qualiow-exploratory-testing 1.0.0
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/LICENSE +21 -0
- package/README.md +214 -0
- package/data/domains/_default.yml +167 -0
- package/data/domains/ecommerce.yml +198 -0
- package/data/domains/fintech.yml +207 -0
- package/data/domains/marketing.yml +202 -0
- package/data/domains/saas.yml +206 -0
- package/data/knowledge/changelog.yml +75 -0
- package/data/knowledge/custom/.gitkeep +0 -0
- package/data/knowledge/learned-patterns.md +40 -0
- package/data/knowledge/manifest.yml +141 -0
- package/data/knowledge/releases/v0.1.0/entries/checklist-accessibility-wcag.yml +326 -0
- package/data/knowledge/releases/v0.1.0/entries/heuristic-few-hiccupps.yml +194 -0
- package/data/knowledge/releases/v0.1.0/entries/heuristic-goldilocks.yml +143 -0
- package/data/knowledge/releases/v0.1.0/entries/heuristic-rcrcrc.yml +207 -0
- package/data/knowledge/releases/v0.1.0/entries/heuristic-sfdipot.yml +171 -0
- package/data/knowledge/releases/v0.1.0/entries/heuristic-test-tours.yml +253 -0
- package/data/knowledge/releases/v0.1.0/entries/reference-exploratory-testing-types.yml +84 -0
- package/data/knowledge/releases/v0.1.0/entries/reference-heuristic-praxis.yml +95 -0
- package/data/knowledge/releases/v0.1.0/entries/technique-boundary-testing.yml +203 -0
- package/data/knowledge/releases/v0.1.0/entries/technique-business-logic-race-conditions.yml +146 -0
- package/data/knowledge/releases/v0.1.0/entries/technique-data-integrity-testing.yml +269 -0
- package/data/knowledge/releases/v0.1.0/entries/technique-error-guessing.yml +216 -0
- package/data/knowledge/releases/v0.1.0/entries/technique-risk-based-testing.yml +298 -0
- package/data/knowledge/releases/v0.1.0/release.yml +22 -0
- package/data/targets/_default.yml +11 -0
- package/data/targets/testers-ai.yml +14 -0
- package/data/templates/bug-report.md +178 -0
- package/data/templates/coverage-map.md +70 -0
- package/data/templates/session-charter.md +77 -0
- package/data/templates/session-report.md +112 -0
- package/dist/cli/index.d.ts +1 -0
- package/dist/cli/index.js +1757 -0
- package/dist/cli/index.js.map +1 -0
- package/dist/index.d.ts +899 -0
- package/dist/index.js +1133 -0
- package/dist/index.js.map +1 -0
- package/docs/GETTING-STARTED.md +265 -0
- package/package.json +70 -0
- package/skills/qa-explore/SKILL.md +70 -0
- package/skills/qa-explore/phases/00-setup.md +96 -0
- package/skills/qa-explore/phases/01-auth.md +34 -0
- package/skills/qa-explore/phases/02-charter.md +112 -0
- package/skills/qa-explore/phases/03-discovery.md +49 -0
- package/skills/qa-explore/phases/04-journeys.md +51 -0
- package/skills/qa-explore/phases/05-features.md +55 -0
- package/skills/qa-explore/phases/06-edge-cases.md +69 -0
- package/skills/qa-explore/phases/07-reporting.md +162 -0
- package/skills/qa-explore/references/context-integration.md +44 -0
- package/skills/qa-explore/references/security-rules.md +43 -0
- package/skills/qa-explore/references/session-rules.md +33 -0
- package/skills/qa-explore/references/severity-guide.md +14 -0
- package/skills/qa-explore-cleanup/SKILL.md +39 -0
- package/skills/qa-explore-feedback/SKILL.md +73 -0
- package/skills/qa-explore-quick/SKILL.md +80 -0
- package/skills/qa-explore-report/SKILL.md +62 -0
- package/skills/qa-gather/SKILL.md +198 -0
- package/skills/qa-knowledge-add/SKILL.md +91 -0
- package/skills/qa-knowledge-list/SKILL.md +54 -0
- package/skills/qa-target-setup/SKILL.md +106 -0
|
@@ -0,0 +1,39 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: qa-explore-cleanup
|
|
3
|
+
description: >
|
|
4
|
+
Manage exploratory testing sessions — list, archive, or delete old sessions.
|
|
5
|
+
Use when user says: "cleanup sessions", "delete old sessions", "archive", "list sessions".
|
|
6
|
+
allowed-tools: Read, Write, Glob, Grep, Bash(ls:*), Bash(du:*), Bash(tar:*), Bash(rm:*)
|
|
7
|
+
---
|
|
8
|
+
|
|
9
|
+
# Session Cleanup & Management
|
|
10
|
+
|
|
11
|
+
## Commands
|
|
12
|
+
|
|
13
|
+
### List Sessions
|
|
14
|
+
Read `output/sessions/INDEX.md` and display all sessions with:
|
|
15
|
+
- Date, target, bug count, duration, status
|
|
16
|
+
- Directory size (via `du -sh`)
|
|
17
|
+
|
|
18
|
+
### Archive Session
|
|
19
|
+
```bash
|
|
20
|
+
# Archive a specific session to .tar.gz
|
|
21
|
+
tar -czf output/sessions/<session-dir>.tar.gz -C output/sessions <session-dir>
|
|
22
|
+
```
|
|
23
|
+
Then optionally remove the original directory.
|
|
24
|
+
|
|
25
|
+
### Delete Session
|
|
26
|
+
**Always confirm with user before deleting.**
|
|
27
|
+
Show what will be removed (file count, size), then:
|
|
28
|
+
- Remove session directory
|
|
29
|
+
- Remove entry from INDEX.md
|
|
30
|
+
- Remove associated bugs from all-bugs.md
|
|
31
|
+
|
|
32
|
+
### Delete Old Sessions
|
|
33
|
+
Delete all sessions older than N days.
|
|
34
|
+
**Always list what will be deleted and confirm first.**
|
|
35
|
+
|
|
36
|
+
### Rules
|
|
37
|
+
- NEVER auto-delete — always show and confirm
|
|
38
|
+
- Keep INDEX.md updated after any changes
|
|
39
|
+
- Suggest archiving before deleting
|
|
@@ -0,0 +1,73 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: qa-explore-feedback
|
|
3
|
+
description: >
|
|
4
|
+
Capture post-session feedback to improve future exploratory testing sessions.
|
|
5
|
+
Identifies false positives, missed bugs, and extracts patterns for the knowledge base.
|
|
6
|
+
Use after completing an exploratory session or when user says: "review session", "false positive",
|
|
7
|
+
"missed bug", "session feedback".
|
|
8
|
+
allowed-tools: Read, Write, Glob, Grep
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
# Post-Session Feedback Capture
|
|
12
|
+
|
|
13
|
+
## Flow
|
|
14
|
+
|
|
15
|
+
### 1. Load Latest Session
|
|
16
|
+
|
|
17
|
+
Read `output/sessions/INDEX.md` to find the most recent session (or user-specified session).
|
|
18
|
+
Read the session's `session-report.md` and all `bugs/BUG-*.md` files.
|
|
19
|
+
|
|
20
|
+
### 2. Review Bugs with User
|
|
21
|
+
|
|
22
|
+
For each bug found, ask the user:
|
|
23
|
+
- **Valid bug?** Keep as-is
|
|
24
|
+
- **False positive?** Mark as false positive, ask WHY (the pattern that triggered it incorrectly)
|
|
25
|
+
- **Severity wrong?** Adjust severity
|
|
26
|
+
|
|
27
|
+
### 3. Capture Missed Bugs
|
|
28
|
+
|
|
29
|
+
Ask: "Did you find any bugs manually that the session missed?"
|
|
30
|
+
|
|
31
|
+
For each missed bug:
|
|
32
|
+
- Record it as an additional finding
|
|
33
|
+
- Extract the PATTERN: What should have been checked? Which heuristic would have caught it?
|
|
34
|
+
|
|
35
|
+
### 4. Rate Session Quality
|
|
36
|
+
|
|
37
|
+
Ask user to rate (1-5):
|
|
38
|
+
- Coverage completeness
|
|
39
|
+
- Bug detection accuracy
|
|
40
|
+
- Report quality
|
|
41
|
+
|
|
42
|
+
### 5. Update Learned Patterns
|
|
43
|
+
|
|
44
|
+
Append to `data/knowledge/learned-patterns.md`:
|
|
45
|
+
|
|
46
|
+
**False positives → add to skip list:**
|
|
47
|
+
```markdown
|
|
48
|
+
## False Positive Patterns (skip these)
|
|
49
|
+
- [NEW] <description of what was incorrectly flagged and why>
|
|
50
|
+
```
|
|
51
|
+
|
|
52
|
+
**Missed bugs → add to must-check list:**
|
|
53
|
+
```markdown
|
|
54
|
+
## Missed Bug Patterns (always check these)
|
|
55
|
+
- [NEW] <description of what was missed and the pattern to always check>
|
|
56
|
+
```
|
|
57
|
+
|
|
58
|
+
**Domain insights → add to domain section:**
|
|
59
|
+
```markdown
|
|
60
|
+
## Domain-Specific Insights
|
|
61
|
+
### <domain>
|
|
62
|
+
- [NEW] <insight learned from this session>
|
|
63
|
+
```
|
|
64
|
+
|
|
65
|
+
### 6. Update Session Index
|
|
66
|
+
|
|
67
|
+
Update the session's row in `output/sessions/INDEX.md` with feedback status.
|
|
68
|
+
|
|
69
|
+
### 7. Summary
|
|
70
|
+
|
|
71
|
+
Present to user:
|
|
72
|
+
- Changes made (false positives removed, patterns added)
|
|
73
|
+
- How this will improve future sessions
|
|
@@ -0,0 +1,80 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: qa-explore-quick
|
|
3
|
+
description: >
|
|
4
|
+
Quick focused exploratory testing session on a single page or feature (~15 min).
|
|
5
|
+
No full site mapping — goes directly to the target, applies heuristics, reports findings.
|
|
6
|
+
Use when user says: "quick check", "test this page", "quick explore", or wants a fast review.
|
|
7
|
+
allowed-tools: Bash(playwright-cli:*), Bash(npx playwright-cli:*), Read, Write, Glob, Grep
|
|
8
|
+
---
|
|
9
|
+
|
|
10
|
+
# Quick Exploratory Testing Session
|
|
11
|
+
|
|
12
|
+
You are a **Principal QA Engineer** doing a focused 15-minute exploratory session on a specific page or feature.
|
|
13
|
+
|
|
14
|
+
## Input
|
|
15
|
+
|
|
16
|
+
- **URL**: The specific page to test (required)
|
|
17
|
+
- **focus**: What to look for (optional — e.g., "forms", "accessibility", "navigation")
|
|
18
|
+
|
|
19
|
+
## Flow
|
|
20
|
+
|
|
21
|
+
### 1. Setup (~1 min)
|
|
22
|
+
```bash
|
|
23
|
+
playwright-cli open <url>
|
|
24
|
+
playwright-cli snapshot
|
|
25
|
+
playwright-cli console error
|
|
26
|
+
playwright-cli network
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
Create session dir: `output/sessions/<date>-quick-<target>/`
|
|
30
|
+
|
|
31
|
+
### 2. Quick Analysis (~2 min)
|
|
32
|
+
From the snapshot, identify:
|
|
33
|
+
- Forms and interactive elements
|
|
34
|
+
- Navigation and links
|
|
35
|
+
- Images and media
|
|
36
|
+
- Error states visible
|
|
37
|
+
|
|
38
|
+
### 3. Focused Testing (~10 min)
|
|
39
|
+
|
|
40
|
+
Based on what's on the page, apply relevant heuristics:
|
|
41
|
+
|
|
42
|
+
**If forms present:**
|
|
43
|
+
- Happy path → boundary values → negative inputs → XSS/injection
|
|
44
|
+
- Check validation messages, required fields, error states
|
|
45
|
+
|
|
46
|
+
**If navigation/links:**
|
|
47
|
+
- Click all links, check for dead links, verify back/forward
|
|
48
|
+
- Check active states, breadcrumbs, consistency
|
|
49
|
+
|
|
50
|
+
**If content heavy:**
|
|
51
|
+
- Check headings hierarchy, alt text, contrast
|
|
52
|
+
- Test responsive: `playwright-cli resize 375 667` then `playwright-cli resize 1280 720`
|
|
53
|
+
|
|
54
|
+
**Always check:**
|
|
55
|
+
- `playwright-cli console error` — JS errors
|
|
56
|
+
- `playwright-cli network` — failed requests
|
|
57
|
+
- `playwright-cli press Tab` (x5) — focus order and visibility
|
|
58
|
+
- Responsive mobile: `playwright-cli resize 375 667`
|
|
59
|
+
|
|
60
|
+
For each bug: `playwright-cli screenshot` and document immediately.
|
|
61
|
+
|
|
62
|
+
### 4. Report (~2 min)
|
|
63
|
+
|
|
64
|
+
```bash
|
|
65
|
+
playwright-cli close
|
|
66
|
+
```
|
|
67
|
+
|
|
68
|
+
Write `output/sessions/<session-dir>/quick-report.md`:
|
|
69
|
+
- Page tested, date, duration
|
|
70
|
+
- Bugs found (inline, using bug report template)
|
|
71
|
+
- Observations
|
|
72
|
+
- Recommendations
|
|
73
|
+
|
|
74
|
+
Present summary to user.
|
|
75
|
+
|
|
76
|
+
## Rules
|
|
77
|
+
- 15 minutes max
|
|
78
|
+
- Snapshot before every interaction
|
|
79
|
+
- ONE BUG = ONE finding in report
|
|
80
|
+
- Evidence (screenshot/console/network) for every bug
|
|
@@ -0,0 +1,62 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: qa-explore-report
|
|
3
|
+
description: >
|
|
4
|
+
Generate, regenerate, or reformat reports from existing exploratory testing sessions.
|
|
5
|
+
Use when user says: "show report", "generate report", "reformat bugs", "session summary",
|
|
6
|
+
or wants to review past session findings.
|
|
7
|
+
allowed-tools: Read, Write, Glob, Grep
|
|
8
|
+
---
|
|
9
|
+
|
|
10
|
+
# Exploratory Testing Report Generator
|
|
11
|
+
|
|
12
|
+
## Input
|
|
13
|
+
|
|
14
|
+
- **session**: Session directory name or "latest" (optional — defaults to latest)
|
|
15
|
+
- **format**: Output format (optional — "markdown" default, "summary", "bugs-only")
|
|
16
|
+
|
|
17
|
+
## Flow
|
|
18
|
+
|
|
19
|
+
### 1. Find Session
|
|
20
|
+
|
|
21
|
+
```
|
|
22
|
+
# If "latest" or no session specified:
|
|
23
|
+
Read output/sessions/INDEX.md → find most recent session
|
|
24
|
+
|
|
25
|
+
# If specific session:
|
|
26
|
+
Read output/sessions/<session-dir>/
|
|
27
|
+
```
|
|
28
|
+
|
|
29
|
+
### 2. Read Session Data
|
|
30
|
+
|
|
31
|
+
Read all phase files from the session directory:
|
|
32
|
+
- `charter.md` — session charter
|
|
33
|
+
- `phase-1-discovery.md` — discovery findings
|
|
34
|
+
- `phase-2-functional.md` — functional testing findings
|
|
35
|
+
- `phase-3-edge-cases.md` — edge case findings
|
|
36
|
+
- `session-log.md` — full session log
|
|
37
|
+
- `bugs/BUG-*.md` — all bug reports
|
|
38
|
+
- `coverage-map.md` — coverage data
|
|
39
|
+
|
|
40
|
+
### 3. Generate Report
|
|
41
|
+
|
|
42
|
+
Based on requested format:
|
|
43
|
+
|
|
44
|
+
**markdown** (default): Full session report following `data/templates/session-report.md`
|
|
45
|
+
- Session metadata, charter summary, stats
|
|
46
|
+
- Coverage map, bugs grouped by severity
|
|
47
|
+
- Observations, questions, recommendations
|
|
48
|
+
|
|
49
|
+
**summary**: Brief executive summary
|
|
50
|
+
- Target, date, duration
|
|
51
|
+
- Bug count by severity
|
|
52
|
+
- Top 3 findings
|
|
53
|
+
- Key recommendation
|
|
54
|
+
|
|
55
|
+
**bugs-only**: Just the bug list
|
|
56
|
+
- All bugs sorted by severity
|
|
57
|
+
- One-line summary each with link to full report
|
|
58
|
+
|
|
59
|
+
### 4. Write Output
|
|
60
|
+
|
|
61
|
+
Save to `output/sessions/<session-dir>/session-report.md` (or specified filename).
|
|
62
|
+
Present to user.
|
|
@@ -0,0 +1,198 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: qa-gather
|
|
3
|
+
description: >
|
|
4
|
+
Gather and analyze requirements from various sources to prepare context for exploratory
|
|
5
|
+
testing sessions. Collects from Jira tickets, Confluence pages, design docs, PRs,
|
|
6
|
+
acceptance criteria, pasted text, URLs — and produces structured context that /qa-explore consumes.
|
|
7
|
+
Use when user says: "gather requirements", "prepare context", "analyze this ticket",
|
|
8
|
+
"what should I test", or provides requirements documents before an explore session.
|
|
9
|
+
allowed-tools: Read, Write, Glob, Grep, WebFetch, Bash(git:*)
|
|
10
|
+
---
|
|
11
|
+
|
|
12
|
+
# Requirements Gathering & Analysis for Exploratory Testing
|
|
13
|
+
|
|
14
|
+
You are a **Senior QA Analyst** preparing context for an exploratory testing session. Your job is to collect requirements from whatever sources are available, analyze them for completeness and testability, and produce a structured context file that the `/qa-explore` skill can consume.
|
|
15
|
+
|
|
16
|
+
## Quick Start
|
|
17
|
+
|
|
18
|
+
```
|
|
19
|
+
# Analyze a requirements document
|
|
20
|
+
/qa-gather requirements.md
|
|
21
|
+
|
|
22
|
+
# Analyze from a URL (Jira-style ticket page, wiki, etc.)
|
|
23
|
+
/qa-gather https://jira.company.com/browse/PROJ-123
|
|
24
|
+
|
|
25
|
+
# Analyze pasted text
|
|
26
|
+
/qa-gather
|
|
27
|
+
> "We're building a new checkout flow that supports Visa and Mastercard.
|
|
28
|
+
> Users should enter shipping address, select payment, and get confirmation
|
|
29
|
+
> with a unique order ID. The payment service was refactored in PR #456."
|
|
30
|
+
|
|
31
|
+
# Analyze a local file (design doc, spec, PR description)
|
|
32
|
+
/qa-gather path/to/design-spec.md
|
|
33
|
+
|
|
34
|
+
# Combine multiple sources
|
|
35
|
+
/qa-gather --jira PROJ-123 --pr 456 --design mockup.png
|
|
36
|
+
```
|
|
37
|
+
|
|
38
|
+
## What This Skill Does
|
|
39
|
+
|
|
40
|
+
1. **Collects** information from provided sources
|
|
41
|
+
2. **Analyzes** for completeness, ambiguity, and testability
|
|
42
|
+
3. **Extracts** acceptance criteria, risk areas, change scope
|
|
43
|
+
4. **Identifies gaps** — what's missing from the requirements that should be there
|
|
44
|
+
5. **Outputs** a structured context file for `/qa-explore --context`
|
|
45
|
+
|
|
46
|
+
## Input Sources
|
|
47
|
+
|
|
48
|
+
### Source: Local File
|
|
49
|
+
Read the file and extract:
|
|
50
|
+
- Feature description
|
|
51
|
+
- Acceptance criteria (look for "AC:", "Given/When/Then", numbered criteria, checkboxes)
|
|
52
|
+
- Technical details (APIs, data models, components mentioned)
|
|
53
|
+
- Assumptions and constraints
|
|
54
|
+
|
|
55
|
+
### Source: URL
|
|
56
|
+
Fetch the URL via WebFetch and extract the same elements. Works with:
|
|
57
|
+
- Jira-like ticket pages (summary, description, acceptance criteria, labels, status)
|
|
58
|
+
- Confluence/wiki pages (specs, design docs, meeting notes)
|
|
59
|
+
- GitHub/GitLab PR descriptions (what changed, why, linked issues)
|
|
60
|
+
- Any web page with requirements or spec content
|
|
61
|
+
|
|
62
|
+
### Source: Pasted Text
|
|
63
|
+
Parse the user's inline text for requirements information. People paste:
|
|
64
|
+
- Slack conversations about what to build
|
|
65
|
+
- Email threads with stakeholder requests
|
|
66
|
+
- Meeting notes with decisions
|
|
67
|
+
- Verbal descriptions of what the feature should do
|
|
68
|
+
|
|
69
|
+
### Source: Git/PR
|
|
70
|
+
If a git repo is available:
|
|
71
|
+
```bash
|
|
72
|
+
git log --oneline -20 # Recent changes
|
|
73
|
+
git diff main...HEAD # What changed on this branch
|
|
74
|
+
```
|
|
75
|
+
Extract: files changed, components affected, commit messages describing intent.
|
|
76
|
+
|
|
77
|
+
### Source: Multiple Combined
|
|
78
|
+
When multiple sources are provided, merge them into a unified context. Resolve conflicts by noting both versions.
|
|
79
|
+
|
|
80
|
+
## Analysis Process
|
|
81
|
+
|
|
82
|
+
### Step 1: Extract Raw Content
|
|
83
|
+
Read/fetch all provided sources. Identify:
|
|
84
|
+
- **Feature name/title**
|
|
85
|
+
- **Description** (what is being built/changed)
|
|
86
|
+
- **Acceptance criteria** (explicit or implicit)
|
|
87
|
+
- **Technical scope** (which components, APIs, pages are involved)
|
|
88
|
+
- **User stories** (who does what, why)
|
|
89
|
+
|
|
90
|
+
### Step 2: Analyze for Completeness
|
|
91
|
+
Compare extracted requirements against the relevant domain checklist (read from `data/domains/`):
|
|
92
|
+
|
|
93
|
+
**Ask these questions:**
|
|
94
|
+
- Are all acceptance criteria testable? (can you verify each one with a specific action?)
|
|
95
|
+
- Are edge cases mentioned? (what about empty states, errors, boundaries?)
|
|
96
|
+
- Are non-functional requirements specified? (performance, security, accessibility?)
|
|
97
|
+
- Is the user journey complete? (does it cover the full flow, not just one screen?)
|
|
98
|
+
- Are error scenarios defined? (what happens when things go wrong?)
|
|
99
|
+
- Is the data model clear? (what gets created, modified, deleted?)
|
|
100
|
+
|
|
101
|
+
**Flag gaps:**
|
|
102
|
+
```
|
|
103
|
+
[GAP] No error handling defined — what happens when payment fails?
|
|
104
|
+
[GAP] No mention of mobile/responsive behavior
|
|
105
|
+
[GAP] Acceptance criteria says "user can checkout" but doesn't specify: with what payment methods? Is address required?
|
|
106
|
+
[AMBIGUITY] "Fast checkout" — what is "fast"? Under 3 seconds? Under 5?
|
|
107
|
+
[MISSING AC] No acceptance criteria for: empty cart, duplicate submission, session timeout
|
|
108
|
+
```
|
|
109
|
+
|
|
110
|
+
### Step 3: Extract Test Scenarios
|
|
111
|
+
From the requirements, derive:
|
|
112
|
+
- **Happy path scenarios** (what should work)
|
|
113
|
+
- **Edge case scenarios** (boundaries, limits, unusual inputs)
|
|
114
|
+
- **Negative scenarios** (what should be rejected, error states)
|
|
115
|
+
- **Data integrity scenarios** (does the math add up? is data consistent?)
|
|
116
|
+
|
|
117
|
+
### Step 4: Assess Risk
|
|
118
|
+
Based on what was gathered:
|
|
119
|
+
- **Change risk**: How much is changing? New feature vs modification vs refactor?
|
|
120
|
+
- **Complexity risk**: How many components/services involved?
|
|
121
|
+
- **Domain risk**: Is this in a high-risk area (payments, auth, data)?
|
|
122
|
+
- **Historical risk**: Has this area had bugs before? (check learned-patterns.md)
|
|
123
|
+
|
|
124
|
+
### Step 5: Write Output
|
|
125
|
+
|
|
126
|
+
Save to `output/context/<feature-name>-context.md`:
|
|
127
|
+
|
|
128
|
+
```markdown
|
|
129
|
+
# Exploratory Testing Context
|
|
130
|
+
|
|
131
|
+
## Source
|
|
132
|
+
**Gathered from:** [list of sources]
|
|
133
|
+
**Date:** [today]
|
|
134
|
+
**Prepared by:** QA Gather Agent
|
|
135
|
+
|
|
136
|
+
## Feature Summary
|
|
137
|
+
**Name:** [feature name]
|
|
138
|
+
**Description:** [what it does in 2-3 sentences]
|
|
139
|
+
**Type:** [new feature | enhancement | bug fix | refactor]
|
|
140
|
+
**Components affected:** [list of pages, APIs, services]
|
|
141
|
+
|
|
142
|
+
## Acceptance Criteria
|
|
143
|
+
- [ ] [AC 1 — extracted from requirements]
|
|
144
|
+
- [ ] [AC 2]
|
|
145
|
+
- [ ] [AC 3]
|
|
146
|
+
_(Each becomes a test checkpoint during exploration)_
|
|
147
|
+
|
|
148
|
+
## Derived Test Scenarios
|
|
149
|
+
### Happy Path
|
|
150
|
+
1. [scenario]
|
|
151
|
+
2. [scenario]
|
|
152
|
+
|
|
153
|
+
### Edge Cases
|
|
154
|
+
1. [scenario]
|
|
155
|
+
2. [scenario]
|
|
156
|
+
|
|
157
|
+
### Negative / Error Cases
|
|
158
|
+
1. [scenario]
|
|
159
|
+
2. [scenario]
|
|
160
|
+
|
|
161
|
+
### Data Integrity
|
|
162
|
+
1. [what to verify]
|
|
163
|
+
2. [what numbers should add up]
|
|
164
|
+
|
|
165
|
+
## What Changed (if PR/commits provided)
|
|
166
|
+
- [file/component]: [what changed]
|
|
167
|
+
- [file/component]: [what changed]
|
|
168
|
+
**Focus testing on:** [changed areas]
|
|
169
|
+
|
|
170
|
+
## Risk Assessment
|
|
171
|
+
| Area | Risk Level | Reason |
|
|
172
|
+
|------|-----------|--------|
|
|
173
|
+
| [area] | High | [why] |
|
|
174
|
+
| [area] | Medium | [why] |
|
|
175
|
+
|
|
176
|
+
## Gaps & Concerns
|
|
177
|
+
- [GAP] [what's missing from requirements]
|
|
178
|
+
- [AMBIGUITY] [what's unclear]
|
|
179
|
+
- [MISSING AC] [acceptance criteria that should exist but don't]
|
|
180
|
+
|
|
181
|
+
## Suggested Session Focus
|
|
182
|
+
**Primary focus:** [what to test most deeply]
|
|
183
|
+
**Secondary focus:** [what to test at medium depth]
|
|
184
|
+
**Quick check only:** [what needs minimal attention]
|
|
185
|
+
**Skip:** [what's out of scope for this session]
|
|
186
|
+
|
|
187
|
+
## How to Use This Context
|
|
188
|
+
Run: `/qa-explore <url> --context output/context/<feature-name>-context.md`
|
|
189
|
+
```
|
|
190
|
+
|
|
191
|
+
## Rules
|
|
192
|
+
|
|
193
|
+
1. **Never block on missing sources** — work with whatever is provided, flag what's missing
|
|
194
|
+
2. **Always identify gaps** — the most valuable output is what the requirements DON'T say
|
|
195
|
+
3. **Be specific in test scenarios** — "test checkout" is useless; "add 2 items, apply coupon, verify total = items - discount + tax" is useful
|
|
196
|
+
4. **Match domain checklist** — always compare against `data/domains/<domain>.md` completeness requirements
|
|
197
|
+
5. **Acceptance criteria must be testable** — if an AC is vague ("system should be fast"), flag it and suggest a testable version ("page loads in under 3 seconds")
|
|
198
|
+
6. **Output is for /qa-explore** — format it so the explore skill can consume it directly as `--context`
|
|
@@ -0,0 +1,91 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: qa-knowledge-add
|
|
3
|
+
description: >
|
|
4
|
+
Add new QA knowledge to the knowledge base — heuristics, techniques, checklists,
|
|
5
|
+
references, or patterns. Supports text input, URLs, and file ingestion.
|
|
6
|
+
Use when user says: "add knowledge", "add heuristic", "learn this", "save this technique",
|
|
7
|
+
"add to knowledge base", or provides QA documentation to ingest.
|
|
8
|
+
allowed-tools: Read, Write, Glob, Grep, WebFetch
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
# Add QA Knowledge
|
|
12
|
+
|
|
13
|
+
## Input Options
|
|
14
|
+
|
|
15
|
+
1. **Text**: User pastes a heuristic, technique, article excerpt
|
|
16
|
+
2. **URL**: User provides a URL to documentation — fetch and extract
|
|
17
|
+
3. **File**: User provides a local file path to ingest
|
|
18
|
+
4. **Session pattern**: Extract patterns from recent session bugs/findings
|
|
19
|
+
|
|
20
|
+
## Flow
|
|
21
|
+
|
|
22
|
+
### 1. Parse Input
|
|
23
|
+
|
|
24
|
+
Determine the input type and extract the raw content.
|
|
25
|
+
For URLs: use WebFetch to retrieve and summarize the content.
|
|
26
|
+
|
|
27
|
+
### 2. Classify Entry Type
|
|
28
|
+
|
|
29
|
+
Determine the best type:
|
|
30
|
+
- **heuristic**: A named method for deciding what/how to test (e.g., SFDIPOT, Goldilocks)
|
|
31
|
+
- **technique**: A specific testing technique with steps (e.g., Boundary Value Analysis)
|
|
32
|
+
- **checklist**: A list of items to verify (e.g., WCAG checklist)
|
|
33
|
+
- **reference**: A pointer to external documentation with key takeaways (e.g., OWASP Top 10)
|
|
34
|
+
- **pattern**: A learned pattern from real-world testing (e.g., "login forms often miss autocomplete")
|
|
35
|
+
|
|
36
|
+
### 3. Structure as YAML
|
|
37
|
+
|
|
38
|
+
Create entry following the schema:
|
|
39
|
+
|
|
40
|
+
```yaml
|
|
41
|
+
id: <type>-<slug>
|
|
42
|
+
version: "<current_version>"
|
|
43
|
+
type: <heuristic|technique|checklist|reference|pattern>
|
|
44
|
+
name: "<Name>"
|
|
45
|
+
description: "<One-line description>"
|
|
46
|
+
author: "<Author if known>"
|
|
47
|
+
source: "<Source if known>"
|
|
48
|
+
source_url: "<URL if available>"
|
|
49
|
+
tags: [<relevant tags>]
|
|
50
|
+
domains: [all] # or specific domains
|
|
51
|
+
priority: <high|medium|low>
|
|
52
|
+
added: "<today's date>"
|
|
53
|
+
updated: "<today's date>"
|
|
54
|
+
|
|
55
|
+
content:
|
|
56
|
+
summary: "<Brief summary>"
|
|
57
|
+
# ... type-specific content structure
|
|
58
|
+
```
|
|
59
|
+
|
|
60
|
+
### 4. Ask User to Review
|
|
61
|
+
|
|
62
|
+
Present the structured entry and ask:
|
|
63
|
+
- Is the classification correct?
|
|
64
|
+
- Any tags to add/change?
|
|
65
|
+
- Which domains does this apply to?
|
|
66
|
+
- Priority level?
|
|
67
|
+
|
|
68
|
+
### 5. Determine Release Version
|
|
69
|
+
|
|
70
|
+
Read `data/knowledge/manifest.yml` for current version.
|
|
71
|
+
- If adding to existing release: place in current version's entries/
|
|
72
|
+
- If user wants a new release: bump version, create new release directory
|
|
73
|
+
|
|
74
|
+
Default: add to current release unless user specifies otherwise.
|
|
75
|
+
|
|
76
|
+
### 6. Write Files
|
|
77
|
+
|
|
78
|
+
1. Write YAML entry to `data/knowledge/releases/<version>/entries/<id>.yml`
|
|
79
|
+
(or `data/knowledge/custom/<id>.yml` for user-custom entries)
|
|
80
|
+
2. Update `data/knowledge/manifest.yml`:
|
|
81
|
+
- Increment stats for the entry type
|
|
82
|
+
- Add to loading rules (always, by_domain, or by_tag)
|
|
83
|
+
3. Update `data/knowledge/changelog.yml`:
|
|
84
|
+
- Add entry to current release's `entries_added` list
|
|
85
|
+
|
|
86
|
+
### 7. Confirm
|
|
87
|
+
|
|
88
|
+
Tell user:
|
|
89
|
+
- What was added (name, type, location)
|
|
90
|
+
- How it will be used (which sessions will load it, based on loading rules)
|
|
91
|
+
- Current knowledge base stats
|
|
@@ -0,0 +1,54 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: qa-knowledge-list
|
|
3
|
+
description: >
|
|
4
|
+
Browse and search the QA knowledge base. List entries by type, domain, or tag.
|
|
5
|
+
Show changelog and stats.
|
|
6
|
+
Use when user says: "list knowledge", "show heuristics", "what's in the knowledge base",
|
|
7
|
+
"knowledge stats", "show changelog".
|
|
8
|
+
allowed-tools: Read, Glob, Grep
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
# Browse QA Knowledge Base
|
|
12
|
+
|
|
13
|
+
## Commands
|
|
14
|
+
|
|
15
|
+
### List All
|
|
16
|
+
Read `data/knowledge/manifest.yml` and display:
|
|
17
|
+
- Total entries by type (heuristics, techniques, checklists, references, patterns)
|
|
18
|
+
- Active releases
|
|
19
|
+
- Last updated date
|
|
20
|
+
|
|
21
|
+
Then list all entries grouped by type:
|
|
22
|
+
```
|
|
23
|
+
## Heuristics (N)
|
|
24
|
+
- SFDIPOT - Product Elements (v0.1.0) [high] [tags: exploration, what-to-test]
|
|
25
|
+
- FEW HICCUPPS - Consistency Oracles (v0.1.0) [high] [tags: oracles, recognize-problems]
|
|
26
|
+
...
|
|
27
|
+
|
|
28
|
+
## Techniques (N)
|
|
29
|
+
...
|
|
30
|
+
```
|
|
31
|
+
|
|
32
|
+
### Filter by Domain
|
|
33
|
+
`/qa-knowledge-list --domain ecommerce`
|
|
34
|
+
Show only entries where `domains` includes the specified domain or "all".
|
|
35
|
+
|
|
36
|
+
### Filter by Tag
|
|
37
|
+
`/qa-knowledge-list --tag security`
|
|
38
|
+
Show only entries with the specified tag.
|
|
39
|
+
|
|
40
|
+
### Filter by Type
|
|
41
|
+
`/qa-knowledge-list --type heuristic`
|
|
42
|
+
Show only entries of the specified type.
|
|
43
|
+
|
|
44
|
+
### Show Entry Detail
|
|
45
|
+
`/qa-knowledge-list --entry heuristic-sfdipot`
|
|
46
|
+
Read and display the full YAML entry content.
|
|
47
|
+
|
|
48
|
+
### Show Changelog
|
|
49
|
+
`/qa-knowledge-list --changelog`
|
|
50
|
+
Read `data/knowledge/changelog.yml` and display recent changes.
|
|
51
|
+
|
|
52
|
+
### Show Stats
|
|
53
|
+
`/qa-knowledge-list --stats`
|
|
54
|
+
Display from manifest: entry counts, release history, loading strategy summary.
|