From orchestrator-plugin
Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality
How this skill is triggered — by the user, by Claude, or both
Slash command
/orchestrator-plugin:agentic-evalThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Patterns for self-improvement through iterative evaluation and refinement.
Patterns for self-improvement through iterative evaluation and refinement.
Evaluation patterns enable agents to assess and improve their own outputs, moving beyond single-shot generation to iterative refinement loops.
Generate → Evaluate → Critique → Refine → Output
↑ │
└──────────────────────────────┘
Agent evaluates and improves its own output through self-critique.
def reflect_and_refine(task: str, criteria: list[str], max_iterations: int = 3) -> str:
"""Generate with reflection loop."""
output = llm(f"Complete this task:\n{task}")
for i in range(max_iterations):
# Self-critique
critique = llm(f"""
Evaluate this output against criteria: {criteria}
Output: {output}
Rate each: PASS/FAIL with feedback as JSON.
""")
critique_data = json.loads(critique)
all_pass = all(c["status"] == "PASS" for c in critique_data.values())
if all_pass:
return output
# Refine based on critique
failed = {k: v["feedback"] for k, v in critique_data.items() if v["status"] == "FAIL"}
output = llm(f"Improve to address: {failed}\nOriginal: {output}")
return output
Key insight: Use structured JSON output for reliable parsing of critique results.
Separate generation and evaluation into distinct components for clearer responsibilities.
class EvaluatorOptimizer:
def __init__(self, score_threshold: float = 0.8):
self.score_threshold = score_threshold
def generate(self, task: str) -> str:
return llm(f"Complete: {task}")
def evaluate(self, output: str, task: str) -> dict:
return json.loads(llm(f"""
Evaluate output for task: {task}
Output: {output}
Return JSON: {{"overall_score": 0-1, "dimensions": {{"accuracy": ..., "clarity": ...}}}}
"""))
def optimize(self, output: str, feedback: dict) -> str:
return llm(f"Improve based on feedback: {feedback}\nOutput: {output}")
def run(self, task: str, max_iterations: int = 3) -> str:
output = self.generate(task)
for _ in range(max_iterations):
evaluation = self.evaluate(output, task)
if evaluation["overall_score"] >= self.score_threshold:
break
output = self.optimize(output, evaluation)
return output
Test-driven refinement loop for code generation.
class CodeReflector:
def reflect_and_fix(self, spec: str, max_iterations: int = 3) -> str:
code = llm(f"Write Python code for: {spec}")
tests = llm(f"Generate pytest tests for: {spec}\nCode: {code}")
for _ in range(max_iterations):
result = run_tests(code, tests)
if result["success"]:
return code
code = llm(f"Fix error: {result['error']}\nCode: {code}")
return code
Evaluate whether output achieves the expected result.
def evaluate_outcome(task: str, output: str, expected: str) -> str:
return llm(f"Does output achieve expected outcome? Task: {task}, Expected: {expected}, Output: {output}")
Use LLM to compare and rank outputs.
def llm_judge(output_a: str, output_b: str, criteria: str) -> str:
return llm(f"Compare outputs A and B for {criteria}. Which is better and why?")
Score outputs against weighted dimensions.
RUBRIC = {
"accuracy": {"weight": 0.4},
"clarity": {"weight": 0.3},
"completeness": {"weight": 0.3}
}
def evaluate_with_rubric(output: str, rubric: dict) -> float:
scores = json.loads(llm(f"Rate 1-5 for each dimension: {list(rubric.keys())}\nOutput: {output}"))
return sum(scores[d] * rubric[d]["weight"] for d in rubric) / 5
| Practice | Rationale |
|---|---|
| Clear criteria | Define specific, measurable evaluation criteria upfront |
| Iteration limits | Set max iterations (3-5) to prevent infinite loops |
| Convergence check | Stop if output score isn't improving between iterations |
| Log history | Keep full trajectory for debugging and analysis |
| Structured output | Use JSON for reliable parsing of evaluation results |
## Evaluation Implementation Checklist
### Setup
- [ ] Define evaluation criteria/rubric
- [ ] Set score threshold for "good enough"
- [ ] Configure max iterations (default: 3)
### Implementation
- [ ] Implement generate() function
- [ ] Implement evaluate() function with structured output
- [ ] Implement optimize() function
- [ ] Wire up the refinement loop
### Safety
- [ ] Add convergence detection
- [ ] Log all iterations for debugging
- [ ] Handle evaluation parse failures gracefully
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub mapengbo0314/e2g --plugin orchestrator-plugin