xtbloom-run-python-inference SKILL.md skillA
xtbloom-run-python-inference from jinzhezenggroup/computational-chemistry-agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jinzhezenggroup/computational-chemistry-agent-skills/xtbloom-run-python-inference@git:20260810.6a7d139Pins git:20260810.6a7d139 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jinzhezenggroup/computational-chemistry-agent-skills
- Path
quantum-chemistry/xtbloom-run-python-inference/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260810.6a7d139, committed Aug 10, 2026
- First version recorded
- Aug 10, 2026
- Size
- 5,214 bytes
- Repository stars
- 156
- License
- LGPL-3.0
Write, review, and run high-level xTBloom Python GFN2-xTB inference with `Calculator`, `Structure`, and `BatchCalculator`, including single systems, repeated geometry updates, heterogeneous ragged batches, backend selection, units, finite-temperature meaning, and peer-local failure handling. Use for ordinary NumPy-based energy, force, and charge workflows; use a dedicated integration skill instead for Array API/DLPack/PyTorch zero-copy, ASE/dpdata, the native C API, or QM/MM coupling.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Run xTBloom Python Inference Build a calculation whose units, backend behavior, lifetime, and failure policy are explicit. Read [references/python-inference.md](references/python-inference.md) for the public API contract and complete examples. ## Run Standalone Programs Ephemerally Do not require xTBloom to be preinstalled for an agent-generated standalone program. Add PEP 723 metadata at the top, then run it with `uv run --script calculation.py`: ```python # /// script # requires-python = ">=3.10" # dependencies = ["xtbloom>=0.1.1"] # /// ``` Respect an existing application environment when the user asks to modify one; do not replace its dependency policy merely to make the example standalone. ## Select the Interface - Use `Calculator` for one system and for repeated geometry updates on one topology. - Use `Structure` plus `BatchCalculator` for differently sized systems in one native ragged request. - Use context managers so native contexts and persistent backend resources are released deterministically. …
Read the whole file at its exact version.
How to install
mdr add jinzhezenggroup/computational-chemistry-agent-skills/xtbloom-run-python-inference@sha256:62a4dadd6b1d6e89The line at the top of this page pins the label git:20260810.6a7d139, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_uj5h5qme4allfjr3)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, all committed on Aug 10, 2026.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260810.6a7d139 latest | 2026-08-10 | 6a7d139 | 5,214 B | A | view · diff |
| git:20260810.e2c149b | 2026-08-10 | e2c149b | 4,750 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5214 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
jinzhezenggroup/computational-chemistry-agent-skills · 156 stars · license LGPL-3.0 · pushed 2026-11-02 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_uj5h5qme4allfjr3 GET https://markdownregistry.com/api/v1/resolve?ref=jinzhezenggroup/computational-chemistry-agent-skills/xtbloom-run-python-inference GET https://markdownregistry.com/api/v1/blob/62a4dadd6b1d6e89dd3f85d6f9af32ec659a836e643ba11df024910517a687e7
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from jinzhezenggroup/computational-chemistry-agent-skills
Every file in jinzhezenggroup/computational-chemistry-agent-skills