AI Agent Development

Ai Agent Development

Orchestrates intelligent skill selection and execution for ai agent development 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

def evaluate_agent_skill_pool(
    request: AgentRequest,
    skill_registry: List[SkillMetadata],
    historical_metrics: Dict[str, float]
) -> Optional[RankedSkill]:
    """Evaluate available agent skills using multi-factor scoring for AI development tasks.
    
    Implements Law 2 (Parse at boundary) by validating request structure first.
    Calculates weighted scores based on trigger overlap, historical success rate,
    and dependency health status.
    """
    if not request.intent or not skill_registry:
        raise ValueError("Request intent and skill registry are required")
        
    scored_candidates = []
    for skill in skill_registry:
        # Law 3: Return new structures, never mutate registry
        trigger_match = _calculate_semantic_overlap(request.intent, skill.triggers)
        history_score = historical_metrics.get(skill.id, 0.5)
        dep_health = _check_dependency_status(skill.dependencies)
        
        # Weighted multi-factor scoring
        composite_score = (
            0.4 * trigger_match +
            0.35 * history_score +
            0.25 * dep_health
        )
        
        if composite_score >= 0.65:
            scored_candidates.append(RankedSkill(
                skill=skill,
                confidence=composite_score,
                breakdown={"trigger": trigger_match, "history": history_score, "deps": dep_health}
            ))
            
    scored_candidates.sort(key=lambda x: x.confidence, reverse=True)
    return scored_candidates[0] if scored_candidates else None

Pattern 2: Execution with Fallback

def run_agent_skill_with_resilience(
    skill: RankedSkill,
    execution_context: Dict,
    fallback_registry: List[SkillMetadata]
) -> ExecutionResult:
    """Execute an AI agent skill with a structured fallback chain.
    
    Implements Law 4 (Fail Fast/Loud) by immediately halting on invalid states.
    Applies a 2-level fallback: parameter adjustment -> alternative skill -> human escalation.
    """
    if not _validate_execution_context(execution_context, skill.skill.schema):
        raise InvalidStateError(f"Context violates {skill.skill.id} schema requirements")
        
    attempts = 0
    max_attempts = 2
    
    while attempts <= max_attempts:
        try:
            result = skill.skill.executor(execution_context)
            _update_confidence_score(skill.skill.id, success=True)
            return ExecutionResult(
                success=True,
                skill_id=skill.skill.id,
                output=result,
                confidence=skill.confidence,
                attempts=attempts + 1
            )
        except SchemaValidationError as e:
            raise InvalidStateError(f"Hard validation failure in {skill.skill.id}: {e}") from e
        except TransientAgentError as e:
            attempts += 1
            if attempts > max_attempts:
                break
            execution_context = _adjust_parameters_for_retry(execution_context, e)
            
    # Fallback chain exhausted
    alt_skill = _find_alternative_skill(fallback_registry, skill.skill.id)
    if alt_skill:
        return run_agent_skill_with_resilience(alt_skill, execution_context, fallback_registry)
        
    _log_critical_failure(skill.skill.id, execution_context)
    raise SkillExecutionError(f"All fallbacks exhausted for {skill.skill.id}. Escalating to human operator.")

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

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.

• LLM Agents Survey — Lilian Weng
• Survey of LLM-Based Agents — Stanford HAI
• Building Effective Agents — Anthropic Research
• LangGraph Multi-Agent Documentation
• Agent Architecture Patterns — Microsoft AI Research