documentation

compatibility	opencode
completeness	95
content-types	["guidance","examples","do-dont"]
description	Implements intelligent documentation 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":"documentation, documentation, how do i documentation, orchestrate documentation, automate documentation, agent documentation","version":"1.0.0"}
name	documentation

Documentation

Orchestrates intelligent skill selection and execution for documentation 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 select_skill(
    task_description: str,
    available_skills: List[Dict],
    min_confidence: float = 0.7
) -> Optional[Dict]:
    """Route a documentation request to the optimal generator.
    
    Evaluates generators based on content type match, historical accuracy,
    and current system load. Returns structured routing metadata.
    """
    # Guard clause - Early Exit (Law 1)
    if not task_description or not task_description.strip():
        raise ValueError("Task description cannot be empty")
        
    if not available_skills:
        raise ValueError("No skills available for selection")
    
    # Parse input - Make Illegal States Unrepresentable (Law 2)
    target_type = "documentation"
    best_match = None
    best_score = 0.0
    
    for skill in available_skills:
        type_match = 1.0 if skill.get("doc_format") == target_type else 0.5
        history_score = skill.get("success_rate", 0.0)
        load_penalty = 1.0 - (skill.get("current_load", 0.0) / 100.0)
        
        score = (type_match * 0.5) + (history_score * 0.3) + (load_penalty * 0.2)
        
        if score > best_score and score >= min_confidence:
            best_score = score
            best_match = skill
    
    if best_match is None:
        return None
    
    # Atomic Predictability (Law 3) - Return new dict, don't mutate
    result = dict(best_match)
    result["selected_confidence"] = best_score
    result["selection_timestamp"] = time.time()
    return result

Pattern 2: Execution with Fallback

def execute_with_fallback(
    skill: Dict,
    task_context: Dict,
    max_retries: int = 2
) -> Dict:
    """Execute documentation generation with structured fallback chain.
    
    Implements the Fail Fast, Fail Loud principle (Law 4):
    - Invalid states halt immediately with descriptive errors
    - No silent failures or partial results
    
    Fallback chain:
    1. Retry with adjusted template parameters
    2. Fallback to static markdown generator
    3. Queue for human documentation specialist
    """
    # Guard clause - validate skill (Early Exit)
    if not _validate_doc_schema(task_context):
        raise DocGenerationError("Invalid documentation schema provided")
    
    # Parse context - Ensure trusted state (Law 2)
    validated_context = _parse_and_validate_context(task_context, skill)
    
    for attempt in range(max_retries + 1):
        try:
            raw_output = _invoke_generator(skill, validated_context)
            validated_doc = _parse_and_validate_output(raw_output)
            
            # Success - Atomic Predictability (Law 3)
            return {
                "success": True,
                "skill_executed": skill["name"],
                "format": skill.get("output_format", "markdown"),
                "content": validated_doc,
                "attempts": attempt + 1,
                "latency_ms": time.time() * 1000
            }
            
        except SchemaValidationError as e:
            # Fail Fast - Don't try to patch bad data (Law 4)
            raise DocGenerationError(f"Schema validation failed: {e}") from e
            
        except GeneratorTimeoutError:
            # Transient error - try fallback
            if attempt == max_retries:
                return _fallback_to_static_generator(validated_context)
    
    # All retries exhausted - Fail Loud (Law 4)
    return _fallback_to_human_review(validated_context, skill["name"])

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
agent-dynamic-replanner	Replans execution when conditions change
agent-parallel-skill-runner	Executes independent skills in parallel
agent-dependency-graph-builder	Builds and resolves skill dependency graphs
agent-task-decomposer	Breaks complex tasks into delegable subtasks
agent-confidence-based-selector	Alternative confidence-based routing approach

---

Constraints

MUST DO

• Ensure each agent handles a single responsibility
• Include explicit fallback/error routing for every branching point
• Reference code-philosophy (5 Laws of Elegant Defense)

MUST NOT DO

• Use fixed thresholds without adaptive tuning
• Ignore low-confidence fallback scenarios
• Skip execution history tracking