Menu
This skill should be used when the user asks to generate a report, summarize results, write up findings, or create documentation for a computational math reproduction or tuning experiment.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
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 | report-generation-skill |
| description | This skill should be used when the user asks to generate a report, summarize results, write up findings, or create documentation for a computational math reproduction or tuning experiment. |
Generates compact Markdown reports for the Skill-first Codex workflow.
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.
Four compact Markdown report types:
# Reproduction Plan
## Goal
## Selected Source
## Minimal Command To Run
## Expected Outputs
## Risks
## Approval Scope
Reply with approve / revise / reject / skip.
# Repair Plan
## Failure Summary
## Evidence
## Proposed Minimal Repair
## Files To Modify
## What Will Not Be Changed
## Patch / Rollback Plan
Reply with approve / revise / reject / skip.
# Run Summary
## Status
## Source
## Commands Run
## Evidence
## Results
## Figures
## Patches
## Limitations
## Optional Tuning Recommendation
# Tuning Summary
## Status
## Budget
## Search Method
## Best Parameters
## Baseline vs Best
## Evidence
## Limitations
plan.md before execution when a durable plan is useful.RUN_SUMMARY.md with status, evidence, limits, and next options.tuning/TUNING_SUMMARY.md.Input: --run <path> — run directory with execution logs, optional tuning outputs, and figures.
python -m skills.report_generation_skill.scripts.report_writer --run /path/to/output