# Result Report Generator

Summarize modeling experiment evidence, compare the approved main method with a usable...

- Repository: https://github.com/zhnnky329/MathModeling-skills (1073 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-09-24
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add zhnnky329/MathModeling-skills --skill result-report-generator -g -a claude-code -y`
Codex: `npx skills add zhnnky329/MathModeling-skills --skill result-report-generator -g -a codex -y`
Cursor: `npx skills add zhnnky329/MathModeling-skills --skill result-report-generator -g -a cursor -y`
Gemini CLI: `npx skills add zhnnky329/MathModeling-skills --skill result-report-generator -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add zhnnky329/MathModeling-skills`

## Description

Summarize modeling experiment evidence, compare the approved main method with a usable baseline, surface fallback triggers, and produce a decision-point or final report without creating routine per-round prose.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Purpose

Turn saved experiment artifacts into compact evidence. Do not treat ordinary successful runs as requiring a long report, and do not choose the winning method.

# Inputs

- `run_summary.json`
- method card and probe summary
- decision ledger
- saved tables, metrics, and figures
- session `rigor_profile`

Stop if the run summary claims outputs that do not exist or if main and baseline are not comparable.

# Modes

## Ordinary lean round

- Validate the run summary and referenced artifacts.
- Return a compact evidence digest in the conversation.
- Do not save a Markdown report unless:
  - a fallback trigger fired;
  - a material anomaly or contradiction exists;
  - the human must make a proceed/adjust/fallback decision.

## Decision-point round

Save:

`results/Qx/experiments/roundN/qx_decision_report.md`

Include only:

- main vs baseline metrics;
- output-degeneracy/concentration evidence;
- assumption or feasibility warnings;
- robustness evidence already available;
- fallback trigger state;
- unresolved trade-offs.

Then invoke `decision-prompt-builder`. After the human answers, route the answer to `modeler-decision-logger`.

## Final/submission mode

Save:

`results/Qx/reports/qx_final_result_analysis.md`

Include:

- final main/baseline comparison;
- uncertainty and error;
- concentration/degeneracy interpretation;
- robustness links;
- limitations and applicable scope;
- exact source paths for numerical claims.

# Rejection and Fallback

- Archive a method only after a human `result_verdict` or `fallback_activation` decision.
- Move rejected code and outputs to `workspace/archived/<Qx>/<method>_REJECTED_roundN/`.
- Add one compact history line to `qx_method_card.md`; do not create a separate iteration log.
- Do not archive from an AI suggestion alone.

# Rules

The rest: https://github.com/zhnnky329/MathModeling-skills/blob/HEAD/.claude/skills/result-report-generator/SKILL.md