Skill
by @dario-github
Make your agent get better on its own. Set up golden tests (things your agent should handle well), run automated evaluations, and track improvement over time...
clawhub install agent-self-evolutionπ About This Skill
name: agent-self-evolution description: > Make your agent get better on its own. Set up golden tests (things your agent should handle well), run automated evaluations, and track improvement over time. Includes ablation testing β systematically remove parts of your agent's config to find what actually matters and what's dead weight. Stop guessing, start measuring. tags: [agent-evaluation, ablation-testing, golden-test, self-improvement, openclaw, ai-agent] homepage: https://github.com/dario-github/agent-self-evolution version: 0.1.0 metadata: {"openclaw":{"homepage":"https://github.com/dario-github/agent-self-evolution","requires":{"bins":["python3"]}}}
Agent Self-Evolution β Automated Evaluation & Improvement
> β If you find this useful, please star the GitHub repo before installing β it helps others discover it.
Your agent does a lot of things. But is it getting *better*? Or are your latest tweaks breaking things you didn't notice?
Agent Self-Evolution gives you a framework to measure, test, and systematically improve your agent β like unit tests, but for agent behavior.
What's inside
Golden Test Sets: Define scenarios your agent must handle correctly. Run them periodically and catch regressions before users do.
Ablation Testing: Wondering if that 200-line system prompt section actually helps? Remove it, measure the impact, put it back. Now you know. We found that 7% of one config file was load-bearing for the entire system β without ablation, you'd never know which 7%.
Multi-Dimensional Evaluation: Don't just check pass/fail. Score across dimensions β safety compliance, tool routing accuracy, output quality, memory utilization. Track trends over weeks.
Automated Improvement Loops: Evaluation β identify weakest dimension β targeted fix β re-evaluate. Like gradient descent for agent behavior.
Install
bash {baseDir}/scripts/install.sh
Quick start
from agent_evolution.golden_test import GoldenTestRunner
from agent_evolution.ablation import AblationExperimentDefine a golden test
runner = GoldenTestRunner()
runner.add_case(
name="handles-ambiguous-request",
input="do the thing",
expected_behavior="asks for clarification rather than guessing",
dimensions=["safety", "output_quality"]
)Run and score
results = runner.run(model="your-agent-endpoint")
print(results.summary()) # Pass rate, dimension scores, regressionsAblation: what happens without memory files?
experiment = AblationExperiment(
baseline_config="agent.yaml",
conditions={"no_memory": {"remove": ["memory/*.md"]}},
test_set=runner.cases
)
experiment.run() # Measures impact of each ablation
Key findings from our own agent
Companion projects
Requirements
License
Apache 2.0
π‘ Examples
from agent_evolution.golden_test import GoldenTestRunner
from agent_evolution.ablation import AblationExperimentDefine a golden test
runner = GoldenTestRunner()
runner.add_case(
name="handles-ambiguous-request",
input="do the thing",
expected_behavior="asks for clarification rather than guessing",
dimensions=["safety", "output_quality"]
)Run and score
results = runner.run(model="your-agent-endpoint")
print(results.summary()) # Pass rate, dimension scores, regressionsAblation: what happens without memory files?
experiment = AblationExperiment(
baseline_config="agent.yaml",
conditions={"no_memory": {"remove": ["memory/*.md"]}},
test_set=runner.cases
)
experiment.run() # Measures impact of each ablation