Name: Verify Features via Conversational UAT
Author: Skills Guide Bot

Automated summary

This skill runs a conversational user-acceptance test pass over already-built features, one test at a time, recording results in a persistent {phase_num}-UAT.md tracker.

Strengths

Asks one test question at a time in plain text, with no interrogation, so a UAT pass moves quickly
Keeps persistent state in UAT.md, including session management and the ability to resume later
On failure, it automatically diagnoses the gap, plans fixes, and prepares them for execution
Finishes with a Next Up block pointing to /gsd:complete-milestone, /gsd:plan-phase --gaps, or /gsd:next

Limitations

Assumes features are already built: it is guided manual validation, not automated testing
Tied to the GSD ecosystem (workflows, UAT.md template, HANDOFF.json, CLAUDE_PLUGIN_ROOT), so it is hard to reuse outside that plugin
Coverage depends entirely on the user's answers; no automated test coverage is guaranteed

When to use it

Use it after a GSD phase has been executed to confirm from the user's perspective that what was built actually works.

When not to use it

Avoid it when you need automated tests or CI coverage, or when the phase's features have not been implemented yet.

Security analysis

Caution

Quality score82/100

No destructive, exfiltration, or obfuscated instructions are present, and the declared tools serve a legitimate UAT/fix-planning purpose. However, Bash/Edit/Write/Task are powerful, and the referenced workflow/template files are not shown, so listing warrants caution rather than a clean safe rating.

Findings

•Declares Bash, Edit, Write, and Task tools, enabling command execution and file modification during verification and fix planning.
•Core behavior is delegated to external files (workflows/verify-work.md, templates/UAT.md, references/continuation-format.md) not included in the SKILL.md, so exact commands and safety controls cannot be audited from this content.
•Workflow may automatically diagnose gaps and prepare fix plans for execution, which could lead to unintended code changes if run without review.

How this analysis is made

Examples

Verify phase 4

/gsd:verify-work 4

Resume an interrupted UAT

/gsd:verify-work — continue the UAT session we left off in, pick up at the next untested item

Continue without a phase

/gsd:verify-work

name: gsd:verify-work description: Validate built features through conversational UAT argument-hint: "[phase number, e.g., '4']" allowed-tools:

Read
Bash
Glob
Grep
Edit
Write
Task

<objective> Validate built features through conversational testing with persistent state.

Purpose: Confirm what Claude built actually works from user's perspective. One test at a time, plain text responses, no interrogation. When issues are found, automatically diagnose, plan fixes, and prepare for execution.

Output: {phase_num}-UAT.md tracking all test results. If issues found: diagnosed gaps, verified fix plans ready for /gsd:execute-phase </objective>

<execution_context> @${CLAUDE_PLUGIN_ROOT}/workflows/verify-work.md @${CLAUDE_PLUGIN_ROOT}/templates/UAT.md </execution_context>

<context> Phase: $ARGUMENTS (optional) - If provided: Test specific phase (e.g., "4") - If not provided: Check for active sessions or prompt for phase

Context files are resolved inside the workflow (init verify-work) and delegated via <files_to_read> blocks. </context>

<process> Execute the verify-work workflow from @${CLAUDE_PLUGIN_ROOT}/workflows/verify-work.md end-to-end. Preserve all workflow gates (session management, test presentation, diagnosis, fix planning, routing). </process>

<output_format> When this workflow concludes (verification passed or routed to gap closure), emit a Next Up continuation block following the pattern in references/continuation-format.md:

Show verification status (e.g., ## ✓ Verification Passed or ## ⚠ Gaps Found — Routing to Plan with details)
Emit a ## ▶ Next Up heading with the next likely command (/gsd:complete-milestone if all phases verified, /gsd:plan-phase --gaps if gaps found, /gsd:next if unsure)
Use `/clear` then: before the command
Include a parenthetical: (/clear is safe — /gsd:resume-work restores position from HANDOFF.json if you change your mind)
Add an "Also available:" section with 1-3 alternatives where relevant

Verification accumulates lots of test/UAT prose that won't help downstream; phase-end is a clean boundary for /clear. </output_format>

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/verify-features-via-conversational-uat-mrwakb94/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/verify-features-via-conversational-uat-mrwakb94' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/verify-features-via-conversational-uat-mrwakb94/download' --output '.skill-downloads/verify-features-via-conversational-uat-mrwakb94/SKILL.md.part' && mv '.skill-downloads/verify-features-via-conversational-uat-mrwakb94/SKILL.md.part' '.skill-downloads/verify-features-via-conversational-uat-mrwakb94/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/verify-features-via-conversational-uat-mrwakb94/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.