review
Independently review mathematical-modeling candidates, experiments, comparisons, or fusions from fixed selected material.
Skill by SoFarSoGoodya
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sofarsogoodya-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/review
What's inside
- Skill name
review- Description
- Independently review mathematical-modeling candidates, experiments, comparisons, or fusions from fixed selected material.
- License
- MIT
- Instructions
- 9 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Review Start in a fresh context with only fixed candidate/comparison/experiment material needed for the review. Do not inherit author chat history or an asserted recommendation. Review mathematical validity separately from fair programmatic comparison. Mathematical review checks assumptions, derivations, units, identifiability, constraint handling, uncertainty, and conclusion scope. Programmatic comparison checks fixed data/splits, metric units and recomputation, baseline relevance, budget equality, leakage, coverage, failures, and denominators. State evidence and unresolved issues precisely. A finite experiment is not an asymptotic proof; a successful process is not scientific validity; parent validity does not transfer to a fusion. Recommend a new bounded experiment or a human decision only when it could alter the conclusion.
From SoFarSoGoodya/mathmodel-weave, MIT.
More from SoFarSoGoodya/mathmodel-weave
- 0.598score
publication
SoFarSoGoodya
Build and review a Chinese XeLaTeX mathematical-modeling paper from a fixed selected result, evidence freeze, and formal execution manifest.
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
execution
SoFarSoGoodya
Run a local mathematical experiment through the MathModel runtime and package traceable observations, metrics, checks, and figures.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
coordinator
SoFarSoGoodya
Coordinate a bounded mathematical-modeling case through runtime RESULT.json handoffs and human decisions.
SkillAFreshness: A★ 2Claude Code +9 - 0.554score
evidence
SoFarSoGoodya
Intake modeling problem files and curate research evidence with faithful source text, targeted verification, pins, and freezes.
SkillBFreshness: B★ 2Claude Code +9 - 0.546score
exploration
SoFarSoGoodya
Develop independently reasoned mathematical-modeling candidates and fixed comparison material for an approved case.
SkillBFreshness: B★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 13, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/SoFarSoGoodya/mathmodel-weave
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from SoFarSoGoodya
- 0.598score
publication
SoFarSoGoodya
Build and review a Chinese XeLaTeX mathematical-modeling paper from a fixed selected result, evidence freeze, and formal execution manifest.
SkillAFreshness: A★ 2Claude Code +9 - 0.595score
execution
SoFarSoGoodya
Run a local mathematical experiment through the MathModel runtime and package traceable observations, metrics, checks, and figures.
SkillAFreshness: A★ 2Claude Code +9 - 0.587score
coordinator
SoFarSoGoodya
Coordinate a bounded mathematical-modeling case through runtime RESULT.json handoffs and human decisions.
SkillAFreshness: A★ 2Claude Code +9 - 0.554score
evidence
SoFarSoGoodya
Intake modeling problem files and curate research evidence with faithful source text, targeted verification, pins, and freezes.
SkillBFreshness: B★ 2Claude Code +9 - 0.546score
exploration
SoFarSoGoodya
Develop independently reasoned mathematical-modeling candidates and fixed comparison material for an approved case.
SkillBFreshness: B★ 2Claude Code +9
Cite this page
review skill. Agent Mart. https://agentmart.dev/skills/sofarsogoodya-review (last updated 2026-10-24)