gsd-verify-work
Perform interactive UAT on new features to confirm they meet requirements.
Install
mkdir -p .claude/skills/gsd-verify-work && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12662" && unzip -o skill.zip -d .claude/skills/gsd-verify-work && rm skill.zipInstalls to .claude/skills/gsd-verify-work
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Validate built features through conversational UATKey capabilities
- →Validate built features through conversational testing
- →Confirm what the agent built actually works from user's perspective
- →Diagnose issues when found
- →Plan fixes for identified issues
- →Prepare for execution of fix plans
How it works
The skill invokes a verify-work workflow, translating Claude Code syntax for user questions and tasks into Codex collaboration tools, and manages conversational testing with persistent state.
Inputs & outputs
When to use gsd-verify-work
- →Verifying a newly completed feature
- →Running UAT for a new UI component
- →Confirming expected behavior for a bug fix
About gsd-verify-work
Facilitates UAT by engaging the user in a conversation to verify specific feature implementations against the plan, ensuring alignment between intent and build.
Validate built features through conversational UAT
When not to use it
- →When multi-select input is required from the user
- →When inline model selection is needed for tasks
- →When testing multiple features simultaneously without conversational UAT
Limitations
- →Codex has no multiSelect functionality
- →Model selection is per-role config, not inline
- →Only one test is conducted at a time
How it compares
This workflow conducts conversational user acceptance testing one test at a time with plain text responses, rather than relying on manual, unstructured testing.
Compared to similar skills
gsd-verify-work side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| gsd-verify-work (this skill) | 0 | 7mo | No flags | Intermediate |
| webapp-testing | 353 | 7mo | Review | Intermediate |
| ui-ux-expert-skill | 91 | 1y | Review | Advanced |
| skill-creator | 128 | 7mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
webapp-testing
anthropics
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
ui-ux-expert-skill
fercracix33
Technical workflow for implementing accessible React user interfaces with shadcn/ui, Tailwind CSS, and TanStack Query. Includes 6-phase process with mandatory Style Guide compliance, Context7 best practices consultation, Chrome DevTools validation, and WCAG 2.1 AA accessibility standards. Use after Test Agent, Implementer, and Supabase agents complete their work.
skill-creator
anthropics
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
python-testing-patterns
wshobson
Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.
dependency-upgrade
wshobson
Manage major dependency version upgrades with compatibility analysis, staged rollout, and comprehensive testing. Use when upgrading framework versions, updating major dependencies, or managing breaking changes in libraries.
playwright-mcp
sfc-gh-dflippo
Browser testing, web scraping, and UI validation using Playwright MCP. Use this skill when you need to test Streamlit apps, validate web interfaces, test responsive design, check accessibility, or automate browser interactions through MCP tools.