@codewizard-dt/bootstrap 2.10.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.github/workflows/build.yml +88 -0
- package/.github/workflows/security.yml +24 -0
- package/.gitleaks.toml +15 -0
- package/README.md +472 -0
- package/bin/cli.js +47 -0
- package/lib/README.md +27 -0
- package/lib/hooks/README.md +316 -0
- package/lib/hooks/env-file-guard.js +45 -0
- package/lib/hooks/git-protected-ops-block.js +77 -0
- package/lib/hooks/lib/serena-languages.js +158 -0
- package/lib/hooks/lib/serena.js +787 -0
- package/lib/hooks/mv-absolute-path-block.js +53 -0
- package/lib/hooks/serena-bash-grep-block.js +501 -0
- package/lib/hooks/serena-edit-guard.js +74 -0
- package/lib/hooks/serena-first-glob-guard.js +94 -0
- package/lib/hooks/serena-first-guard.js +74 -0
- package/lib/hooks/serena-first-read-guard.js +167 -0
- package/lib/hooks/serena-pre-delegation.js +117 -0
- package/lib/hooks/serena-session-reset.js +45 -0
- package/lib/hooks/serena-usage-tracker.js +186 -0
- package/lib/hooks/serena-write-guard.js +58 -0
- package/lib/prompts/README.md +16 -0
- package/lib/prompts/migrate-wiki.md +111 -0
- package/lib/prompts/setup-deployment.md +322 -0
- package/lib/prompts/setup-design-system.md +162 -0
- package/lib/prompts/setup-strict-typechecks.md +139 -0
- package/lib/scripts/README.md +49 -0
- package/lib/scripts/bootstrap-serena.sh +145 -0
- package/lib/scripts/build-mcp-guide.sh +108 -0
- package/lib/scripts/install-global.sh +78 -0
- package/lib/scripts/install-mcps.sh +131 -0
- package/lib/scripts/lib.sh +154 -0
- package/lib/scripts/merge-gitignore.sh +65 -0
- package/lib/scripts/migrate-project.sh +273 -0
- package/lib/scripts/setup-deployment.sh +104 -0
- package/lib/scripts/setup-project.sh +55 -0
- package/lib/scripts/setup-runner.sh +99 -0
- package/lib/scripts/setup-strict-typechecks.sh +29 -0
- package/lib/scripts/startup.sh +42 -0
- package/lib/scripts/sync-wiki-scaffold.sh +104 -0
- package/lib/scripts/templates/CLAUDE-env-safety.md +3 -0
- package/lib/scripts/templates/CLAUDE-wiki.md +60 -0
- package/lib/scripts/templates/gitignore +136 -0
- package/lib/scripts/templates/guides/stubs/00-header.md +15 -0
- package/lib/scripts/templates/guides/stubs/brave-search.md +20 -0
- package/lib/scripts/templates/guides/stubs/context7.md +26 -0
- package/lib/scripts/templates/guides/stubs/playwright.md +26 -0
- package/lib/scripts/templates/guides/stubs/serena.md +219 -0
- package/lib/scripts/templates/wiki/conventions.md +100 -0
- package/lib/scripts/templates/wiki/dashboard.html +1733 -0
- package/lib/scripts/templates/wiki/hot.md +21 -0
- package/lib/scripts/templates/wiki/index.md +46 -0
- package/lib/scripts/templates/wiki/knowledge/concepts/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/entities/components/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/entities/organisations/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/entities/people/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/entities/tools/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/knowledge/sources/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/log.md +14 -0
- package/lib/scripts/templates/wiki/work/bugs/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/bugs/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/bugs/index.md +12 -0
- package/lib/scripts/templates/wiki/work/bugs/lifecycle.md +39 -0
- package/lib/scripts/templates/wiki/work/decisions/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/decisions/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/decisions/index.md +12 -0
- package/lib/scripts/templates/wiki/work/decisions/lifecycle.md +42 -0
- package/lib/scripts/templates/wiki/work/requirements/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/requirements/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/requirements/index.md +12 -0
- package/lib/scripts/templates/wiki/work/requirements/lifecycle.md +34 -0
- package/lib/scripts/templates/wiki/work/roadmaps/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/roadmaps/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/roadmaps/index.md +12 -0
- package/lib/scripts/templates/wiki/work/roadmaps/lifecycle.md +32 -0
- package/lib/scripts/templates/wiki/work/tasks/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/tasks/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/tasks/index.md +12 -0
- package/lib/scripts/templates/wiki/work/tasks/lifecycle.md +39 -0
- package/lib/scripts/templates/wiki/work/uat/.gitkeep +0 -0
- package/lib/scripts/templates/wiki/work/uat/archive/index.md +6 -0
- package/lib/scripts/templates/wiki/work/uat/index.md +12 -0
- package/lib/scripts/templates/wiki/work/uat/lifecycle.md +48 -0
- package/lib/scripts/templates/wiki/work/uat/screenshots/.gitkeep +0 -0
- package/lib/scripts/update-project.sh +75 -0
- package/lib/scripts/wiki-dashboard-server.js +146 -0
- package/lib/skills/README.md +146 -0
- package/lib/skills/anti-slop/SKILL.md +183 -0
- package/lib/skills/bug-close/SKILL.md +136 -0
- package/lib/skills/bug-file/SKILL.md +114 -0
- package/lib/skills/bug-triage/SKILL.md +140 -0
- package/lib/skills/company-align/SKILL.md +203 -0
- package/lib/skills/debug-logs/SKILL.md +129 -0
- package/lib/skills/decision-create/SKILL.md +220 -0
- package/lib/skills/decision-finalize/SKILL.md +181 -0
- package/lib/skills/decision-next/SKILL.md +129 -0
- package/lib/skills/decision-walkthrough/SKILL.md +169 -0
- package/lib/skills/demo/SKILL.md +183 -0
- package/lib/skills/elevator-pitch/SKILL.md +125 -0
- package/lib/skills/eval-create/SKILL.md +344 -0
- package/lib/skills/eval-gap/SKILL.md +150 -0
- package/lib/skills/eval-run/SKILL.md +214 -0
- package/lib/skills/extract-feature/SKILL.md +344 -0
- package/lib/skills/flashcard/SKILL.md +513 -0
- package/lib/skills/frontend-taste/SKILL.md +184 -0
- package/lib/skills/gap-assess/SKILL.md +97 -0
- package/lib/skills/git-commit/SKILL.md +164 -0
- package/lib/skills/lint/SKILL.md +99 -0
- package/lib/skills/marp-slideshow/SKILL.md +212 -0
- package/lib/skills/mermaid-flowchart/SKILL.md +194 -0
- package/lib/skills/now/SKILL.md +36 -0
- package/lib/skills/port-feature/SKILL.md +315 -0
- package/lib/skills/power-mode/SKILL.md +184 -0
- package/lib/skills/primer/SKILL.md +84 -0
- package/lib/skills/project-readme/SKILL.md +166 -0
- package/lib/skills/req-compile/SKILL.md +131 -0
- package/lib/skills/req-create/SKILL.md +124 -0
- package/lib/skills/req-extract-decisions/SKILL.md +241 -0
- package/lib/skills/req-finalize/SKILL.md +251 -0
- package/lib/skills/req-retire/SKILL.md +185 -0
- package/lib/skills/req-update/SKILL.md +265 -0
- package/lib/skills/research/SKILL.md +250 -0
- package/lib/skills/research-company/SKILL.md +345 -0
- package/lib/skills/roadmap-add/SKILL.md +238 -0
- package/lib/skills/roadmap-create/SKILL.md +223 -0
- package/lib/skills/roadmap-next/SKILL.md +132 -0
- package/lib/skills/security-audit/SKILL.md +246 -0
- package/lib/skills/serena-config/SKILL.md +92 -0
- package/lib/skills/simplify/SKILL.md +227 -0
- package/lib/skills/tackle/SKILL.md +156 -0
- package/lib/skills/task-add/SKILL.md +208 -0
- package/lib/skills/task-audit/SKILL.md +294 -0
- package/lib/skills/task-trash/SKILL.md +115 -0
- package/lib/skills/task-update/SKILL.md +136 -0
- package/lib/skills/uat-auto/SKILL.md +69 -0
- package/lib/skills/uat-auto-plus/SKILL.md +115 -0
- package/lib/skills/uat-generate/SKILL.md +289 -0
- package/lib/skills/uat-skip/SKILL.md +169 -0
- package/lib/skills/uat-walk/SKILL.md +164 -0
- package/lib/skills/uat-walk/UAT-CORE.md +140 -0
- package/lib/skills/update-docs/SKILL.md +75 -0
- package/lib/skills/wiki-archive/SKILL.md +96 -0
- package/lib/skills/wiki-ingest/SKILL.md +139 -0
- package/lib/skills/wiki-lint/SKILL.md +131 -0
- package/lib/skills/wiki-query/SKILL.md +71 -0
- package/lib/skills/wiki-rotate-log/SKILL.md +90 -0
- package/lib/skills/wiki-tidy/SKILL.md +107 -0
- package/package.json +32 -0
- package/raw/.gitkeep +0 -0
- package/raw/design-principles.md +65 -0
- package/raw/guides/command-anti-patterns.md +79 -0
- package/raw/guides/deployment-strategy.md +448 -0
- package/raw/guides/evals-framework.md +452 -0
- package/raw/guides/mcp-tools.md +335 -0
- package/raw/guides/task-spec.md +79 -0
- package/raw/guides/type-checking-templates/README.md +112 -0
- package/raw/guides/type-checking-templates/eslint/eslint.config.ts +105 -0
- package/raw/guides/type-checking-templates/python/mypy.ini +69 -0
- package/raw/guides/type-checking-templates/python/pyproject.toml +164 -0
- package/raw/guides/type-checking-templates/python/pyrightconfig.json +67 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.app.jsonc +45 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.lib.jsonc +44 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.node-esm.jsonc +40 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.node.jsonc +34 -0
- package/raw/guides/type-checking-templates/tsconfig/tsconfig.vite-root.json +8 -0
- package/raw/harness-notes.md +20 -0
- package/raw/house-style/components/Badge.tsx +16 -0
- package/raw/house-style/components/Button.tsx +32 -0
- package/raw/house-style/components/Card.tsx +26 -0
- package/raw/house-style/components/Chip.tsx +57 -0
- package/raw/house-style/components/IconButton.tsx +67 -0
- package/raw/house-style/components/Modal.tsx +18 -0
- package/raw/house-style/components/Stepper.tsx +141 -0
- package/raw/house-style/components/icons.tsx +128 -0
- package/raw/house-style/preview/src/index.css +46 -0
- package/raw/house-style/tokens/tailwind.preset.ts +49 -0
- package/raw/house-style/tokens/tokens.json +62 -0
- package/raw/llm-wiki-2.md +162 -0
- package/raw/llm-wiki.md +75 -0
- package/raw/research/dark-mode-theme/index.md +85 -0
- package/raw/research/dark-mode-theme/sources.md +49 -0
- package/raw/research/serena-mcp-disconnect/index.md +81 -0
- package/raw/research/serena-mcp-disconnect/sources.md +87 -0
- package/raw/research/wiki-tooling-improvements/index.md +126 -0
- package/raw/research/wiki-tooling-improvements/sources.md +73 -0
- package/raw/software-factory-case-study.pdf +0 -0
|
@@ -0,0 +1,289 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: uat-generate
|
|
3
|
+
description: Generate UAT tests in wiki/work/uat/ for a task
|
|
4
|
+
category: planning
|
|
5
|
+
model: claude-sonnet-4-6
|
|
6
|
+
argument-hint: <TASK-NNN | path/to/task-file.md | feature description>
|
|
7
|
+
disable-model-invocation: false
|
|
8
|
+
user-invocable: true
|
|
9
|
+
---
|
|
10
|
+
**Prereqs:** obey `.docs/guides/mcp-tools.md`; run /primer if not done this session.
|
|
11
|
+
|
|
12
|
+
# UAT Generator
|
|
13
|
+
|
|
14
|
+
Generate comprehensive User Acceptance Tests (UAT) for a feature, writing them to `wiki/work/uat/`.
|
|
15
|
+
|
|
16
|
+
UAT owns **runtime and end-to-end verification**. `/tackle` only runs static gates (typecheck, lint, unit tests). Any behavior that requires executing the feature — running a script against real paths, hitting an API, walking a user flow, asserting on produced files — is a UAT test, not a tackle step.
|
|
17
|
+
|
|
18
|
+
When a UAT case also contains behavior that can easily be preserved as a deterministic repeatable unit test, create that unit test immediately. UAT should not be the only place a cheap, automatable assertion lives.
|
|
19
|
+
|
|
20
|
+
---
|
|
21
|
+
|
|
22
|
+
**Target**: $ARGUMENTS
|
|
23
|
+
|
|
24
|
+
---
|
|
25
|
+
|
|
26
|
+
## Test Integrity (Non-Negotiable)
|
|
27
|
+
|
|
28
|
+
**Tests verify required functionality, not implementation behavior.** Encode what the feature *must do* per acceptance criteria — never what the current code happens to produce.
|
|
29
|
+
|
|
30
|
+
- Never weaken an assertion to make a test pass.
|
|
31
|
+
- Never narrow scope or drop edge cases to match buggy behavior.
|
|
32
|
+
- When research reveals a gap between requirement and implementation, write the test against the requirement and report the gap. Do not silently align with broken behavior.
|
|
33
|
+
- If you cannot determine the correct expected result from the requirement, stop and ask — do not invent a permissive assertion.
|
|
34
|
+
|
|
35
|
+
---
|
|
36
|
+
|
|
37
|
+
## Instructions
|
|
38
|
+
|
|
39
|
+
### Step 1: Resolve the source task and derive the UAT path
|
|
40
|
+
|
|
41
|
+
Parse `$ARGUMENTS`:
|
|
42
|
+
|
|
43
|
+
1. **TASK-NNN or path**: use `mcp__serena__find_file` to locate the task file in `wiki/work/tasks/`. All task files live in this single directory — files never move, status is in frontmatter.
|
|
44
|
+
2. **Number-slug** (e.g. `014-api-refactor`): use `mcp__serena__find_file` in `wiki/work/tasks/`.
|
|
45
|
+
3. **Feature description**: scan `wiki/work/tasks/` for a matching task via `mcp__serena__list_dir`. If none found, ask the user whether to create a task first via `/task-add`.
|
|
46
|
+
|
|
47
|
+
**UAT ID mirrors the task number**: TASK-014 → UAT-014. Slug mirrors the task slug.
|
|
48
|
+
|
|
49
|
+
Output path: `wiki/work/uat/UAT-NNN-slug.md`
|
|
50
|
+
|
|
51
|
+
**Check for an existing UAT file**: search `wiki/work/uat/` for a file starting with `UAT-NNN-`. If found and `status` is not `trashed`, ask the user: replace, append, or abort?
|
|
52
|
+
|
|
53
|
+
Screenshots directory: `wiki/work/uat/screenshots/`
|
|
54
|
+
|
|
55
|
+
### Step 2: Analyze the feature
|
|
56
|
+
|
|
57
|
+
Use Serena to explore the codebase:
|
|
58
|
+
- `find_symbol` and `get_symbols_overview` to find API endpoints, services, models, and UI components
|
|
59
|
+
- `search_for_pattern` when symbol names are unclear
|
|
60
|
+
|
|
61
|
+
Read the task file for acceptance criteria and scope. Identify happy paths, edge cases, and integration points.
|
|
62
|
+
|
|
63
|
+
#### Step 2.3: Research the contract for every planned test (mandatory)
|
|
64
|
+
|
|
65
|
+
Before writing any test, determine the **exact** behavior under test by reading the actual code. Guessed payloads, selectors, and error messages produce broken tests.
|
|
66
|
+
|
|
67
|
+
For each test type, produce a research notes block (in working context, not in the UAT file):
|
|
68
|
+
|
|
69
|
+
**2.3a. API tests** — capture: HTTP method + full path, required headers, request body schema (read the route handler or validator), query params, success response (status + body shape), error responses, side effects, auth prerequisites.
|
|
70
|
+
|
|
71
|
+
**2.3b. UI tests** — capture: route/URL (from router config — do not guess), component file path, exact element labels (read JSX), user actions, expected post-action state, loading/error states, auth/role requirements.
|
|
72
|
+
|
|
73
|
+
**2.3c. Edge case tests** — capture: exact code path that handles the case, trigger condition, observable response, and whether the behavior is intentional (verified in source).
|
|
74
|
+
|
|
75
|
+
**2.3d. Integration tests** — capture: every component/service/endpoint in the flow (in order), data passed between steps, side effects at each step, terminal observable state.
|
|
76
|
+
|
|
77
|
+
#### Step 2.4: Research checkpoint (hard gate)
|
|
78
|
+
|
|
79
|
+
Do not proceed to Step 3 until you can answer yes to all:
|
|
80
|
+
- [ ] Every API test: full request/response contract from source code (not guessed)
|
|
81
|
+
- [ ] Every UI test: route, component file, exact element labels, expected post-action state
|
|
82
|
+
- [ ] Every edge case test: actual handling code located
|
|
83
|
+
- [ ] Every integration test: full step-by-step flow documented
|
|
84
|
+
- [ ] Any test you cannot answer yes for: dropped (not approximated) and added to Step 6 gaps report
|
|
85
|
+
|
|
86
|
+
#### Step 2.5: Unit-test promotion checkpoint (mandatory)
|
|
87
|
+
|
|
88
|
+
For every planned UAT case, decide whether any part of it can be captured as a repeatable unit test with low setup cost.
|
|
89
|
+
|
|
90
|
+
A UAT case is **unit-test promotable** when all are true:
|
|
91
|
+
- The assertion targets deterministic business logic, parsing, validation, formatting, command construction, state transitions, error mapping, or a pure component/service boundary.
|
|
92
|
+
- It can run inside the project's normal unit-test runner without a live server, real browser session, external API, database, network, secrets, wall-clock sleeps, or filesystem state that is hard to isolate.
|
|
93
|
+
- The expected result is known from the task acceptance criteria or source contract.
|
|
94
|
+
- The needed test harness already exists, or can be added in the same local pattern as nearby tests without creating new infrastructure.
|
|
95
|
+
|
|
96
|
+
A UAT case is **not** unit-test promotable when it primarily verifies:
|
|
97
|
+
- Browser rendering, visual layout, screenshots, accessibility tree output, or user flow timing.
|
|
98
|
+
- Real HTTP service wiring, authentication middleware, deployment behavior, shell environment setup, database migrations, or file permissions.
|
|
99
|
+
- Third-party service behavior or integration between multiple independently deployed systems.
|
|
100
|
+
|
|
101
|
+
Before writing the UAT file, inspect the existing test layout and runner:
|
|
102
|
+
- Find nearby test files for the changed code.
|
|
103
|
+
- Identify the test framework, naming convention, fixtures, mocks, and command used by the repo.
|
|
104
|
+
- Prefer adding focused assertions to an existing nearby test file when that is the local pattern.
|
|
105
|
+
- Otherwise create the smallest conventional new test file beside the unit under test.
|
|
106
|
+
|
|
107
|
+
If a case is promotable, you **must** create or update the unit test file. Do not merely list it as a recommendation. If you cannot create it because the test framework is absent or the harness would require new infrastructure, record that as a gap with the concrete blocker.
|
|
108
|
+
|
|
109
|
+
### Step 3: Generate UAT test cases
|
|
110
|
+
|
|
111
|
+
**Only test what the task changed or introduced.** Do not include tests for pre-existing functionality that was not modified.
|
|
112
|
+
|
|
113
|
+
Create the UAT file with this structure:
|
|
114
|
+
|
|
115
|
+
```markdown
|
|
116
|
+
---
|
|
117
|
+
id: UAT-NNN
|
|
118
|
+
title: "UAT: [Task Title]"
|
|
119
|
+
status: pending
|
|
120
|
+
task: TASK-NNN
|
|
121
|
+
created: YYYY-MM-DD
|
|
122
|
+
updated: YYYY-MM-DD
|
|
123
|
+
---
|
|
124
|
+
|
|
125
|
+
# UAT-NNN — UAT: [Task Title]
|
|
126
|
+
|
|
127
|
+
implements::[[TASK-NNN]]
|
|
128
|
+
|
|
129
|
+
> **Source task**: [[TASK-NNN]]
|
|
130
|
+
> **Generated**: YYYY-MM-DD
|
|
131
|
+
|
|
132
|
+
---
|
|
133
|
+
|
|
134
|
+
## Prerequisites
|
|
135
|
+
|
|
136
|
+
- [ ] [Environment prerequisite 1]
|
|
137
|
+
- [ ] [Data/state prerequisite]
|
|
138
|
+
|
|
139
|
+
---
|
|
140
|
+
|
|
141
|
+
## Test Cases
|
|
142
|
+
|
|
143
|
+
### UAT-API-001: [Descriptive Test Name]
|
|
144
|
+
- **Endpoint**: `[METHOD] /api/v1/[path]`
|
|
145
|
+
- **Description**: [What this test verifies]
|
|
146
|
+
- **Steps**:
|
|
147
|
+
1. [Step-by-step instructions]
|
|
148
|
+
2. Run the curl command below as-is
|
|
149
|
+
- **Command**:
|
|
150
|
+
```bash
|
|
151
|
+
curl -sS -X POST 'http://localhost:8000/api/v1/example' -H 'Content-Type: application/json' -d '{"field":"value"}'
|
|
152
|
+
```
|
|
153
|
+
- **Expected Result**: [Status code + concrete body shape]
|
|
154
|
+
- [ ] Pass
|
|
155
|
+
|
|
156
|
+
### UAT-UI-001: [Descriptive Test Name]
|
|
157
|
+
- **Page**: [URL or route path]
|
|
158
|
+
- **Description**: [What this test verifies]
|
|
159
|
+
- **Steps**:
|
|
160
|
+
1. [Navigation instructions]
|
|
161
|
+
2. [User actions to perform]
|
|
162
|
+
3. [What to observe]
|
|
163
|
+
- **Expected Result**: [What success looks like]
|
|
164
|
+
- [ ] Pass
|
|
165
|
+
|
|
166
|
+
### UAT-EDGE-001: [Error Handling Test Name]
|
|
167
|
+
- **Scenario**: [The edge case being tested]
|
|
168
|
+
- **Steps**: [How to trigger this scenario]
|
|
169
|
+
- **Expected Result**: [How the system should handle it]
|
|
170
|
+
- **Repeatable Unit Test**: [Created: `path/to/test-file` | Not applicable: reason | Blocked: reason]
|
|
171
|
+
- [ ] Pass
|
|
172
|
+
```
|
|
173
|
+
|
|
174
|
+
**Key rules**:
|
|
175
|
+
- Every test case ends with `- [ ] Pass`
|
|
176
|
+
- The `implements::[[TASK-NNN]]` typed link must appear on the first line after the H1
|
|
177
|
+
- Section separators (`---`) match the outline format `/tackle` expects
|
|
178
|
+
|
|
179
|
+
**Curl command standards** (mandatory):
|
|
180
|
+
- One single `curl` invocation per test; no `echo` wrappers, no `&&`/`;` chaining, no `2>&1`
|
|
181
|
+
- Use `-sS` (silent + show errors)
|
|
182
|
+
- Single quotes around URL and `-d` payload
|
|
183
|
+
- Inline the payload on `-d` with valid JSON
|
|
184
|
+
- `| jq` is allowed for a single pipe stage
|
|
185
|
+
- No `-w "\nHTTP %{http_code}\n"` format strings
|
|
186
|
+
- Auth tokens: use `-H "Authorization: Bearer $UAT_AUTH_TOKEN"` (double quotes so shell expands it)
|
|
187
|
+
- No literal credentials in the file
|
|
188
|
+
|
|
189
|
+
**Repeatable unit test metadata** (mandatory for every test case):
|
|
190
|
+
- Add `- **Repeatable Unit Test**: Created: \`path/to/test-file\`` when you created or updated a unit test for the behavior.
|
|
191
|
+
- Add `- **Repeatable Unit Test**: Not applicable: <short reason>` when the case cannot reasonably become a unit test.
|
|
192
|
+
- Add `- **Repeatable Unit Test**: Blocked: <short reason>` only when it was promotable in principle but the repo lacks the needed test harness or fixtures.
|
|
193
|
+
|
|
194
|
+
**Auth metadata** (required for every auth-gated test):
|
|
195
|
+
```
|
|
196
|
+
Auth-Required: true
|
|
197
|
+
Auth-Role: user
|
|
198
|
+
```
|
|
199
|
+
|
|
200
|
+
**API test ordering**: Create before Read/Update/Delete; validation/error tests after happy-path for each resource.
|
|
201
|
+
|
|
202
|
+
### Step 4: Write repeatable unit tests, the UAT file, and cross-reference
|
|
203
|
+
|
|
204
|
+
1. For each promotable case from Step 2.5, create or update the actual unit test file before writing the UAT file:
|
|
205
|
+
- Use existing test framework conventions and nearby examples.
|
|
206
|
+
- Keep the test focused on the behavior from the UAT case.
|
|
207
|
+
- Do not add broad snapshots or duplicate end-to-end checks as unit tests.
|
|
208
|
+
- Do not introduce a new testing framework unless the source task explicitly requires it.
|
|
209
|
+
- If editing code test files, use Serena editing tools.
|
|
210
|
+
- If creating new config/markdown/test files where Serena is unavailable, use the appropriate project-approved edit/write tool; never shell redirection.
|
|
211
|
+
|
|
212
|
+
2. Include the created test path in the corresponding UAT case's `Repeatable Unit Test` metadata.
|
|
213
|
+
|
|
214
|
+
3. Write `wiki/work/uat/UAT-NNN-slug.md` using the `Write` tool.
|
|
215
|
+
|
|
216
|
+
4. Update the source task file's frontmatter: set `uat: "[[UAT-NNN]]"`. Use `Read` then `Edit` — never shell redirection.
|
|
217
|
+
|
|
218
|
+
### Step 5: Update the family index
|
|
219
|
+
|
|
220
|
+
Append to `wiki/work/uat/index.md`:
|
|
221
|
+
|
|
222
|
+
```
|
|
223
|
+
- [UAT-NNN — UAT: Title](UAT-NNN-slug.md) — verifies TASK-NNN · pending
|
|
224
|
+
```
|
|
225
|
+
|
|
226
|
+
If the file does not exist, create it with a `# UAT` heading and the list entry.
|
|
227
|
+
|
|
228
|
+
### Step 6: Append to wiki/log.md
|
|
229
|
+
|
|
230
|
+
Append:
|
|
231
|
+
|
|
232
|
+
```
|
|
233
|
+
## [YYYY-MM-DD] uat | UAT-NNN UAT: <task title>
|
|
234
|
+
Generated UAT-NNN for TASK-NNN with N test cases covering <brief scope>. Created M repeatable unit test(s): <paths or "none">.
|
|
235
|
+
```
|
|
236
|
+
|
|
237
|
+
### Step 7: Report completion
|
|
238
|
+
|
|
239
|
+
Print:
|
|
240
|
+
- UAT file: `wiki/work/uat/UAT-NNN-slug.md`
|
|
241
|
+
- Source task: `TASK-NNN`
|
|
242
|
+
- Test counts by category
|
|
243
|
+
- Repeatable unit tests created or blocked
|
|
244
|
+
- Any gaps (tests dropped due to insufficient research)
|
|
245
|
+
|
|
246
|
+
Next steps:
|
|
247
|
+
```
|
|
248
|
+
To walk through tests interactively: /uat-walk wiki/work/uat/UAT-NNN-slug.md
|
|
249
|
+
To run tests headlessly: /uat-auto wiki/work/uat/UAT-NNN-slug.md
|
|
250
|
+
```
|
|
251
|
+
|
|
252
|
+
Output this banner verbatim:
|
|
253
|
+
|
|
254
|
+
```
|
|
255
|
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
256
|
+
UAT GENERATED
|
|
257
|
+
File: wiki/work/uat/UAT-NNN-slug.md
|
|
258
|
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
259
|
+
```
|
|
260
|
+
|
|
261
|
+
(Replace `UAT-NNN-slug` with the actual filename.)
|
|
262
|
+
|
|
263
|
+
---
|
|
264
|
+
|
|
265
|
+
## Directory Structure
|
|
266
|
+
|
|
267
|
+
```
|
|
268
|
+
wiki/work/uat/
|
|
269
|
+
├── index.md # Family index — active items only
|
|
270
|
+
├── UAT-014-api-refactor.md # pending/in-progress/failed UATs
|
|
271
|
+
├── UAT-015-user-auth.md
|
|
272
|
+
└── screenshots/ # Screenshots captured during walkthrough
|
|
273
|
+
|
|
274
|
+
wiki/work/tasks/
|
|
275
|
+
├── index.md # Family index — active items only
|
|
276
|
+
├── TASK-014-api-refactor.md # All tasks — status in frontmatter, never moved
|
|
277
|
+
└── TASK-015-user-auth.md
|
|
278
|
+
```
|
|
279
|
+
|
|
280
|
+
**UAT lifecycle** (via frontmatter `status`): `pending` → `in-progress` → `passed` | `failed` | `skipped` | `trashed`. Files never move.
|
|
281
|
+
|
|
282
|
+
---
|
|
283
|
+
|
|
284
|
+
## Naming Convention
|
|
285
|
+
|
|
286
|
+
| Task | UAT file |
|
|
287
|
+
|------|---------|
|
|
288
|
+
| `wiki/work/tasks/TASK-014-api-refactor.md` | `wiki/work/uat/UAT-014-api-refactor.md` |
|
|
289
|
+
| `wiki/work/tasks/TASK-003-user-auth.md` | `wiki/work/uat/UAT-003-user-auth.md` |
|
|
@@ -0,0 +1,169 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: uat-skip
|
|
3
|
+
description: Skip UAT for a task — sets UAT and task status to skipped/done, removes index rows, auto-checkoffs roadmap
|
|
4
|
+
category: planning
|
|
5
|
+
model: claude-haiku-4-5-20251001
|
|
6
|
+
argument-hint: <TASK-NNN or path/to/task-file.md>
|
|
7
|
+
disable-model-invocation: false
|
|
8
|
+
user-invocable: true
|
|
9
|
+
---
|
|
10
|
+
**Prereqs:** obey `.docs/guides/mcp-tools.md`; run /primer if not done this session.
|
|
11
|
+
|
|
12
|
+
# UAT Skip
|
|
13
|
+
|
|
14
|
+
Skip UAT testing for a task. Sets UAT status to `skipped` (creating a skeleton if none exists), sets task status to `done`, removes both rows from their family indexes, auto-checkoffs active roadmaps, and annotates linked decisions.
|
|
15
|
+
|
|
16
|
+
No files are moved. Status lives in frontmatter.
|
|
17
|
+
|
|
18
|
+
---
|
|
19
|
+
|
|
20
|
+
**Target**: $ARGUMENTS
|
|
21
|
+
|
|
22
|
+
---
|
|
23
|
+
|
|
24
|
+
## Pipeline Context
|
|
25
|
+
|
|
26
|
+
`/uat-skip` is an escape hatch — use it when UAT testing is not needed, not applicable, or intentionally deferred for a task that has completed implementation.
|
|
27
|
+
|
|
28
|
+
---
|
|
29
|
+
|
|
30
|
+
## Step 1: Resolve the Task File
|
|
31
|
+
|
|
32
|
+
Parse `$ARGUMENTS` to locate the task file in `wiki/work/tasks/`:
|
|
33
|
+
|
|
34
|
+
1. **TASK-NNN** or **TASK-NNN-slug** — use Serena `find_file` to locate `TASK-NNN*.md` inside `wiki/work/tasks/`. Task files never move; there are no subdirectories to check.
|
|
35
|
+
2. **Full path** — confirm the file exists with `find_file`. If it does not exist, STOP and report the error.
|
|
36
|
+
3. **Ambiguous / description only** — list matches and ask the user to clarify.
|
|
37
|
+
|
|
38
|
+
Read the task file. Extract:
|
|
39
|
+
- `id:` frontmatter field (e.g. `TASK-007`)
|
|
40
|
+
- `uat:` frontmatter field (path to linked UAT file, if any)
|
|
41
|
+
- `title:` frontmatter field
|
|
42
|
+
- Any `implements::` decision reference in the body
|
|
43
|
+
|
|
44
|
+
---
|
|
45
|
+
|
|
46
|
+
## Step 2: Find or Create the UAT File
|
|
47
|
+
|
|
48
|
+
**If a UAT file is linked** (`uat:` frontmatter exists):
|
|
49
|
+
- Read `wiki/work/uat/<UAT-NNN-slug>.md`.
|
|
50
|
+
- The file will have its status set to `skipped` in Step 3.
|
|
51
|
+
|
|
52
|
+
**If no UAT file exists:**
|
|
53
|
+
- Determine the next UAT-NNN by reading `wiki/work/uat/index.md` (highest existing NNN + 1).
|
|
54
|
+
- Derive the slug from the task title (lowercase, hyphens, strip special chars).
|
|
55
|
+
- Create `wiki/work/uat/UAT-NNN-slug.md` using this skeleton:
|
|
56
|
+
|
|
57
|
+
```markdown
|
|
58
|
+
---
|
|
59
|
+
id: UAT-NNN
|
|
60
|
+
title: "UAT: <Task Title> (Skipped)"
|
|
61
|
+
task: <task-file-path>
|
|
62
|
+
status: skipped
|
|
63
|
+
created: YYYY-MM-DD
|
|
64
|
+
updated: YYYY-MM-DD
|
|
65
|
+
---
|
|
66
|
+
|
|
67
|
+
# UAT: <Task Title> (Skipped)
|
|
68
|
+
|
|
69
|
+
> **Source task**: [[<TASK-NNN>]]
|
|
70
|
+
> **Skipped**: YYYY-MM-DD
|
|
71
|
+
> **Reason**: UAT intentionally skipped via /uat-skip — no tests generated
|
|
72
|
+
|
|
73
|
+
---
|
|
74
|
+
|
|
75
|
+
This task's UAT was intentionally skipped. No test cases were generated or executed.
|
|
76
|
+
```
|
|
77
|
+
|
|
78
|
+
- Add a row to `wiki/work/uat/index.md`:
|
|
79
|
+
`| UAT-NNN | <title> | skipped | <TASK-NNN> |`
|
|
80
|
+
|
|
81
|
+
---
|
|
82
|
+
|
|
83
|
+
## Step 3: Status-Flip Procedure
|
|
84
|
+
|
|
85
|
+
Apply the STATUS-FLIP PROCEDURE to both artifacts:
|
|
86
|
+
|
|
87
|
+
**UAT file** (`wiki/work/uat/UAT-NNN-slug.md`):
|
|
88
|
+
1. Edit `status: pending` (or whatever current status) → `status: skipped`
|
|
89
|
+
2. Edit `updated:` → today's date
|
|
90
|
+
3. Remove the UAT's row from `wiki/work/uat/index.md` (skipped UATs are not active)
|
|
91
|
+
|
|
92
|
+
**Task file** (`wiki/work/tasks/TASK-NNN-slug.md`):
|
|
93
|
+
1. Edit `status:` (whatever it currently is — `todo`, `in-progress`, or `pending-uat`) → `status: done`
|
|
94
|
+
2. Edit `updated:` → today's date
|
|
95
|
+
3. Remove the task's row from `wiki/work/tasks/index.md` (done tasks are not active)
|
|
96
|
+
|
|
97
|
+
Use the `Edit` tool for all frontmatter changes. Never use `sed`, `awk`, or shell redirection.
|
|
98
|
+
|
|
99
|
+
---
|
|
100
|
+
|
|
101
|
+
## Step 3a: Archive Both Files
|
|
102
|
+
|
|
103
|
+
After the status flips and index row removals in Step 3, archive both artifacts:
|
|
104
|
+
|
|
105
|
+
1. `git mv wiki/work/uat/<UAT-file>.md wiki/work/uat/archive/<UAT-file>.md`
|
|
106
|
+
2. Append UAT row to `wiki/work/uat/archive/index.md`: `| [[UAT-NNN]] | Title | skipped | YYYY-MM-DD |`
|
|
107
|
+
3. `git mv wiki/work/tasks/<TASK-file>.md wiki/work/tasks/archive/<TASK-file>.md`
|
|
108
|
+
4. Append task row to `wiki/work/tasks/archive/index.md`: `| [[TASK-NNN]] | Title | done | YYYY-MM-DD |`
|
|
109
|
+
|
|
110
|
+
Use `Bash` for `git mv` only. Use `Edit` for all index appends.
|
|
111
|
+
|
|
112
|
+
---
|
|
113
|
+
|
|
114
|
+
## Step 4: Roadmap Auto-Checkoff
|
|
115
|
+
|
|
116
|
+
Scan every active roadmap (files in `wiki/work/roadmaps/` whose `status: active` frontmatter):
|
|
117
|
+
|
|
118
|
+
1. Use Serena `list_dir` on `wiki/work/roadmaps/` (exclude `lifecycle.md` and `index.md`).
|
|
119
|
+
2. Read each file. Look for lines matching `- [ ] [[TASK-NNN` (wiki-style task link).
|
|
120
|
+
3. For each match, `Edit` `- [ ] [[TASK-NNN` → `- [x] [[TASK-NNN` **and** update `updated:` in that roadmap's frontmatter to today.
|
|
121
|
+
4. **Phase sweep**: after flipping this task's line, scan other `- [ ] [[TASK-NNN` lines in the same `## Phase` block. For each, check if that task's `status:` is `done`. If yes, flip `- [ ]` → `- [x]`.
|
|
122
|
+
5. **Roadmap completion check**: if ALL checkboxes in the roadmap are now `[x]`, flip the roadmap's `status: active` → `status: done` and `updated:` → today, remove the roadmap's row from `wiki/work/roadmaps/index.md`, then archive the roadmap file:
|
|
123
|
+
- `git mv wiki/work/roadmaps/<file>.md wiki/work/roadmaps/archive/<file>.md`
|
|
124
|
+
- Append to `wiki/work/roadmaps/archive/index.md`: `| [[ROADMAP-NNN]] | Title | done | YYYY-MM-DD |`
|
|
125
|
+
6. Silent no-op if no roadmap references this task.
|
|
126
|
+
|
|
127
|
+
---
|
|
128
|
+
|
|
129
|
+
## Step 5: Decision Annotation
|
|
130
|
+
|
|
131
|
+
Check the task body for a typed link `implements::[[DEC-NNNN#DM]]` or similar decision reference:
|
|
132
|
+
|
|
133
|
+
- If found, locate the decision file in `wiki/work/decisions/`.
|
|
134
|
+
- Search the decision file for any `Source task(s):` line referencing this task.
|
|
135
|
+
- If found, append ` — done (UAT skipped) YYYY-MM-DD` to that line.
|
|
136
|
+
- Use Serena `search_for_pattern` on `wiki/work/decisions/` for the task ID to catch any reference pattern.
|
|
137
|
+
- If not found: skip silently.
|
|
138
|
+
|
|
139
|
+
---
|
|
140
|
+
|
|
141
|
+
## Step 6: Log Entry
|
|
142
|
+
|
|
143
|
+
Append to `wiki/log.md`:
|
|
144
|
+
|
|
145
|
+
```markdown
|
|
146
|
+
## [YYYY-MM-DD] uat | UAT-NNN skipped → TASK-NNN done · both archived
|
|
147
|
+
|
|
148
|
+
UAT skipped for <task title>. Task marked done. Archived UAT-NNN → uat/archive/ and TASK-NNN → tasks/archive/. <Optional: reason if user provided one.>
|
|
149
|
+
```
|
|
150
|
+
|
|
151
|
+
Use the `Edit` tool (append at end of file).
|
|
152
|
+
|
|
153
|
+
---
|
|
154
|
+
|
|
155
|
+
## Step 7: Report Completion
|
|
156
|
+
|
|
157
|
+
```
|
|
158
|
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
159
|
+
UAT SKIP COMPLETE
|
|
160
|
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
161
|
+
Task: TASK-NNN → status: done → archived to tasks/archive/
|
|
162
|
+
UAT: UAT-NNN → status: skipped → archived to uat/archive/
|
|
163
|
+
(or: Skeleton UAT-NNN created and immediately archived)
|
|
164
|
+
|
|
165
|
+
Roadmaps updated: [list or "None"]
|
|
166
|
+
Decisions updated: [list or "None"]
|
|
167
|
+
Log entry appended.
|
|
168
|
+
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
169
|
+
```
|
|
@@ -0,0 +1,164 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: uat-walk
|
|
3
|
+
description: Walk through a pending UAT file test-by-test with the user
|
|
4
|
+
category: executing
|
|
5
|
+
model: claude-sonnet-4-6
|
|
6
|
+
argument-hint: <path/to/uat-file.md, number-slug, or description>
|
|
7
|
+
disable-model-invocation: false
|
|
8
|
+
user-invocable: true
|
|
9
|
+
---
|
|
10
|
+
**Prereqs:** obey `.docs/guides/mcp-tools.md` + `wiki/work/uat/lifecycle.md`; run /primer if not done this session.
|
|
11
|
+
|
|
12
|
+
Read `~/.claude/skills/uat-walk/UAT-CORE.md` now — it defines Steps 1–5 (resolution, prerequisites, classification, judging, closure). This file defines only what differs for **interactive** mode.
|
|
13
|
+
|
|
14
|
+
# UAT (interactive walk)
|
|
15
|
+
|
|
16
|
+
**UAT File**: $ARGUMENTS
|
|
17
|
+
|
|
18
|
+
Walk each test in a pending UAT file test-by-test, present it to the user, and record the user's pass/fail verdict. **The user is the only authority on pass/fail** — the agent presents and facilitates, never auto-judges (this replaces UAT-CORE Step 4's auto-judge criteria; Steps 1, 2, 3, 5, and Closure apply as written). UAT-CORE Step 3.5 (stub detection) does not run here.
|
|
19
|
+
|
|
20
|
+
Loop: `read/parse → mode-select (first cycle) → find next batch → present (3A/3B/3C) → record verdicts → update file → repeat` until no test has a blocking status, then run UAT-CORE **Closure**.
|
|
21
|
+
|
|
22
|
+
---
|
|
23
|
+
|
|
24
|
+
## Mode selection (first cycle only)
|
|
25
|
+
|
|
26
|
+
Decide from what's present; **only ask when genuinely ambiguous**:
|
|
27
|
+
|
|
28
|
+
| Failed | Pending | Action |
|
|
29
|
+
|--------|---------|--------|
|
|
30
|
+
| 0 | any | **Pending only**, silently |
|
|
31
|
+
| ≥1 | 0 | **Failed only**, silently (note it: "N failed, no pending — re-running failed") |
|
|
32
|
+
| ≥1 | ≥1 | Ask inline: `N failed and M pending. Failed first / Pending only / Failed only?` |
|
|
33
|
+
|
|
34
|
+
- **Failed first** — all `[FAIL]` (document order) → then all `- [ ] Pass`
|
|
35
|
+
- **Pending only** — only `- [ ] Pass` (skip `[FAIL]`)
|
|
36
|
+
- **Failed only** — only `[FAIL]` (skip `- [ ] Pass`)
|
|
37
|
+
|
|
38
|
+
Store the choice for the walkthrough. When re-testing a failed test, reset its status `- [FAIL: ...]` → `- [ ] Pass` before presenting.
|
|
39
|
+
|
|
40
|
+
Prerequisites are always handled first (UAT-CORE Step 2, walk mode) regardless of test mode.
|
|
41
|
+
|
|
42
|
+
---
|
|
43
|
+
|
|
44
|
+
## Find the next batch
|
|
45
|
+
|
|
46
|
+
Classify each eligible test (UAT-CORE Step 3), then collect the next batch of consecutive same-type tests. Starting a different type begins a fresh batch.
|
|
47
|
+
|
|
48
|
+
| Type | Batch size | Present via |
|
|
49
|
+
|------|-----------|-------------|
|
|
50
|
+
| API/CLI | up to 5 | 3A (auto-execute) |
|
|
51
|
+
| UI | up to 3 (all must fit on screen) | 3B (compact) |
|
|
52
|
+
| Manual | exactly 1 (never batched) | 3C (single) |
|
|
53
|
+
|
|
54
|
+
If no more tests match the mode, go to UAT-CORE **Closure** and run it in full — do not stop early.
|
|
55
|
+
|
|
56
|
+
All presentation uses `**bold**` labels (rendered in-terminal) and always shows progress counts.
|
|
57
|
+
|
|
58
|
+
---
|
|
59
|
+
|
|
60
|
+
## 3A — API/CLI batch (auto-execute)
|
|
61
|
+
|
|
62
|
+
Auto-execute — **never** ask "Run / Manual / Skip?". Present the header, then run each test and show results inline:
|
|
63
|
+
|
|
64
|
+
```markdown
|
|
65
|
+
━━━━━━━━━━ API TEST BATCH [tests 3–7 of 18] ━━━━━━━━━━
|
|
66
|
+
**Progress:** 2/18 passed · 0 failed · 16 remaining
|
|
67
|
+
|
|
68
|
+
**[3 of 18] UAT-API-001: Create Position** · POST /api/positions
|
|
69
|
+
▶ **COMMAND:** curl -sS -X POST 'http://localhost:4321/api/positions' -H 'Content-Type: application/json' -d '{"title":"Engineer"}'
|
|
70
|
+
▶ **EXPECTED:** HTTP 201; body has `id` and `title: "Engineer"`
|
|
71
|
+
▶ **ACTUAL:** HTTP 201; {"id":1,"title":"Engineer",...}
|
|
72
|
+
▶ **RESULT:** ✅ Matches expected
|
|
73
|
+
```
|
|
74
|
+
|
|
75
|
+
**Rules:**
|
|
76
|
+
- **One Bash call per test**, run sequentially (batch = presentation grouping, never command chaining). Follow UAT-CORE "Bash hygiene". If a test classified API/CLI has no extractable command, present it as manual (3C) instead.
|
|
77
|
+
- **EXPECTED directly above ACTUAL**, nothing between them — the user compares at a glance. Truncate long bodies inside the ACTUAL block.
|
|
78
|
+
- **`▶ RESULT:` on every presentation** (including fix-now retests): `✅ Matches expected` or `❌ Does not match expected — <one-line reason>`. This is the agent's *observation*, not a verdict — the user still issues pass/fail.
|
|
79
|
+
- **Halt on failure (mandatory):** if a test errors or clearly diverges from Expected (status mismatch, error body, missing fields, exception), **STOP the batch immediately at that test**. Ask that single test `Pass / Fail / Fix now / Skip?` and **wait** for explicit direction. Never move on after a failure without it. Apply the verdict, then resume the remaining tests from where you halted.
|
|
80
|
+
- After all tests execute without failure, ask for batch verdicts (below).
|
|
81
|
+
|
|
82
|
+
## 3B — UI batch (compact)
|
|
83
|
+
|
|
84
|
+
Up to 3 UI tests, compact so the whole batch fits without scrolling — one line each for description/steps/expected, no prose. Share the `Page:` URL in the header if common.
|
|
85
|
+
|
|
86
|
+
```markdown
|
|
87
|
+
━━━━━━━━━━ UI TEST BATCH [tests 8–10 of 18] ━━━━━━━━━━
|
|
88
|
+
**Progress:** 7/18 passed · 0 failed · 11 remaining · **Page:** http://localhost:4321/strengths
|
|
89
|
+
[8] UAT-UI-001 — Strength Panel Layout
|
|
90
|
+
Steps: Navigate to /strengths · Verify panel on the right
|
|
91
|
+
Expected: Right-aligned, no horizontal scroll
|
|
92
|
+
[9] UAT-UI-002 — Empty State · Steps: Clear strengths · Navigate to /strengths · Expected: "No strengths yet" visible
|
|
93
|
+
Verdicts (8–10)? [8] P/F/Fix/Skip? [9] … [10] …
|
|
94
|
+
```
|
|
95
|
+
|
|
96
|
+
## 3C — Manual test (single)
|
|
97
|
+
|
|
98
|
+
One at a time. Show description, scenario, numbered steps, then the expected result:
|
|
99
|
+
|
|
100
|
+
```markdown
|
|
101
|
+
━━━━━━━━━━ TEST [14 of 18]: UAT-EDGE-003 — Concurrent Updates ━━━━━━━━━━
|
|
102
|
+
**Progress:** 12/18 passed · 1 failed · 5 remaining
|
|
103
|
+
**Description:** concurrent updates to the same record don't cause data loss
|
|
104
|
+
**STEPS:** 1. Open position #1 in two tabs 2. Edit title in tab 1, save 3. Edit description in tab 2, save
|
|
105
|
+
▶ **EXPECTED:** second save merges or shows a conflict error; no silent data loss
|
|
106
|
+
```
|
|
107
|
+
|
|
108
|
+
---
|
|
109
|
+
|
|
110
|
+
## Verdicts
|
|
111
|
+
|
|
112
|
+
Prompt **inline** — never `AskUserQuestion`. Accept any unambiguous prefix (`p`/`pass`, `f`/`fail`, `fix`, `s`/`skip`).
|
|
113
|
+
|
|
114
|
+
### ⛔ Mandatory verdict gate
|
|
115
|
+
Receive an explicit pass/fail/fix/skip verdict for **every** test before advancing. No exceptions — violating this invalidates the walkthrough.
|
|
116
|
+
- **Batched (API/UI):** ask all verdicts in one prompt, then **STOP and wait**. Don't present the next batch, run commands, or call tools until every test in the batch is accounted for. If the reply leaves any test uncovered, ask a follow-up for just those — never assume, never default to pass.
|
|
117
|
+
- **Single (manual / fix-now retest):** ask immediately after presentation, **STOP and wait**.
|
|
118
|
+
- **Auto-executed failure (3A):** halt at that test, ask `Pass / Fail / Fix now / Skip?`, **STOP and wait** before running or calling anything else.
|
|
119
|
+
- **Never** auto-judge, infer a verdict from output, or move on "because it looked fine."
|
|
120
|
+
|
|
121
|
+
Batch verdict input formats: `all pass` / `all p` (same to all) · `p p f fix s` (per-test, in order) · `3: pass, 5: fail, rest pass` (selective + default) · single word → applies to all. Ambiguous → ask.
|
|
122
|
+
|
|
123
|
+
### Verdict actions (per test)
|
|
124
|
+
- **Pass** → `- [x] Pass <!-- YYYY-MM-DD -->`
|
|
125
|
+
- **Fail** → ask inline "What went wrong? (optional)"; mark `- [FAIL: <note or "No details provided">] <!-- YYYY-MM-DD -->`
|
|
126
|
+
- **Skip** → ask inline "Reason for skipping? (optional)"; mark `- [SKIP: <reason or "User skipped">] <!-- YYYY-MM-DD -->`
|
|
127
|
+
- **Fix now** → see Fix workflow. Process all non-fix verdicts in the batch first, then handle fix-now tests one at a time.
|
|
128
|
+
|
|
129
|
+
File updates follow UAT-CORE Step 5 (one `Edit` per status line, never `sed`).
|
|
130
|
+
|
|
131
|
+
---
|
|
132
|
+
|
|
133
|
+
## Fix workflow
|
|
134
|
+
|
|
135
|
+
When the user picks **Fix now**:
|
|
136
|
+
|
|
137
|
+
1. Ask inline "What went wrong?".
|
|
138
|
+
2. **Resolve approach ambiguity before delegating (mandatory).** Root cause and target are usually clear; the ambiguity that matters is *how* to fix — side effects, multiple valid approaches with different tradeoffs, or a fix that touches shared code. If any is unclear, **STOP and ask** first (e.g. "clamp at the API layer or adjust the validation schema?" / "scope this to the test or update the shared `<X>` utility globally?"). If unambiguous (one obvious change, no shared-code risk), proceed.
|
|
139
|
+
3. Mark `- [FIXING: <note>] <!-- YYYY-MM-DD -->`.
|
|
140
|
+
4. **Delegate to one `general-purpose` subagent** (`Task` tool; **max 1 fix subagent at a time** — wait for completion). Prompt: UAT file path, test ID + name, the failure description, the full test section (endpoint/page, description, steps, expected). Instruct it to use Serena to find the code, identify root cause, implement the fix, run available quality checks (lint/typecheck/tests), and report changes + rationale.
|
|
141
|
+
5. **⚠️ NEVER AUTO-PASS AFTER A FIX.** Reset status to `- [ ] Pass`, re-present the test (single-test flow), and ask the user for a verdict. Only the **user** marks it passing. If the subagent reports it couldn't resolve the issue, present Fail / Skip.
|
|
142
|
+
|
|
143
|
+
The `[FIXING: ...]` marker is temporary — it must resolve to `[x] Pass`, `[FAIL: ...]`, `[SKIP: ...]`, or `[ ] Pass` before moving on.
|
|
144
|
+
|
|
145
|
+
---
|
|
146
|
+
|
|
147
|
+
## Progress persistence
|
|
148
|
+
|
|
149
|
+
Every verdict is written to the file immediately (UAT-CORE Step 5), so an aborted or interrupted walkthrough keeps its progress and resumes from the first pending test.
|
|
150
|
+
|
|
151
|
+
**Completion summary** (before running UAT-CORE Closure):
|
|
152
|
+
|
|
153
|
+
```
|
|
154
|
+
━━━ UAT WALKTHROUGH COMPLETE ━━━
|
|
155
|
+
File: wiki/work/uat/UAT-005-positions.md · Source: wiki/work/tasks/TASK-005-positions.md
|
|
156
|
+
✅ Passed 6 · ⚠️ Skipped 1 · ❌ Failed 2 · ❔ Pending 0 · Total 9
|
|
157
|
+
Failed: • UAT-API-003: Delete Position — "Returns 500 instead of 204"
|
|
158
|
+
```
|
|
159
|
+
|
|
160
|
+
- **All complete** (no `[FAIL]`/`[FIXING]`) → run UAT-CORE **Closure → All pass**.
|
|
161
|
+
- **Some failed** → leave the file in place (`status: in-progress`); suggest `/uat-walk <path>` to re-test or `/task-add "Fix UAT failures in <feature>"`.
|
|
162
|
+
- **Aborted** → leave in place; note progress was saved.
|
|
163
|
+
|
|
164
|
+
**Start now — read UAT-CORE.md, resolve the UAT file, and present the first prerequisite or test.**
|