with one click
documentation
// Implements intelligent documentation with multi-factor skill selection, fallback chains, and adherence to the 5 Laws of Elegant Defense
// Implements intelligent documentation with multi-factor skill selection, fallback chains, and adherence to the 5 Laws of Elegant Defense
| 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 |
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.
┌───────────────────────────────────────────────────────────────────────────────┐ │ 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 │ │ │ └──────────────────────────────────────────────────────────┘ │ └─────────────────────────────────────────────────────────────────────┘
Use this skill when:
Avoid this skill for:
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:
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:
related-skillsCheckpoint: Record outcome with timing and confidence metadata.
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
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"])
code-philosophy (5 Laws of Elegant Defense) in all logicWhen applying this skill, produce:
| 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 |