AGENT SKILL

test-case-design-expert

Use when the user wants comprehensive user-facing end-to-end test scenarios for a feature description.

License 许可
MIT
所属仓库
xhd2015/agent-pro
最近更新
2026-11-12
Stars
★ 1
Forks
0

01 前言 Front Matter

name
test-case-design-expert
description
Use when the user wants comprehensive user-facing end-to-end test scenarios for a feature description.

02 资源文件 7

03 SKILL.md 正文

Design user-facing end-to-end test cases for a feature. Follow these steps:

  1. Brainstorm — Expand the feature considering core functionality, user roles, integration points, error states, and edge conditions.

  2. Clarify — If details are ambiguous, batch all questions and call add-pending-questions with JSON arguments. Each argument has a question field and optional options array. After calling it, stop and wait for answers. Only ask questions that affect test design.

  3. Design Test Cases — For each test case, include:

    • Scenario: what the user does (the user-facing story)
    • Steps: concrete, reproducible steps
    • Expected: what should happen

    Cover happy path, common edge cases, error states, and boundary conditions. Be specific and concrete.

Output to a markdown file with an auto-derived UPPER_CASE slug name (e.g. FEATURE-TEST-DESIGN.md). The report must include the original feature request, all clarifications and answers, the expanded feature plan, and all test cases.

04 同仓库更多 Skills

xhd2015
xhd2015/agent-pro

verify-with-prototype

Prototype-before-production workflow for risky host integrations (sudo, privileges, system config). Use when a feature touches the real OS, when behavior must be proven with a small script before full implementation, or when the user mentions prototype verification, POC script, or verify-with-prototype. Run after investigate/followup and before doctest-TDD integration.

★ 1
xhd2015
xhd2015/agent-pro

verify-on-behalf-of-user

Run human-style scenario verification after an agent claims work is done: git status, build into ~/.sandbox/bin (default sandbox mode) or opt-in host mode (outside sandbox: wrk --reinstall-local / change-scoped install), real integration/E2E scenarios (start servers, browser-agent for UI), always-labeled depth, markdown transcript written and inlined for review. Use for "verify on my behalf", before commit. Complements doctests; does not replace them. Load a sub-topic with: agent-pro skill --show verify-on-behalf-of-user/<topic>

★ 1
xhd2015
xhd2015/agent-pro

test-case-tree-design-expert

Use when the user wants a decision-tree style test case design with inherited setup and per-leaf assertions.

★ 1
xhd2015
xhd2015/agent-pro

tdd-expert

Use when the user has a test-case-tree output and wants runnable Go tests plus stub implementation following Test-Driven Development.

★ 1
xhd2015
xhd2015/agent-pro

summarize-a-skill

Meta-skill: distill durable high-signal guidance (worked vs failed, wrong → correct, and anything else that quickens future similar tasks) into a brief reusable skill document with YAML frontmatter. When the user does not explicitly ask for a new skill/file, prefer updating an existing skill over creating one. Writes skills/<name>/SKILL.md (or docs|doc/skills/…). Use for /summarize-a-skill, "summarize what worked", "lessons learned into a skill", or "write a skill from this session".

★ 1
xhd2015
xhd2015/agent-pro

split-phases

Break a large implementation plan into dependency-ordered phases that are independently implementable and verifiable. Use when the user runs /split-phases, or says "split into phases", "phase this plan", "break into units of work", "dependency-ordered milestones", or wants a giant plan split for phase-by-phase work.

★ 1