Skill

formalize

Convert problem state into rigorous math modules with falsifiable assumptions and surrogate ladder

Install

npx claudepluginhub jobrien127/plugin-marketplace --plugin solution-engine

Tool Access

This skill is limited to using the following tools:

Read Glob Grep Write Agent

Preview

Transform `problem-state.yaml` into modular math specifications following the PROBLEM_TEMPLATE rigor level.

SKILL.md

Similar Skills

cache-components

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

139.2k

mcp-builder

9 files

Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).

anthropics-skills-13

124.2k

canvas-design

20 files

Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.

anthropics-skills-13

124.2k

Stats

Parent Repo Stars0

Parent Repo Forks0

Last CommitApr 24, 2026

Actions

View Source View Plugin View on GitHub View README

/formalize

Transform problem-state.yaml into modular math specifications following the PROBLEM_TEMPLATE rigor level.

Pipeline Position

Requires: collect complete, valid problem-state.yaml

Produces: $MATH_ROOT/ populated modules (00-notation through operations)

Advances: formalize → complete

Instructions

Load $PROBLEMS_ROOT/$ARGUMENTS/problem-state.yaml.

Load ${CLAUDE_PLUGIN_ROOT}/templates/PROBLEM_TEMPLATE.md for required structure.

Load existing math modules from $MATH_ROOT/ (may have content from external sources).

For each PROBLEM_TEMPLATE section: a. Check if an external source has a more advanced version (maturity markers) b. If yes: migrate and modularize that content, don't rewrite inferior version c. If no: formalize from the problem state

Each module must have valid YAML frontmatter (id, layer, depends, symbols_defined, inputs, outputs).

Use LaTeX for equations. YAML blocks for structured data. No prose padding.

Declare assumptions as named + falsifiable (A1, A2, ...) with thresholds and falsification methods.

Include surrogate ladder if the problem has a long-horizon objective.

Update pipeline-state.json: set formalize to complete.

/formalize

Transform problem-state.yaml into modular math specifications following the PROBLEM_TEMPLATE rigor level.

Pipeline Position

Requires: collect complete, valid problem-state.yaml
Produces: $MATH_ROOT/ populated modules (00-notation through operations)
Advances: formalize → complete

Instructions

Load $PROBLEMS_ROOT/$ARGUMENTS/problem-state.yaml.
Load ${CLAUDE_PLUGIN_ROOT}/templates/PROBLEM_TEMPLATE.md for required structure.
Load existing math modules from $MATH_ROOT/ (may have content from external sources).
For each PROBLEM_TEMPLATE section: a. Check if an external source has a more advanced version (maturity markers) b. If yes: migrate and modularize that content, don't rewrite inferior version c. If no: formalize from the problem state
Each module must have valid YAML frontmatter (id, layer, depends, symbols_defined, inputs, outputs).
Use LaTeX for equations. YAML blocks for structured data. No prose padding.
Declare assumptions as named + falsifiable (A1, A2, ...) with thresholds and falsification methods.
Include surrogate ladder if the problem has a long-horizon objective.
Update pipeline-state.json: set formalize to complete.