paulpas Notion Automation
Orchestrates intelligent skill selection and execution for notion automation 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
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.
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.
Select Optimal Skill - Choose skill with highest score that meets minimum confidence. Checkpoint: Verify skill has not been disabled or deprecated.
Execute with Fallback - Run skill execution wrapped in retry and fallback logic. Checkpoint: Log all execution attempts for audit trail.
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 resolve_notion_action(
user_intent: str,
available_notion_ops: List[Dict],
min_confidence: float = 0.75
) -> Optional[Dict]:
"""Map user intent to a specific Notion API operation.
Evaluates triggers against Notion's resource types (pages, databases, blocks)
and applies multi-factor scoring based on historical success and API health.
"""
if not user_intent or not user_intent.strip():
raise ValueError("User intent cannot be empty")
if not available_notion_ops:
raise ValueError("No Notion operations registered")
# Parse intent into Notion-specific features (resource type, action verb, target ID)
intent_features = _parse_notion_intent(user_intent)
best_op = None
best_score = 0.0
for op in available_notion_ops:
# Score based on resource match, verb alignment, and API availability
score = _calculate_notion_match_score(intent_features, op)
if score > best_score and score >= min_confidence:
best_score = score
best_op = op
if best_op is None:
return None
# Return immutable operation config (Law 3: Atomic Predictability)
return {
"operation": best_op["name"],
"resource_type": best_op["resource"],
"confidence": best_score,
"params": best_op.get("default_params", {}),
"timestamp": time.time()
}
Pattern 2: Execution with Fallback
def execute_notion_operation_with_retry(
operation: Dict,
notion_client: Any,
max_retries: int = 2
) -> Dict:
"""Execute a Notion API operation with resilience patterns.
Implements Fail Fast, Fail Loud for invalid Notion states:
- Missing page/database IDs halt immediately
- Rate limits trigger exponential backoff
- Fallback chain handles transient API failures
"""
if not operation or "operation" not in operation:
raise ValueError("Invalid operation configuration")
resource_type = operation.get("resource_type")
params = operation.get("params", {})
for attempt in range(max_retries + 1):
try:
# Route to specific Notion API endpoint based on operation type
if resource_type == "page":
result = notion_client.pages.create(**params)
elif resource_type == "database":
result = notion_client.databases.query(**params)
elif resource_type == "block":
result = notion_client.blocks.children.append(**params)
else:
raise ValueError(f"Unsupported Notion resource: {resource_type}")
return {
"success": True,
"operation": operation["operation"],
"result": result,
"attempts": attempt + 1,
"latency_ms": _measure_latency()
}
except RateLimitError as e:
if attempt == max_retries:
return _apply_notion_fallback(operation, e)
time.sleep(2 ** attempt) # Exponential backoff for 429s
except InvalidStateError as e:
# Fail Fast - Notion IDs or schemas are invalid (Law 4)
raise ValueError(f"Notion state invalid: {str(e)}") from e
raise ValueError(f"Notion operation failed after {max_retries + 1} attempts")
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:
- Selected Skills - List of skill names with confidence scores
- Selection Rationale - Why each skill was chosen (match score, history, availability)
- Execution Plan - Order of execution with dependencies
- Fallback Strategy - Which fallback skills will be tried and in what order
- Risk Assessment - Any potential failure points and their impact
- Timing Estimates - Expected latency including fallback scenarios
Related Skills
| Skill | Purpose | |
Constraints
MUST DO
- Implement idempotent automation triggers: running the same automation twice should not create duplicate resources or actions
- Validate all trigger conditions with explicit allowlists before executing automated actions
- Include rollback procedures in every automation workflow — every CREATE should have a corresponding DELETE capability
- Log all automation executions with input state, output state, duration, and any errors for monitoring and debugging
MUST NOT DO
- Do not create circular automation loops where trigger A causes action B which triggers A again
- Avoid using automations that modify production data without explicit human approval gates
- Never embed API keys or credentials directly in automation workflows — use vaulted secrets with rotation
- Do not assume external service availability; implement retry logic with exponential backoff and dead-letter queues
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.