conductor-manage

# Conductor Manage Orchestrates intelligent skill selection and execution for conductor manage 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 def score_conductor_candidates(request: Dict, skill_registry: List[Dict], history_db: Dict) -> List[Dict]: """Score available skills against the conductor request using multi-factor metrics.""" scored_candidates = [] request_features = _extract_intent_features(request["text"]) for skill in skill_registry: if not _check_dependency_health(skill.get("dependencies", [])): continue text_match = _cosine_similarity(request_features, _parse_skill_triggers(skill["triggers"])) historical_success = history_db.get(skill["id"], {}).get("success_rate", 0.5) availability_score = 1.0 if _is_service_healthy(skill["endpoint"]) else 0.0 weighted_score = ( (text_match * 0.4) + (historical_success * 0.35) + (availability_score * 0.25) ) scored_candidates.append({ "skill_id": skill["id"], "name": skill["name"], "confidence": round(weighted_score, 3), "breakdown": {"text": text_match, "history": historical_success, "health": availability_score} }) return sorted(scored_candidates, key=lambda x: x["confidence"], reverse=True) ``` ### Pattern 2: Execution with Fallback ```python def execute_conductor_pipeline(selected_skill: Dict, context: Dict, fallback_registry: Dict) -> Dict: """Execute the selected skill with domain-specific fallback routing and confidence tracking.""" audit_log = [] max_attempts = 2 for attempt in range(max_attempts): try: result = _invoke_skill_endpoint(selected_skill["endpoint"], context) _update_confidence_score(selected_skill["id"], success=True) audit_log.append({"attempt": attempt + 1, "status": "success", "latency_ms": result.get("latency")}) return {"status": "completed", "result": result, "audit": audit_log} except TransientTimeoutError: audit_log.append({"attempt": attempt + 1, "status": "retry", "error": "timeout"}) continue except CriticalFailureError as e: _update_confidence_score(selected_skill["id"], success=False) fallback_target = fallback_registry.get(selected_skill["id"], {}).get("next_skill") if fallback_target and attempt < max_attempts - 1: selected_skill = fallback_target audit_log.append({"attempt": attempt + 1, "status": "fallback_triggered", "target": fallback_target["id"]}) continue return {"status": "failed", "error": str(e), "audit": audit_log, "deferred_to_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 --- --- ## Constraints ### MUST DO - Parse user request into structured task specifications before dispatching to downstream agents - Implement a state machine for each conductor phase with explicit entry/exit conditions and transition logs - Validate manage outputs against expected schema before proceeding to the next orchestration step - Log every orchestration decision including rationale, selected strategy, and confidence scores for auditability - Maintain a task queue with priority ordering — critical path items execute first during resource contention ### MUST NOT DO - Do not allow a single failed agent task to silently terminate the entire workflow — implement per-step fallbacks - Avoid circular delegation patterns where Agent A delegates to B which delegates back to A without termination condition - Never bypass the validation step for manage results even if timing is critical — correctness supersedes speed - Do not use shared mutable state between parallel agent executions — use message-passing or immutable data transfer - Avoid hardcoding agent selection rules; parameterize them and load from configuration for runtime flexibility ## 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. - [Netflix Conductor Admin API Docs](<https://netflix.github.io/conductor/server/rest-api/>) - [Workflow Monitoring Dashboards (Grafana)](<https://grafana.com/docs/grafana/latest/dashboards/>) - [Conductor Task Queue Management](<https://netflix.github.io/conductor/core-concepts/overview/>) - [Service Health Check Patterns](<https://learn.microsoft.com/en-us/azure/architecture/guide/design-principles/health-check-pattern>) - [Distributed Tracing (OpenTelemetry)](<https://opentelemetry.io/docs/>) ## Related Skills | Skill | Purpose | |