Menü
Submit and manage tracked remote E2B sandboxes on Bohrium platform.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | e2b |
| description | Submit and manage tracked remote E2B sandboxes on Bohrium platform. |
| metadata | {"tools":["submit_e2b_sandbox","get_e2b_job_status","pause_e2b_sandbox","terminate_e2b_sandbox"],"tags":["e2b","remote-job","sandbox","bohrium"]} |
Use the E2B tools for remote sandbox work. They persist the sandbox ID against the current session and graph node, enabling the FastAPI frontend to monitor and control the sandbox even after the agent or browser reconnects.
template explicitly for every submit_e2b_sandbox call. When the
template name is unknown, run lbg sdbx template ls -q to list available
templates. Install the command with pip install -U --pre lbg when needed.submit_e2b_sandbox once for the current step. It is idempotent for
the current session, node, and template.upload_e2b_input for workspace files, then use run_e2b_command for
the sandbox command. Both require the returned job_id.job_id in the step result and use it for status and
sandbox control.terminate_e2b_sandbox to RELEASE the sandbox when work is complete.get_e2b_job_status reads the persisted provider snapshot.pause_e2b_sandbox preserves the sandbox and pauses remote execution.terminate_e2b_sandbox releases the sandbox.The frontend can issue the same controls. Before continuing dependent work after
a pause or termination, return a needs_replanning step result with the job ID
and the observed state.
Generate VASP inputs (INCAR/POSCAR/POTCAR/KPOINTS) via pymatgen.io.vasp.sets for DFT calculations: MPRelaxSet (geometry relaxation), MPStaticSet (SCF), MPNonSCFSet (band structure), MatPESStaticSet (MLFF energy/force labeling). INCAR is driven by pymatgen defaults; the agent only supplies user_incar_settings overrides. Use when the user asks to prepare VASP calculations, run DFT, or generate MLFF training data from structures. Do NOT use for VASP result post-processing / analysis, non-VASP DFT codes, or molecular dynamics — this skill only generates input files and submits jobs.
Deep potential models finetuning and testing using the DeePMD-kit. Use this skill whenever finetuning a Deep Potential (DPA-1 / DPA-2 / DPA-3 / DPA-4) model or running model tests on a dataset. The oldest DP descriptors such as se_e2_a, se_e2_r, and se_e3 are no longer supported. Training from scratch is NEVER advised unless distilling a student model from a teacher model. Multitask fine-tuning is NOT supported.
Skill for running ASE calculations, including energy/force/stress evaluation, molecular dynamics (MD) and structure optimization. Now only use machine-learned force fields (MLFFs) as calculators.
Concept skill for Machine Learning Force Fields (MLFFs). Describes what MLFFs are, the distinction between fine-tuning and distillation, and which tool skills to use. Load this before selecting a specific MLFF framework (DeePMD, MatterSim, etc.).
Concept skill for Molecular Dynamics (MD) simulation. Describes MD ensembles, key parameters, and which tool skills to invoke for MD runs. Use this to understand MD concepts before selecting a specific simulation tool.
Equation-of-State (EOS) benchmark skill — compare DFT, pretrained, and finetuned model E(V) curves to evaluate force-field quality for bulk crystals and simple systems.