Tracks UAT status across the entire project for verification and sign-off.

Install

mkdir -p .claude/skills/gsd-audit-uat-gustavosareto && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12872" && unzip -o skill.zip -d .claude/skills/gsd-audit-uat-gustavosareto && rm skill.zip

Installs to .claude/skills/gsd-audit-uat-gustavosareto

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.

Cross-phase audit of all outstanding UAT and verification items
63 charsno explicit “when” trigger
Intermediate

Key capabilities

  • Scan phases for pending UAT items
  • Scan phases for skipped UAT items
  • Scan phases for blocked UAT items
  • Scan phases for human_needed UAT items
  • Cross-reference against codebase for stale documentation
  • Produce prioritized human test plan

How it works

This skill scans all project phases for outstanding UAT and verification items, cross-references them against the codebase to detect stale documentation, and then produces a prioritized human test plan.

Inputs & outputs

You give it
GSD_ARGS (empty)
You get back
prioritized human test plan

When to use gsd-audit-uat

  • Audit UAT status
  • Check verification backlog
  • Verify sign-off items
  • Review project compliance

About this skill

<codex_skill_adapter>

A. Skill Invocation

  • This skill is invoked by mentioning $gsd-audit-uat.
  • Treat all user text after $gsd-audit-uat as {{GSD_ARGS}}.
  • If no arguments are present, treat {{GSD_ARGS}} as empty.

B. AskUserQuestion → request_user_input Mapping

GSD workflows use AskUserQuestion (Claude Code syntax). Translate to Codex request_user_input:

Parameter mapping:

  • headerheader
  • questionquestion
  • Options formatted as "Label" — description{label: "Label", description: "description"}
  • Generate id from header: lowercase, replace spaces with underscores

Batched calls:

  • AskUserQuestion([q1, q2]) → single request_user_input with multiple entries in questions[]

Multi-select workaround:

  • Codex has no multiSelect. Use sequential single-selects, or present a numbered freeform list asking the user to enter comma-separated numbers.

Execute mode fallback:

  • When request_user_input is rejected (Execute mode), present a plain-text numbered list and pick a reasonable default.

C. Task() → spawn_agent Mapping

GSD workflows use Task(...) (Claude Code syntax). Translate to Codex collaboration tools:

Direct mapping:

  • Task(subagent_type="X", prompt="Y")spawn_agent(agent_type="X", message="Y")
  • Task(model="...") → omit (Codex uses per-role config, not inline model selection)
  • fork_context: false by default — GSD agents load their own context via <files_to_read> blocks

Parallel fan-out:

  • Spawn multiple agents → collect agent IDs → wait(ids) for all to complete

Result parsing:

  • Look for structured markers in agent output: CHECKPOINT, PLAN COMPLETE, SUMMARY, etc.
  • close_agent(id) after collecting results from each agent </codex_skill_adapter>
<objective> Scan all phases for pending, skipped, blocked, and human_needed UAT items. Cross-reference against codebase to detect stale documentation. Produce prioritized human test plan. </objective>

<execution_context> @C:/Users/gusta/OneDrive/Documentos/gerenciador-de-quadras/.codex/get-shit-done/workflows/audit-uat.md </execution_context>

<context> Core planning files are loaded in-workflow via CLI.

Scope: Glob: .planning/phases//-UAT.md Glob: .planning/phases//-VERIFICATION.md </context>

When not to use it

  • When not auditing outstanding UAT items
  • When not verifying items across phases
  • When not needing a human test plan

Limitations

  • Limited to UAT and verification items
  • Scope is limited to `.planning/phases/*/*-UAT.md` and `.planning/phases/*/*-VERIFICATION.md`
  • Requires core planning files to be loaded in-workflow via CLI

How it compares

This workflow provides a structured, cross-phase audit of UAT items, integrating codebase checks for documentation staleness, which a manual UAT review might not systematically include.

Compared to similar skills

gsd-audit-uat side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
gsd-audit-uat (this skill)04moNo flagsIntermediate
empirical-validation14moReviewBeginner
linear-ci-integration125dCautionIntermediate
work-on-issue06moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry