proof-assistant

Assist in constructing algorithm correctness proofs

509 stars

Best use case

proof-assistant is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Assist in constructing algorithm correctness proofs

Teams using proof-assistant should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/proof-assistant/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/specializations/algorithms-optimization/skills/proof-assistant/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/proof-assistant/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How proof-assistant Compares

Feature / Agentproof-assistantStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Assist in constructing algorithm correctness proofs

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Proof Assistant Skill

## Purpose

Assist in constructing formal correctness proofs for algorithms using standard proof techniques.

## Capabilities

- Proof structure templates (induction, contradiction, etc.)
- Step-by-step proof guidance
- Termination argument generation
- Proof review and validation
- Identify proof gaps

## Target Processes

- correctness-proof-testing
- algorithm-implementation

## Proof Techniques

### Mathematical Induction
- Base case identification
- Inductive hypothesis formulation
- Inductive step construction

### Proof by Contradiction
- Assumption negation
- Logical derivation
- Contradiction identification

### Loop Invariant Proofs
- Invariant specification
- Three-part proof (init, maintenance, termination)

### Structural Induction
- For recursive data structures
- Base case (leaf/empty)
- Inductive case (composite)

## Input Schema

```json
{
  "type": "object",
  "properties": {
    "algorithm": { "type": "string" },
    "code": { "type": "string" },
    "proofType": {
      "type": "string",
      "enum": ["induction", "contradiction", "invariant", "structural"]
    },
    "claim": { "type": "string" },
    "partialProof": { "type": "string" }
  },
  "required": ["algorithm", "claim"]
}
```

## Output Schema

```json
{
  "type": "object",
  "properties": {
    "success": { "type": "boolean" },
    "proof": { "type": "string" },
    "structure": { "type": "array" },
    "gaps": { "type": "array" },
    "suggestions": { "type": "array" }
  },
  "required": ["success"]
}
```

Related Skills

elicit-research-assistant

509
from a5c-ai/babysitter

AI-assisted literature review for question-answering over papers and evidence synthesis

academic-writing-assistant

509
from a5c-ai/babysitter

Skill for assisting with academic and scientific writing

proof-structure-analyzer

509
from a5c-ai/babysitter

Analyze and restructure mathematical proofs for clarity and completeness

lean-proof-assistant

509
from a5c-ai/babysitter

Interface with Lean 4 proof assistant for formal theorem verification

coq-proof-assistant

509
from a5c-ai/babysitter

Interface with Coq proof assistant for formal verification

soundness-proof-assistant

509
from a5c-ai/babysitter

Assist in constructing type soundness proofs using progress and preservation theorems

latex-proof-formatter

509
from a5c-ai/babysitter

Format proofs and algorithms in publication-quality LaTeX

amortized-analysis-assistant

509
from a5c-ai/babysitter

Apply amortized analysis techniques including aggregate, accounting, and potential methods

qbr-preparation-assistant

509
from a5c-ai/babysitter

Quarterly Business Review preparation and facilitation skill with agenda and materials generation

refactoring-assistant

509
from a5c-ai/babysitter

Suggest and guide application of refactoring patterns to improve code quality

containerization-assistant

509
from a5c-ai/babysitter

Assist in containerizing applications with Dockerfile generation and optimization

process-builder

509
from a5c-ai/babysitter

Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.

Workflow & Productivity