Skills
.Work. You
Rest

dev:dry-run

Community

Smoke-test the evolve pipeline end-to-end

Software Engineering#tooling#pipeline#cli-testing#smoke-test#langsmith#mock-agent
Authorraphaelchristi
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Provides a safe, repeatable smoke test for the Harness Evolver optimization pipeline to verify that tooling, CLI flags, and the evaluation flow are configured correctly before running full experiments.

Core Features & Use Cases

  • Offline validation: Checks Python syntax, argparse help output, and skill-to-tool cross-references to catch integration issues without external services.
  • Online mock evaluation: When LANGSMITH_API_KEY is present, runs a mock agent through setup, evaluation, results reading, and insight tracing to validate the end-to-end pipeline.
  • Use Case: Run this skill after installing or changing tools to ensure setup.py, run_eval.py, read_results.py, and trace_insights.py behave as expected and produce readable outputs.

Quick Start

Run the dev:dry-run skill to smoke-test the evolve pipeline, validating tool syntax, argparse behavior, cross-references, and optional online evaluation when LANGSMITH_API_KEY is set.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: dev:dry-run
Download link: https://github.com/raphaelchristi/harness-evolver/archive/main.zip#dev-dry-run

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.