Skip to main content
Alison Aquinas logoAlison's LLM Skills Marketplace

claude-agent-test-drive

Included in skill bundleshared-skillsView on GitHub ↗

Files

SKILL.mdagentsreferences

Install

Install only this skill with npx skills
npx skills add alisonaquinas/llm-shared-skills --skill 'claude-agent-test-drive' -g -y
Install the containing skill bundle
/plugin install shared-skills@llm-skills
Download claude-agent-test-drive-skill.zip
This skill is bundled inside shared-skills. Use npx skills when you only want this skill, or install the bundle once to make every included skill available through the plugin marketplace flow. Browse the full skill bundle repository at github.com/alisonaquinas/llm-shared-skills.

Invoke

Invoke this skill after installation
/shared-skills:claude-agent-test-drive

SKILL.md


name: claude-agent-test-drive description: > Test Drive phase for delegated agent workflow development. Use when planning, designing, building, testing, validating, or refining a delegated agent workflow as it moves through a full delivery lifecycle. Triggers include drafting the agent orchestration spec, locking contracts, wiring runtime placement, scoring quality, running live scenarios, or choosing the right re-entry point after a failure.

Agent Test Drive

Run realistic scenarios end to end and capture friction, surprises, and missing guidance.

Intent Router

Load reference files on demand only when the corresponding topic is active:

  • references/scenario-matrix.md — Load when designing live agent delegation scenarios and friction review

Quick Start

[ ] Capture the current agent orchestration spec
[ ] Complete the required outputs for this phase
[ ] Record evidence for the gate
[ ] Hand off the evidence to the next phase

Phase Workflow

Start from the current agent orchestration spec and tighten only the decisions owned by this phase. Work forward until the gate is satisfied, then hand the evidence to the next phase in the family. Keep the workflow description portable even when the runtime wiring is specific to one environment.

Example Evidence

| Scenario | Outcome | Friction | Follow-up |
|---|---|---|---|
| Happy path | PASS | None | Keep |
| Variant | PARTIAL | Missing ownership example | Add example |
| Recovery | FAIL | Escalation policy unclear | Tighten docs |

Gate

Test drive is complete when at least five scenarios were attempted, at least three passed, and a friction report was written.

Safety Notes

Record blocked and partial results instead of collapsing them into success. They reveal the next iteration target.

Resource Index

Reference FileLoad When
references/scenario-matrix.mdLoad when designing live agent delegation scenarios and friction review
← Back to marketplace