install
source · Clone the upstream repo
git clone https://github.com/a5c-ai/babysitter
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/specializations/algorithms-optimization/skills/proof-assistant" ~/.claude/skills/a5c-ai-babysitter-proof-assistant && rm -rf "$T"
manifest:
library/specializations/algorithms-optimization/skills/proof-assistant/SKILL.mdsource content
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
{ "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
{ "type": "object", "properties": { "success": { "type": "boolean" }, "proof": { "type": "string" }, "structure": { "type": "array" }, "gaps": { "type": "array" }, "suggestions": { "type": "array" } }, "required": ["success"] }