---

name: closed-loop-delivery compatibility: opencode completeness: 95 content-types:

• guidance
• examples
• do-dont description: Implements intelligent closed loop delivery with multi-factor skill selection, fallback chains, and adherence to the 5 Laws of Elegant Defense license: MIT maturity: stable metadata: domain: agent output-format: analysis related-skills: agent-confidence-based-selector, agent-task-routing role: orchestration scope: orchestration triggers: closed-loop-delivery, closed loop delivery, how do i closed-loop-delivery, orchestrate closed-loop-delivery, automate closed-loop-delivery, agent closed-loop-delivery archetypes:
  • orchestration
  • strategic anti_triggers:
  • brainstorming
  • vague ideation
  • single-agent monolith response_profile: verbosity: medium directive_strength: high abstraction_level: tactical version: "1.0.0"

---

Closed Loop Delivery

Orchestrates intelligent skill selection and execution for closed loop delivery 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 score_and_select_skill(task: str, skill_registry: list[dict], history_db: dict) -> dict | None:
    """Closed-loop skill selection using multi-factor scoring and historical feedback.
    
    Implements Law 1 (Early Exit) and Law 2 (Make Illegal States Unrepresentable).
    Returns immutable selection metadata without mutating the registry.
    """
    if not task or not task.strip():
        raise ValueError("Task description cannot be empty")
    if not skill_registry:
        raise ValueError("No skills available in registry")

    task_vector = _embed_task(task)
    candidates = []
    
    for skill in skill_registry:
        if skill.get("status") != "active":
            continue
        text_sim = cosine_similarity(task_vector, _embed_skill(skill["triggers"]))
        hist_success = history_db.get(skill["id"], {}).get("success_rate", 0.5)
        availability = 1.0 if skill.get("health") == "healthy" else 0.3
        
        weighted_score = (text_sim * 0.5) + (hist_success * 0.3) + (availability * 0.2)
        candidates.append({"skill": skill, "score": weighted_score})

    candidates.sort(key=lambda x: x["score"], reverse=True)
    if not candidates or candidates[0]["score"] < 0.65:
        return None

    selected = candidates[0]
    # Law 3: Atomic Predictability - Return new dict, never mutate registry
    return {
        "skill_id": selected["skill"]["id"],
        "confidence": round(selected["score"], 3),
        "factors": {"text_sim": round(text_sim, 3), "history": hist_success, "avail": availability},
        "timestamp": time.time()
    }

Pattern 2: Execution with Fallback

def execute_closed_loop(skill_meta: dict, context: dict, fallback_graph: dict) -> dict:
    """Execute skill with adaptive fallback and confidence feedback loop.
    
    Implements Law 4 (Fail Fast, Fail Loud) and Law 3 (Immutable Returns).
    Routes through fallback chain only on transient errors, never patches invalid state.
    """
    if not _validate_context(context, skill_meta):
        raise ValueError("Context validation failed - illegal state detected")

    attempts = 0
    max_attempts = 2
    while attempts <= max_attempts:
        try:
            result = _invoke_skill(skill_meta["id"], context)
            # Success path: update confidence and log
            _update_confidence_score(skill_meta["id"], success=True)
            return {"status": "success", "data": result, "attempts": attempts + 1}
        except TransientError as e:
            attempts += 1
            if attempts > max_attempts:
                break
            context = _adjust_context_for_retry(context, e)
        except CriticalError as e:
            # Law 4: Fail fast on invalid state - do not retry
            _update_confidence_score(skill_meta["id"], success=False)
            raise

    # Fallback chain execution
    fallback_candidates = fallback_graph.get(skill_meta["id"], [])
    for fallback_skill in fallback_candidates:
        try:
            result = _invoke_skill(fallback_skill["id"], context)
            _update_confidence_score(fallback_skill["id"], success=True)
            return {"status": "fallback_success", "original": skill_meta["id"], "data": result}
        except Exception:
            continue

    # Exhausted all options - defer to human or return structured error
    _update_confidence_score(skill_meta["id"], success=False)
    return {"status": "failed", "error": "All execution paths exhausted", "requires_human": True}

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
acceptance-orchestrator	Acceptance criteria and delivery validation

---

---

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.

• Closed Loop Delivery — Martin Fowler (Bliki)
• Continuous Delivery Pipeline (Martin Fowler)
• Google DevOps Research — DORA Metrics
• AWS — Continuous Integration & Delivery Patterns
• The DevOps Handbook, 2nd Ed. (Gene Kim et al.) — Chapter 4