Files
msd-core/get-shit-done/workflows/audit-uat.md
Quang Do d4767ac2e0 fix: replace /gsd: slash command format with /gsd- skill format in all user-facing content (#1579)
* fix: replace /gsd: command format with /gsd- skill format in all suggestions

All next-step suggestions shown to users were still using the old colon
format (/gsd:xxx) which cannot be copy-pasted as skills. Migrated all
occurrences across agents/, commands/, get-shit-done/, docs/, README files,
bin/install.js (hardcoded defaults for claude runtime), and
get-shit-done/bin/lib/*.cjs (generate-claude-md templates and error messages).
Updated tests to assert new hyphen format instead of old colon format.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix: migrate remaining /gsd: format to /gsd- in hooks, workflows, and sdk

Addresses remaining user-facing occurrences missed in the initial migration:

- hooks/: fix 4 user-facing messages (pause-work, update, fast, quick)
  and 2 comments in gsd-workflow-guard.js
- get-shit-done/workflows/: fix 21 Skill() literal calls that Claude
  executes directly (installer does not transform workflow content)
- sdk/prompt-sanitizer.ts: update regex to strip /gsd- format in addition
  to legacy /gsd: format; update JSDoc comment
- tests/: update autonomous-ui-steps, prompt-sanitizer to assert new format

Note: commands/gsd/*.md frontmatter (name: gsd:xxx) intentionally unchanged
— installer derives skillName from directory path, not the name field.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(plan-phase): preserve --chain flag in auto-advance sync and handle ui-phase gate in chain mode

Bug 1: step 15 sync-flag check only guarded against --auto, causing
_auto_chain_active to be cleared when plan-phase is invoked without
--auto in ARGUMENTS even though a --chain pipeline was active. Added
--chain to the guard condition, matching discuss-phase behaviour.

Bug 2: UI Design Contract gate (step 5.6) always exited the workflow
when UI-SPEC was missing, breaking the discuss --chain pipeline
silently. When _auto_chain_active is true, the gate now auto-invokes
gsd-ui-phase --auto via Skill() and continues to step 6 without
prompting. Manual invocations retain the existing AskUserQuestion flow.

* fix: remove <sub>/clear</sub> pattern and duplicate old-format command in discuss-phase.md

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-04 07:24:31 -04:00

2.9 KiB

Cross-phase audit of all UAT and verification files. Finds every outstanding item (pending, skipped, blocked, human_needed), optionally verifies against the codebase to detect stale docs, and produces a prioritized human test plan. Run the CLI audit:
AUDIT=$(node "$HOME/.claude/get-shit-done/bin/gsd-tools.cjs" audit-uat --raw)

Parse JSON for results array and summary object.

If summary.total_items is 0:

## All Clear

No outstanding UAT or verification items found across all phases.
All tests are passing, resolved, or diagnosed with fix plans.

Stop here.

Group items by what's actionable NOW vs. what needs prerequisites:

Testable Now (no external dependencies):

  • pending — tests never run
  • human_uat — human verification items
  • skipped_unresolved — skipped without clear blocking reason

Needs Prerequisites:

  • server_blocked — needs external server running
  • device_needed — needs physical device (not simulator)
  • build_needed — needs release/preview build
  • third_party — needs external service configuration

For each item in "Testable Now", use Grep/Read to check if the underlying feature still exists in the codebase:

  • If the test references a component/function that no longer exists → mark as stale
  • If the test references code that has been significantly rewritten → mark as needs_update
  • Otherwise → mark as active
Present the audit report:
## UAT Audit Report

**{total_items} outstanding items across {total_files} files in {phase_count} phases**

### Testable Now ({count})

| # | Phase | Test | Description | Status |
|---|-------|------|-------------|--------|
| 1 | {phase} | {test_name} | {expected} | {active/stale/needs_update} |
...

### Needs Prerequisites ({count})

| # | Phase | Test | Blocked By | Description |
|---|-------|------|------------|-------------|
| 1 | {phase} | {test_name} | {category} | {expected} |
...

### Stale (can be closed) ({count})

| # | Phase | Test | Why Stale |
|---|-------|------|-----------|
| 1 | {phase} | {test_name} | {reason} |
...

---

## Recommended Actions

1. **Close stale items:** `/gsd-verify-work {phase}` — mark stale tests as resolved
2. **Run active tests:** Human UAT test plan below
3. **When prerequisites met:** Retest blocked items with `/gsd-verify-work {phase}`
Generate a human UAT test plan for "Testable Now" + "active" items only:

Group by what can be tested together (same screen, same feature, same prerequisite):

## Human UAT Test Plan

### Group 1: {category — e.g., "Billing Flow"}
Prerequisites: {what needs to be running/configured}

1. **{Test name}** (Phase {N})
   - Navigate to: {where}
   - Do: {action}
   - Expected: {expected behavior}

2. **{Test name}** (Phase {N})
   ...

### Group 2: {category}
...