skills/job-results/SKILL.md
Read and parse results from completed SLURM jobs — check status, retrieve output, filter candidates
npx skillsauth add lamm-mit/scienceclaw job-resultsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Read results from completed SLURM jobs. Checks job status via sacct, reads output files (stdout JSON), and can filter results by criteria (e.g., thermodynamic stability, convergence).
This skill bridges the gap between job submission and subsequent analysis steps. When a screening job completes, use this skill to retrieve results and identify candidates for the next pipeline stage.
read_job_results.py — Retrieve and parse job outputCheck status and read results:
python3 {baseDir}/scripts/read_job_results.py \
--job-id 27018190 \
--output-dir ./uma_screen_output \
--format json
Filter thermodynamically stable candidates:
python3 {baseDir}/scripts/read_job_results.py \
--output-dir ./uma_screen_output \
--filter-stable \
--format json
Read the latest results from a directory:
python3 {baseDir}/scripts/read_job_results.py \
--output-dir ./uma_screen_output \
--format json
| Parameter | Description |
|-----------|-------------|
| --job-id | SLURM job ID to check status for |
| --output-dir | Directory containing SLURM output files (slurm-*.out) |
| --results-file | Direct path to a JSON results file |
| --filter-stable | Only return candidates with formation_energy < 0 or e_above_hull < 0.1 |
| --filter-converged | Only return converged calculations |
| --list-cifs | List relaxed CIF file paths for stable candidates |
| --format | summary | json |
{
"status": "COMPLETED",
"job_id": "27018190",
"results": { ... },
"stable_candidates": [
{
"label": "YH10_from_LaH10",
"formula": "YH10",
"formation_energy_eV_per_atom": -0.18,
"e_above_hull_eV": 0.0,
"relaxed_cif": "/path/to/YH10_0GPa.cif"
}
],
"stable_cif_paths": ["/path/to/YH10_0GPa.cif", ...]
}
tools
Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration
development
Perform AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter. This skill should be used when conducting web searches for current information, finding recent scientific literature, getting grounded answers with source citations, or accessing information beyond the model knowledge cutoff. Provides access to multiple Perplexity models including Sonar Pro, Sonar Pro Search (advanced agentic search), and Sonar Reasoning Pro through a single OpenRouter API key.
testing
Generate a structured scientific PDF report from a JSON description. Accepts a JSON file specifying title, authors, abstract, sections (headings, text, tables, figures), and inline data panels (heatmap, bar, scatter, line). Produces a publication-style A4 PDF using reportlab with no LaTeX dependency. All figures are either loaded from PNG paths or generated on-the-fly from inline data.
development
Execute arbitrary Python code and return stdout. NumPy, pandas, scipy, matplotlib, and other scientific libraries are available.