Parallel Skill Runner

Parallel Skill Runner

Orchestrates intelligent skill selection and execution for parallel skill runner 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_parallel_candidates(
    task: str,
    candidate_skills: List[SkillMetadata],
    historical_registry: Dict[str, HistoricalRecord]
) -> List[RankedSkill]:
    """Score and rank skills for parallel dispatch based on multi-factor metrics.
    
    Applies Law 2 (Parse at boundary) by validating inputs upfront.
    Returns immutable ranked list for deterministic routing.
    """
    if not task or not candidate_skills:
        raise ValueError("Task and candidate_skills must be non-empty")
        
    parsed_task = _parse_intent_and_entities(task)
    ranked = []
    
    for skill in candidate_skills:
        if not _is_skill_available(skill):
            continue
            
        text_match = _cosine_similarity(parsed_task.terms, skill.trigger_terms)
        history = historical_registry.get(skill.id, HistoricalRecord())
        success_rate = history.success_count / max(history.total_runs, 1)
        availability_score = _get_current_load_score(skill.endpoint)
        
        composite_score = (0.4 * text_match) + (0.4 * success_rate) + (0.2 * availability_score)
        
        ranked.append(RankedSkill(
            skill=skill,
            confidence=composite_score,
            expected_latency_ms=_estimate_latency(skill, parsed_task)
        ))
        
    ranked.sort(key=lambda x: x.confidence, reverse=True)
    return ranked

Pattern 2: Execution with Fallback

async def run_parallel_with_fallback(
    ranked_skills: List[RankedSkill],
    task_context: Dict,
    fallback_map: Dict[str, List[str]],
    timeout_seconds: float = 30.0
) -> ParallelExecutionResult:
    """Execute top N skills in parallel with per-skill fallback chains.
    
    Implements Law 4 (Fail Fast/Loud) by isolating failures and applying fallbacks.
    Returns aggregated results without mutating original context.
    """
    if not ranked_skills:
        raise ParallelExecutionError("No skills available for parallel execution")
        
    selected = ranked_skills[:3] # Execute top 3 in parallel
    tasks = []
    
    for ranked in selected:
        tasks.append(_execute_single_skill_with_fallback(
            skill=ranked.skill,
            context=task_context,
            fallback_chain=fallback_map.get(ranked.skill.id, []),
            timeout=timeout_seconds
        ))
        
    results = await asyncio.gather(*tasks, return_exceptions=True)
    
    aggregated = ParallelExecutionResult(
        success_count=0,
        failed_count=0,
        results=[],
        fallbacks_triggered=[]
    )
    
    for ranked, result in zip(selected, results):
        if isinstance(result, Exception):
            aggregated.failed_count += 1
            aggregated.fallbacks_triggered.append(ranked.skill.id)
        else:
            aggregated.success_count += 1
            aggregated.results.append(result)
            
    return aggregated

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

• Implement a dependency graph for all tasks before dispatch — only execute nodes whose dependencies are satisfied
• Use a central coordinator that maintains global state and communicates results between parallel agents via immutable messages
• Set explicit timeouts per task and implement circuit breakers: abort parallel execution if error rate exceeds threshold
• Log all inter-agent communications with timestamps, sender, receiver, payload hash, and outcome for debugging

MUST NOT DO

• Do not allow parallel agents to modify shared mutable state without locking — use message-passing or per-task snapshots
• Avoid fan-out patterns that spawn more than 20 parallel tasks simultaneously without rate limiting
• Never start dependent tasks before confirming upstream task completion — verify status, don't assume success
• Do not ignore agent failures during parallel execution; aggregate and report all errors together rather than failing fast on first

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.

• OpenAI Agent Design Patterns (Microsoft) — Standard patterns for agent orchestration including parallel execution
• LangGraph Parallel Branches — Documentation on implementing parallel processing workflows in LangGraph
• Multi-Agent Orchestration with CrewAI — Guide to parallel task execution across multiple AI agents
• CAMEL Communication Framework — Research on multi-agent communication and coordination patterns
• LLM Powered Autonomous Agents (Liao et al.) — Foundational paper on LLM-based autonomous agent architectures