Menu
Add a new E2E test case to tests/e2e/prompts.yaml for LangSmith evaluation. Use when adding interaction pairs to test, covering new ANSM drug classes, or rebalancing eval coverage.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Run the LangSmith evaluation suite and display pass/fail results
Add a new LangChain tool to the Medox ReAct agent. Use when creating a new tool file, registering it in the graph, and writing its test.
Create a git commit with Medox conventions (co-author, conventional type/scope). Invoke manually with /commit — do NOT trigger automatically.
Audit code changes on the current branch and update docs/ + .claude/rules/ to stay in sync. Run before /pr.
Create or update a GitHub pull request following Medox conventions (author spicode-bot, reviewer spideystreet). Invoke manually with /pr — do NOT trigger automatically.
Fetch and display the full status of the current PR — CI checks, GitHub Actions runs, reviews, and code comments — using GitHub MCP tools. Invoke manually with /pr-status.
| name | add-eval-case |
| description | Add a new E2E test case to tests/e2e/prompts.yaml for LangSmith evaluation. Use when adding interaction pairs to test, covering new ANSM drug classes, or rebalancing eval coverage. |
| argument-hint | <substance-a> <substance-b> |
Identify the interaction pair — substance A + substance B, with ANSM level:
Contre-indication (CI) or Association déconseillée (AD) → expect_warn: truePrécaution d'emploi (PE) or À prendre en compte (APEC) → expect_warn: falseWrite a realistic clinical scenario (in French, pharmacist/physician perspective):
Add the case to tests/e2e/prompts.yaml:
# <ANSM level>: <mechanism> — DB pair: <SUBSTANCE_A> + <SUBSTANCE_B> (<CI|AD|PE|APEC>)
- id: <substance_a>_<substance_b>
prompt: >
<Clinical scenario in French.>
expect_warn: true # or false
expect_in:
- "⚠️" # only if expect_warn: true
- "<substance name as it appears in French DCI>"
expect_not:
- "<unrelated substance that should not appear>"
Choose expect_not carefully — must be a substance meaningfully different,
not a trivial variation. Used as false-positive guard.
Run the eval to validate the new case passes:
uv run dotenv -f .env run -- python scripts/run_eval.py
Maintain balance across:
expect_warn: true cases (CI + AD) — currently: ibuprofene_methotrexate, ciclosporine_simvastatineexpect_warn: false cases (PE + true negatives) — currently: amiodarone_simvastatine, paracetamol_amoxicilline, generiques_dolipraneid format: <substance_a>_<substance_b> in lowercase, underscores, no accentsexpect_in terms must match what the agent actually outputs (test with a manual run first)