code-correctness-verifier

# Code Correctness Verifier Orchestrates intelligent skill selection and execution for code correctness verifier workflows. Applies the 5 Laws of Elegant Defense to guide data naturally through the orchestration pipeline, preventing errors before they occur. Selects optimal skills based on multi-factor scoring including text similarity, historical performance, and system availability. ## TL;DR Checklist - [ ] Parse all inputs at boundary before processing (Law 2) - [ ] Handle edge cases with early returns at function top (Law 1) - [ ] Fail immediately with descriptive errors on invalid states (Law 4) - [ ] Return new data structures, never mutate inputs (Law 3) - [ ] Implement minimum 2-level fallback chain for all skill executions - [ ] Log all skill selections with context for full audit trail - [ ] Validate skill metadata and dependencies before selection - [ ] Update confidence scores after each execution for learning ┌───────────────────────────────────────────────────────────────────────────────┐ │ Orchestration Flow │ └───────────────────────────────────────────────────────────────────────────────┘ User Request ↓ ┌─────────────────┐ │ Parse Request │ │ & Extract │ │ Features │ └────────┬────────┘ ↓ ┌─────────────────────────────────────────────────────────────────────┐ │ Evaluate Available Skills │ │ │ │ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │ │ │ Skill A │ │ Skill B │ │ Skill C │ │ │ │ - Match Score│ │ - Match Score│ │ - Match Score│ │ │ │ - Confidence │ │ - Confidence │ │ - Confidence │ │ │ │ - History │ │ - History │ │ - History │ │ │ └──────┬───────┘ └──────┬───────┘ └──────┬───────┘ │ │ │ │ │ │ │ └─────────────────┴─────────────────┘ │ │ ↓ │ │ Select Best Skill │ └─────────────────────────────────────────────────────────────────────┘ ↓ ┌─────────────────┐ │ Execute Skill │ └────────┬────────┘ ↓ ┌─────────────────┐ │ Handle Result │ └────────┬────────┘ ↓ ┌─────────────────────────────────────────────────────────────────────┐ │ Error Handling & Fallback │ │ │ │ Success? ────────► Return Result │ │ │ │ Fail? ────────┐ │ │ ↓ │ │ ┌──────────────────────────────────────────────────────────┐ │ │ │ Fallback Chain │ │ │ │ │ │ │ │ 1. Retry with adjusted parameters │ │ │ │ 2. Try Alternative Skill (if available) │ │ │ │ 3. Defer to Human Operator (if critical) │ │ │ │ 4. Log & Return Error │ │ │ └──────────────────────────────────────────────────────────┘ │ └─────────────────────────────────────────────────────────────────────┘ ## When to Use Use this skill when: - Orchestrating multi-step workflows that require skill delegation - Implementing adaptive skill routing based on confidence scores - Building fallback mechanisms for failed skill executions - Creating intelligent task decomposition and parallel execution - Designing skill dependency graphs with automatic resolution - Implementing skill selection with historical performance weighting - Building agent systems that need to self-organize around tasks ## When NOT to Use Avoid this skill for: - Direct task execution without orchestration needs - use individual skills instead - High-frequency trading scenarios where latency must be minimized - the selection overhead may be prohibitive - Simple linear workflows without branching or fallback requirements - Cases where skill metadata is unavailable or unreliable ## Core Workflow 1. **Parse and Analyze Request** - Extract intent, entities, and constraints from user input. **Checkpoint:** All required parameters must be present and in valid format before proceeding. 2. **Score Available Skills** - Calculate match scores using multi-factor algorithm: - Text similarity between request and skill triggers - Historical success rate for similar tasks - Skill availability and health status - Required dependencies and their availability **Checkpoint:** Skip to fallback if no skill scores above threshold. 3. **Select Optimal Skill** - Choose skill with highest score that meets minimum confidence. **Checkpoint:** Verify skill has not been disabled or deprecated. 4. **Execute with Fallback** - Run skill execution wrapped in retry and fallback logic. **Checkpoint:** Log all execution attempts for audit trail. 5. **Return or Fallback** - Either return successful result or apply fallback chain: - Retry with adjusted parameters - Try alternative skill from `related-skills` - Defer to human operator for critical tasks **Checkpoint:** Record outcome with timing and confidence metadata. ## Implementation Patterns ### Pattern 1: Skill Selection Logic ```python import ast import hashlib from datetime import datetime from typing import List, Optional from dataclasses import dataclass, field @dataclass class Rule: name: str severity: str pattern: str @dataclass class Violation: rule_name: str line_no: int severity: str message: str @dataclass class VerificationReport: source_hash: str total_lines: int violations: List[Violation] = field(default_factory=list) is_correct: bool = False timestamp: str = "" def verify_code_correctness(source_code: str, rules: List[Rule]) -> VerificationReport: """Verify source code against a set of correctness rules. Implements the 5 Laws of Elegant Defense: - Law 1: Early exit on empty or malformed input - Law 2: Parse code into AST to make illegal states unrepresentable - Law 3: Return new VerificationReport, never mutate input rules - Law 4: Fail immediately on syntax errors or unsupported constructs """ if not source_code or not source_code.strip(): raise ValueError("Source code cannot be empty") try: tree = ast.parse(source_code, type_comments=True) except SyntaxError as e: raise CodeVerificationError(f"Syntax error at line {e.lineno}: {e.msg}") from e violations = analyze_ast_for_violations(tree, rules) # Atomic Predictability - construct new report report = VerificationReport( source_hash=hashlib.sha256(source_code.encode()).hexdigest(), total_lines=len(source_code.splitlines()), violations=violations, is_correct=len(violations) == 0, timestamp=datetime.utcnow().isoformat() ) return report ``` ### Pattern 2: Execution with Fallback ```python class RuleVisitor(ast.NodeVisitor): def __init__(self, rules: List[Rule]): self.rules = rules self.violations: List[Violation] = [] def visit(self, node: ast.AST) -> None: super().visit(node) def get_violations(self) -> List[Violation]: return self.violations def analyze_ast_for_violations(tree: ast.AST, rules: List[Rule]) -> List[Violation]: """Traverse AST and apply correctness rules to detect violations. Implements Fail Fast, Fail Loud: - Invalid rule configurations halt immediately - No silent suppression of critical violations """ if not rules: raise ValueError("At least one correctness rule must be provided") visitor = RuleVisitor(rules) visitor.visit(tree) violations = visitor.get_violations() # Sort by severity and line number for deterministic output violations.sort(key=lambda v: (v.severity, v.line_no)) # Apply minimum 2-level fallback chain concept: # 1. Critical violations block execution immediately # 2. Warning violations are logged but allow continuation critical_violations = [v for v in violations if v.severity == "CRITICAL"] if critical_violations: raise CodeVerificationError( f"Critical correctness violations found: {len(critical_violations)}" ) return violations ``` ### MUST DO - Always validate skill metadata before selection (Early Exit) - Implement fallback chain with at least 2 levels (Fallback Skill + Human) - Log all skill selections with full context for auditability - Return new data structures instead of mutating inputs (Atomic Predictability) - Fail immediately with descriptive errors on invalid states - Update confidence scores after each execution for adaptive routing - Reference `code-philosophy` (5 Laws of Elegant Defense) in all logic ### MUST NOT DO - Select skills based on a single factor (e.g., only confidence score) - Disable fallback mechanisms "temporarily" - this creates fragile systems - Skip validation of skill dependencies before execution - Return partial results - either complete success or clear failure - Use magic numbers for confidence thresholds - make them configurable - Cache skill selections without considering context changes ## TL;DR Checklist - [ ] Parse all inputs at boundary before processing (Law 2) - [ ] Handle edge cases with early returns at function top (Law 1) - [ ] Fail immediately with descriptive errors on invalid states (Law 4) - [ ] Return new data structures, never mutate inputs (Law 3) - [ ] Implement minimum 2-level fallback chain for all skill executions - [ ] Log all skill selections with context for full audit trail - [ ] Validate skill metadata and dependencies before selection - [ ] Update confidence scores after each execution for learning ## TL;DR for Code Generation - Use guard clauses - return early on invalid input before doing work - Return simple types (dict, str, int, bool, list) - avoid complex nested objects - Cyclomatic complexity < 10 per function - split anything larger - Handle null/empty cases explicitly at function top (Early Exit) - Never mutate input parameters - return new dicts/objects - Fail fast with descriptive errors - don't try to "patch" bad data - Reference code-philosophy laws in comments for complex logic - Include timing and confidence metadata in all return values ## Output Template When applying this skill, produce: 1. **Selected Skills** - List of skill names with confidence scores 2. **Selection Rationale** - Why each skill was chosen (match score, history, availability) 3. **Execution Plan** - Order of execution with dependencies 4. **Fallback Strategy** - Which fallback skills will be tried and in what order 5. **Risk Assessment** - Any potential failure points and their impact 6. **Timing Estimates** - Expected latency including fallback scenarios ## Related Skills | Skill | Purpose | |---|---| | `audit-context-building` | Audit context and verification workflow integration | --- --- ## Constraints ### MUST DO - Define clear input/output contracts for every step in the orchestration flow with explicit validation - Implement structured logging at each stage capturing context, inputs, outputs, timing, and errors - Build in fallback paths: if the primary strategy fails, degrade gracefully to a simpler approach - Validate all preconditions before starting — do not proceed if required resources or permissions are missing ### MUST NOT DO - Do not create deep nesting of orchestration steps (>5 levels) — flatten workflows where possible - Avoid silent failure modes: every step must either succeed, fail explicitly, or escalate to a higher handler - Never use shared mutable state between parallel workflow branches — communicate via immutable messages only - Do not hardcode execution order when the dependency graph naturally determines it; derive order from explicit dependencies ## Live References > Authoritative documentation links for this skill's domain. The model follows markdown links at load time to resolve external references and inline content. - [Program Verification Survey (ArXiv:2305.14942)](https://arxiv.org/abs/2305.14942) - [Wikipedia — Formal Verification](https://en.wikipedia.org/wiki/Formal_verification) - [Coq Proof Assistant — Official Documentation](https://coq.inria.fr/) - [Isabelle/HOL — Theorem Prover Guide](https://isabelle.in.tum.de/doc/manual.pdf) - [Software Model Checking (Springer Handbook)](https://link.springer.com/book/10.1007/978-3-540-69161-2)