Menu
This skill should be used when an execution fails, an error occurs, a command times out, or the user asks to diagnose what went wrong with a computational math experiment.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Route AI4Math computational mathematics tasks to the appropriate bundled skill package.
Use when reproducing, deploying, diagnosing, tuning, visualizing, or reporting computational math research code with a coding agent
This skill should be used when the user asks to search for external algorithms, find related implementations, discover alternative approaches, or look up papers and code for computational math optimization methods.
This skill should be used when the user asks to tune parameters, run hyperparameter search, optimize algorithm settings, or find the best configuration for a computational math method.
Use when classifying a computational math repository or task into a broad domain before choosing specialist Skills, references, runtimes, and validation evidence.
Use when a user starts an end-to-end computational math research-code reproduction, deployment, tuning, visualization, or reporting workflow with a coding agent.
| name | failure-diagnosis-skill |
| description | This skill should be used when an execution fails, an error occurs, a command times out, or the user asks to diagnose what went wrong with a computational math experiment. |
Classifies execution failures and generates fix proposals conversationally.
For end-to-end computational math research-code reproduction workflows, this Skill should be selected by computational_math_reproduction_workflow_skill rather than used as the first entrypoint.
Input: --stderr <text>, --stdout <text>, --out <path>
Output: classified failure type (printed to stdout), repair_plan.md only if source/dependency/entrypoint/data changes needed
Classified failure types: dependency_error, version_conflict, missing_data, missing_entrypoint, timeout, numerical_failure, permission_error, high_risk_command, readme_unclear, unknown_error
python -m skills.failure_diagnosis_skill.scripts.failure_classifier --stderr "ModuleNotFoundError" --out /path/to/output
failure_classifier with stderr/stdout.repair_plan.md with a concise reference to logs/run.log — do not copy the full traceback.logs/run.log.logs/run.log, no failure_analysis.md.repair_plan.md when source/dependency/entrypoint/data changes are needed.repair_plan.md must be short — reference logs/run.log, don't copy the full traceback.