adds 1-3s latency per call. With 24 patients x 4 LOINC codes = 96 calls = 5+ minutes. Batching brings this to 4-6 total calls = 30 seconds.
- Lab values: Use
- Build a pandas DataFrame with one row per patient:
patient_id(string){lab_name}(float or None)lab_date(string)on_target_med(boolean -- True if the patient is on the specified medication class)medications(comma-separated string of all active med names)med_count(int)
- Data quality check:
- Report how many patients have the lab recorded vs. missing
- If > 30% missing, flag as a data quality issue but continue analysis
- If < 5 patients have data, warn that the sample is too small for meaningful statistics
- Identify care gap patients: Apply the threshold and medication check:
- Gap = lab value exceeds threshold AND patient is NOT on the specified medication class
- Report: total with condition, total with lab data, total above threshold, total in care gap
- Compute gap rate as percentage of patients with lab data (not total cohort)
- Generate visualization:
- Histogram of the lab value distribution with threshold line
- Use NVIDIA dark theme:
plt.style.use('dark_background'), primary color#76B900, background#1a1a1a - Annotate with sample size (N = ...) and gap count
- Save as PNG with
dpi=150
- Write a plain-English summary including:
- Cohort size and data completeness
- Distribution statistics (mean, median, range)
- Gap patient count and percentage with absolute numbers
- Comparison to relevant CMS quality measure if applicable
- Any notable patterns (e.g., "All gap patients had no medications recorded at all")
- Disclaimer: "This analysis is for research and operational purposes. Clinical decisions should be made by qualified clinicians."
Example: Diabetes Gap Analysis (CMS122)
Condition: Type 2 Diabetes (SNOMED 44054006) Lab: HbA1c (LOINC 4548-4) Threshold: > 9.0% Gap medication: insulin or GLP-1 agonist Quality measure: CMS122v12 (poor glycemic control)
INSULIN_AND_GLP1 = ["insulin", "liraglutide", "semaglutide", "dulaglutide",
"exenatide", "tirzepatide", "victoza", "ozempic",
"trulicity", "byetta", "mounjaro", "rybelsus"]
def is_on_insulin_or_glp1(med_list):
med_lower = [m.lower() for m in med_list]
return any(drug in med_text for drug in INSULIN_AND_GLP1 for med_text in med_lower)Example: Hypertension Gap Analysis (CMS165)
Condition: Essential Hypertension (SNOMED 38341003) Lab: Systolic BP (LOINC 8480-6) -- use component Observation pattern Threshold: >= 140 mmHg Gap medication: any antihypertensive Quality measure: CMS165v12 (controlling high blood pressure)
Note: Use get_latest_bp() from the analysis-methods skill to handle both BP panel (85354-9) and standalone systolic Observations.
ANTIHYPERTENSIVES = ["lisinopril", "enalapril", "ramipril", "benazepril",
"losartan", "valsartan", "irbesartan", "olmesartan", "telmisartan",
"amlodipine", "nifedipine", "diltiazem",
"metoprolol", "atenolol", "carvedilol", "bisoprolol",
"hydrochlorothiazide", "hctz", "chlorthalidone",
"furosemide", "spironolactone"]
def is_on_antihypertensive(med_list):
med_lower = [m.lower() for m in med_list]
return any(drug in med_text for drug in ANTIHYPERTENSIVES for med_text in med_lower)Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

