Skip to main content
woodfishhhh
GitHub creator profile

woodfishhhh

Repository-level view of 29 collected skills across 5 GitHub repositories.

skills collected
29
repositories
5
updated
Aug 28, 2026
repository explorer

Repositories and representative skills

ez-math-model
operations-research-analysts-152031

Use when solving CUMCM, MCM, ICM, or other mathematical modeling tasks that need contest problem intake, model selection, Python solving, figures, paper writing, quality audit, and packaged deliverables.

May 22, 2026
docx
word-processors-and-typists

Use when EZ_math_model needs to convert paper.md to paper.docx, read a DOCX problem statement, preserve equations and tables, or package a modeling report as a Word document.

May 22, 2026
humanizer
technical-writers

Use after EZ_math_model writer creates paper.md and before quality audit when a long modeling paper needs less AI-like prose while preserving formulas, data, citations, tables, and figures.

May 22, 2026
paper-orchestra
software-developers

EZMM writer-stage adapter for the vendored PaperOrchestra skill pack. Use by default during pipeline/04-paper-writing for outline-first paper drafting, literature-review planning, section writing, and refinement discipline. The adapter maps EZMM runtime…

May 22, 2026
pdf
office-clerks-general-439061

Use when EZ_math_model needs to read or convert PDF problem statements, extract text or tables from PDF attachments, summarize reference papers, or fall back when MinerU is unavailable.

May 22, 2026
verification-before-completion
software-quality-assurance-analysts-and-testers

Use before EZ_math_model declares quality_audit, packaging, or final delivery complete, especially when pass/fail claims must be backed by files, commands, counts, or concrete evidence.

May 22, 2026
brainstorming
data-scientists-152051

Use when EZ_math_model model selection is unclear after the modeling decision tree, the problem spans multiple domains, or modeler needs several candidate approaches before writing modeling_plan.md.

May 20, 2026
dataset
data-scientists-152051

公开数据集发现入口。覆盖 Kaggle / UCI / HuggingFace / 天池。题目要求"自行 查找数据"或"补充外部数据"时启用;附件已含数据时**不调用**。

May 20, 2026
Showing 8 of 20 collected skills.
room-6657-style
writers-and-authors

Generate, evaluate, or refine original Chinese barrage text for ADVX Live's room-6657 mode. Use when working on the 6657 mode prompt, persona lenses, style evaluation tasks, SkillOpt proposals, or generated runtime guidance. Preserve scene relevance, persona…

Jul 25, 2026
skillopt-sleep
computer-occupations-all-other

Run the Microsoft SkillOpt-Sleep workflow for ADVX Live's room-6657 style skill. Use when downloading the pinned optimizer, validating the reviewed task set, running mock or Codex optimization, inspecting staged candidates, evaluating final tests, adopting a…

Jul 24, 2026
codex-review
software-quality-assurance-analysts-and-testers

A standalone adversarial PLAN-review loop where Claude Code (builder) and OpenAI Codex (read-only critic) tag-team an implementation plan before any code is written. Use this when you ALREADY have a plan or a clear idea and just want the cross-model…

Jul 24, 2026
grill-me-codex
software-developers

Two-act plan hardening. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan or design, one question at a time, recommending an answer for each and exploring the codebase when it can answer itself, until every branch of the decision tree is…

Jul 24, 2026
grill-with-docs-codex
software-developers

Two-act plan hardening with living documentation. ACT 1 (you ↔ Claude) — Claude interviews you relentlessly about a plan, one question at a time, challenging it against your project's existing domain model and glossary (CONTEXT.md), sharpening fuzzy terms,…

Jul 24, 2026
Showing 5 of 5 repositories
All repositories loaded