From antigravity-awesome-skills
Converts technical documents into structured mathematical problem specifications with variables, constraints, objectives, and uncertainty. Uses strict evidence-tracking and zero-inference rules.
How this skill is triggered — by the user, by Claude, or both
Slash command
/antigravity-awesome-skills:doc2mathThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
- "Formalize this problem statement into math"
"evidence" field)null; ambiguous types use "ambiguous""inferred": true with "inference_basis""status": "MISSING" with "missing_reason"Accept the document text, research excerpt, problem description, or specification as input.
Identify problem_class: optimization | classification | simulation | proof | estimation | other
Variables — id, name, symbol, type, domain, units, role, evidence, inferred, status
Operators — id, name, symbol, arity, acts_on, produces, evidence, inferred
Constraints — id, type, expression, variables_involved, evidence, hardness, inferred, status
Objectives — id, direction (minimize/maximize/satisfy/find/prove), expression, variables_involved, evidence, inferred
Uncertainty — id, type (stochastic/epistemic/measurement/model/none_stated), affects, characterization, evidence, status
Identify what the document implies but doesn't state: missing_information[] with element, needed_for, missing_reason.
validation_flags:
has_complete_objectives: true/false/partialhas_bounded_variables: true/false/partialhas_evidence_for_all_elements: true/false/partialinference_count: integermissing_count: integeroverall_formalizability: HIGH/MEDIUM/LOWProduce the complete MPS as a JSON object:
{
"mps_version": "1.0",
"source_title": "...",
"problem_class": "optimization",
"variables": [...],
"operators": [...],
"constraints": [...],
"objectives": [...],
"uncertainty": [...],
"missing_information": [...],
"validation_flags": {
"overall_formalizability": "HIGH"
}
}
evidence fieldnpx claudepluginhub sickn33/antigravity-awesome-skills --plugin antigravity-bundle-aas-mobile-app-builderExtracts and categorizes requirements from PDFs, Word docs, transcripts, specs, and web content using pattern matching and outputs structured YAML.
Extracts first-principles reasoning chains from technical documents: root problems, assumptions, alternatives, decision sensitivity, and open unknowns. Useful for onboarding, decision review, and understanding why decisions were made.
Translate business/user requirements into technical specifications that engineers can build against. Use when clarifying ambiguous requirements or discovering hidden technical constraints.