القائمة
Isolated exploratory code execution with medsci-sandbox tools. Use when analysis requires custom code beyond existing domain MCP tools.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Shared operational contract for all MedSci agents: sequential execution, planning phase, retry limits, evidence standards.
AlphaFold DB for predicted protein structures and pLDDT confidence scores
Molecular biology toolkit. Use for FASTA parsing, sequence analysis, and translation.
ChEMBL database access for bioactivity data and target search
Datamol for molecular manipulation, SMILES processing, and cheminformatics
Molecular ML with DeepChem - featurizers, models, and molecular property prediction
| name | sandbox-execution |
| description | Isolated exploratory code execution with medsci-sandbox tools. Use when analysis requires custom code beyond existing domain MCP tools. |
1. Prepare sandbox → sandbox_prepare(workspace_path, network_policy="deny")
2. Run command → sandbox_run_job(sandbox_name, command, timeout_sec)
3. Check status → sandbox_status(sandbox_name) [optional/advisory]
4. Fetch outputs → sandbox_fetch_artifact(sandbox_name, artifact_path)
5. Teardown → sandbox_teardown(sandbox_name, remove=true|false)
denytimeout_sec on every run jobsandbox_run_job success/failure as source-of-truth for execution outcomesandbox_status is used, apply 1-2s retry/backoff before final state conclusionremove=true)python3 for inline script execution commandsSANDBOX_TIMEOUT: reduce scope or increase timeoutCLI_UNAVAILABLE: verify Docker + Docker Sandbox CLI installedSANDBOX_CREATE_FAILED: check Docker Desktop status and template availabilityARTIFACT_PATH_FORBIDDEN: use safe paths under workspace/artifact roots onlyARTIFACT_NOT_FOUND: verify command produced expected files before fetch