Requesting Code Review

---




name: requesting-code-review
compatibility: opencode
completeness: 95
content-types:
- guidance
- examples
- do-dont
description: Implements intelligent requesting code review 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: requesting-code-review, requesting code review, how do i requesting-code-review,
    orchestrate requesting-code-review, automate requesting-code-review, agent requesting-code-review
  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"




---




# Requesting Code Review

Orchestrates intelligent skill selection and execution for requesting code review 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 select_review_target(
    repo_config: Dict,
    request_context: Dict,
    min_confidence: float = 0.7
) -> Optional[Dict]:
    """Select the optimal code review target and platform based on repo config.
    
    Evaluates repository metadata, branch protection rules, and historical
    reviewer availability to determine the best PR/MR target.
    
    Args:
        repo_config: Repository metadata including platform, default branch, and reviewers
        request_context: User request containing target branch, reviewers, and scope
        min_confidence: Minimum confidence threshold for target selection
        
    Returns:
        Target configuration dict with platform, branch, and reviewer list
    """
    if not repo_config or not request_context.get("target_branch"):
        raise ValueError("Repository config and target branch are required")
        
    platform = repo_config.get("platform", "github")
    default_branch = repo_config.get("default_branch", "main")
    target_branch = request_context["target_branch"]
    
    # Validate branch exists and is not protected incorrectly
    if not _validate_branch_exists(repo_config, target_branch):
        raise ValueError(f"Branch '{target_branch}' not found in repository")
        
    # Calculate match score based on branch naming conventions and reviewer load
    match_score = _calculate_branch_match_score(target_branch, default_branch)
    reviewer_load = _get_reviewer_availability(repo_config.get("reviewers", []))
    
    if match_score < min_confidence:
        return None
        
    # Return immutable target config
    return {
        "platform": platform,
        "source_branch": target_branch,
        "target_branch": default_branch,
        "reviewers": reviewer_load["available"],
        "confidence": match_score,
        "timestamp": time.time()
    }
```


### Pattern 2: Execution with Fallback

```python
def execute_code_review_request(
    target_config: Dict,
    review_context: Dict,
    max_retries: int = 2
) -> Dict:
    """Execute a code review request with platform-specific API calls and fallbacks.
    
    Creates a Pull Request or Merge Request, assigns reviewers, and attaches
    review context. Implements fallbacks for API rate limits or permission issues.
    
    Args:
        target_config: Selected target configuration from select_review_target
        review_context: PR/MR title, description, labels, and reviewer assignments
        max_retries: Maximum retry attempts for transient API failures
        
    Returns:
        Execution result with PR/MR URL, status, and reviewer confirmation
    """
    platform = target_config["platform"]
    api_client = _get_platform_client(platform)
    
    for attempt in range(max_retries + 1):
        try:
            # Create PR/MR with review context
            pr_response = api_client.create_pull_request(
                source_branch=target_config["source_branch"],
                target_branch=target_config["target_branch"],
                title=review_context["title"],
                body=review_context["description"],
                reviewers=target_config["reviewers"]
            )
            
            # Attach review metadata and labels
            api_client.add_labels(pr_response["id"], review_context.get("labels", []))
            
            return {
                "success": True,
                "platform": platform,
                "pr_url": pr_response["url"],
                "reviewers_notified": target_config["reviewers"],
                "attempts": attempt + 1,
                "latency_ms": _calculate_latency()
            }
            
        except RateLimitError as e:
            if attempt == max_retries:
                return _fallback_to_draft_pr(target_config, review_context)
            time.sleep(2 ** attempt)
            
        except PermissionError as e:
            raise ReviewRequestError(
                f"Insufficient permissions for {platform}: {str(e)}"
            ) from e
            
    raise ReviewRequestError(
        f"Failed to create review request 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:

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 |
|---|---|
| `pr-writer` | Complements code review requests with PR writing best practices for structured submissions |
| `receiving-code-review` | The counterpart skill — after getting feedback, load this to learn how to respond and iterate |

---

## 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 domain. The model follows markdown links at load time to resolve external references and inline content.

- [Google Engineering Practices: Code Review](https://google.github.io/eng-practices/review/) — Google's comprehensive guide to requesting, preparing for, and conducting code reviews
- [Microsoft: Pull Request Etiquette](https://learn.microsoft.com/en-us/devops/develop/cpp/code-review) — Microsoft's documentation on effective pull request practices and reviewer expectations
- [GitHub: About Pull Requests](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/about-pull-requests) — Official GitHub reference for understanding PR workflows and requesting reviews
- [Effective Code Review Request Templates (Stripe)](https://stripe.com/blog/code-review-at-stripe) — Stripe's engineering blog on structuring review requests with context, scope, and checklists
- [Code Review Culture Guide (ThoughtWorks)](https://www.thoughtworks.com/radar/tools/code-review-culture) — ThoughtWorks Radar article on building a healthy code review culture in teams