QA
Use this workflow for verification and test quality work.
Domain Expertise
Three industry-canonical frameworks shape every QA task in this skill.
Heuristic Test Strategy Model (Bach / Kaner)
Questioning lenses for test design. Walk through each mnemonic for any new feature to surface test conditions before writing tests.
| Mnemonic |
Lenses |
Use for |
| SFDPOT ("San Francisco Depot") |
Structure, Function, Data, Platform, Operations, Time |
Product coverage — what to test |
| CIDTESTD |
Capability, Inputs, Data, Tests, Errors, Stress, Time, Design |
Test technique selection — how to test |
Reference: James Bach, Rapid Testing Methodology and the HTSM one-page reference.
Session-Based Test Management (Bach 2000)
Structure for exploratory testing.
| Element |
Length |
Contents |
| Charter |
30–120 min |
Focused mission, e.g., "Investigate file upload handling under network failure" |
| Session report |
Written during session |
Time, charter, areas covered, bugs, issues, todo, % time on test design vs investigation vs setup |
| Debrief |
5–15 min |
Review with team lead — surfaces patterns, refines future charters |
Reference: Jonathan Bach, SBTM 2000 paper.
Risk-Based Testing (ISO/IEC/IEEE 29119-1)
Test depth scales with risk score = Probability × Impact (3×3 matrix, H/M/L per axis, 9 cells).
| Probability factors |
Impact factors |
| Code complexity |
Business criticality |
| Change frequency |
User-base size |
| Dev team experience |
Regulatory exposure |
| Third-party dependency churn |
Financial loss potential |
High P × High I → exhaustive testing + automation. Low P × Low I → smoke only.
1. Determine the QA Task
Classify the request as one of:
- Feature verification
- Bug report
- Test creation
- Test improvement
- Exploratory testing
- Coverage review
2. Gather Context
Read:
TESTING.md if present- Root
AGENTS.md
- Relevant scoped
AGENTS.md
- Feature brief, bug report, or changed code in scope
- Existing tests for the target area
3. Execute the Task
Feature Verification
- Map acceptance criteria to observable behavior
- Check happy path, edge cases, and error paths
- Record pass, fail, or partial status with evidence
Bug Report
- Reproduce the issue
- Capture logs, errors, and minimal repro
- Write a structured report using the template below
Bug report template (all fields required unless marked optional):
| Field |
Format / values |
| Title |
One line, includes severity hint, e.g., [BUG] Login button unresponsive after 2 failed attempts |
| Severity |
S1 Critical / S2 Major / S3 Minor / S4 Cosmetic (impact on system) |
| Priority |
P1 / P2 / P3 / P4 (urgency to fix — separate from severity) |
| Steps to reproduce (STR) |
Numbered, deterministic |
| Expected behavior |
What should happen |
| Actual behavior |
What happens instead |
| Environment |
OS / browser / app version / build / device / region |
| First seen |
Timestamp + commit / release / build |
| Repro rate |
1/1, 1/10, intermittent, etc. |
| Attachments |
Screenshots / video / logs (attached or linked) |
| Workaround |
If known (optional) |
Test Creation or Improvement
- Identify coverage gaps
- Write or improve tests using the project's existing patterns
- Prefer deterministic tests and narrow scope first
Exploratory Testing
- Identify risky or recently changed areas
- Explore happy path, invalid input, state transitions, and regressions
- Record issues with severity and reproduction steps
Coverage Review
- Review current coverage signals
- Identify important untested logic
- Recommend the next highest-value tests
4. Apply the Quality Gate
Check:
- Existing tests still pass
- New tests are deterministic
- Acceptance criteria are covered where relevant
- Bug reports include evidence and reproduction steps
5. Report
Summarize:
- What was tested
- Issues found
- Tests added or improved
- Coverage impact if relevant
- Recommended next steps
Integration
- Companion skills:
test-strategy, run-tests, test-local
- Common follow-up:
bugfix, feature-dev, pre-commit
1---2name: qa3description: Use this skill when the user asks to validate a feature, write or improve tests, report a bug, or audit acceptance criteria coverage — /qa = QA-task workflows (verification, test creation, bug reports, exploratory). /test-strategy = test design principles + pyramid + coverage targets (knowledge). /test-local = test execution workflow.4context: fork5argument-hint: [feature description, bug report, or test target]6---78# QA910Use this workflow for verification and test quality work.1112## Domain Expertise1314Three industry-canonical frameworks shape every QA task in this skill.1516### Heuristic Test Strategy Model (Bach / Kaner)1718Questioning lenses for test design. Walk through each mnemonic for any new feature to surface test conditions before writing tests.1920| Mnemonic | Lenses | Use for |21|---|---|---|22| **SFDPOT** ("San Francisco Depot") | Structure, Function, Data, Platform, Operations, Time | Product coverage — what to test |23| **CIDTESTD** | Capability, Inputs, Data, Tests, Errors, Stress, Time, Design | Test technique selection — how to test |2425Reference: James Bach, [Rapid Testing Methodology](https://www.satisfice.com/rapid-testing-methodology) and the HTSM one-page reference.2627### Session-Based Test Management (Bach 2000)2829Structure for exploratory testing.3031| Element | Length | Contents |32|---|---|---|33| **Charter** | 30–120 min | Focused mission, e.g., "Investigate file upload handling under network failure" |34| **Session report** | Written during session | Time, charter, areas covered, bugs, issues, todo, % time on test design vs investigation vs setup |35| **Debrief** | 5–15 min | Review with team lead — surfaces patterns, refines future charters |3637Reference: Jonathan Bach, [SBTM 2000 paper](https://www.satisfice.com/download/session-based-test-management).3839### Risk-Based Testing (ISO/IEC/IEEE 29119-1)4041Test depth scales with risk score = **Probability × Impact** (3×3 matrix, H/M/L per axis, 9 cells).4243| Probability factors | Impact factors |44|---|---|45| Code complexity | Business criticality |46| Change frequency | User-base size |47| Dev team experience | Regulatory exposure |48| Third-party dependency churn | Financial loss potential |4950High P × High I → exhaustive testing + automation. Low P × Low I → smoke only.5152## 1. Determine the QA Task5354Classify the request as one of:5556- Feature verification57- Bug report58- Test creation59- Test improvement60- Exploratory testing61- Coverage review6263## 2. Gather Context6465Read:66671. `TESTING.md` if present682. Root `AGENTS.md`693. Relevant scoped `AGENTS.md`704. Feature brief, bug report, or changed code in scope715. Existing tests for the target area7273## 3. Execute the Task7475### Feature Verification7677- Map acceptance criteria to observable behavior78- Check happy path, edge cases, and error paths79- Record pass, fail, or partial status with evidence8081### Bug Report8283- Reproduce the issue84- Capture logs, errors, and minimal repro85- Write a structured report using the template below8687**Bug report template** (all fields required unless marked optional):8889| Field | Format / values |90|---|---|91| Title | One line, includes severity hint, e.g., `[BUG] Login button unresponsive after 2 failed attempts` |92| Severity | `S1 Critical` / `S2 Major` / `S3 Minor` / `S4 Cosmetic` (impact on system) |93| Priority | `P1` / `P2` / `P3` / `P4` (urgency to fix — separate from severity) |94| Steps to reproduce (STR) | Numbered, deterministic |95| Expected behavior | What should happen |96| Actual behavior | What happens instead |97| Environment | OS / browser / app version / build / device / region |98| First seen | Timestamp + commit / release / build |99| Repro rate | `1/1`, `1/10`, intermittent, etc. |100| Attachments | Screenshots / video / logs (attached or linked) |101| Workaround | If known (optional) |102103### Test Creation or Improvement104105- Identify coverage gaps106- Write or improve tests using the project's existing patterns107- Prefer deterministic tests and narrow scope first108109### Exploratory Testing110111- Identify risky or recently changed areas112- Explore happy path, invalid input, state transitions, and regressions113- Record issues with severity and reproduction steps114115### Coverage Review116117- Review current coverage signals118- Identify important untested logic119- Recommend the next highest-value tests120121## 4. Apply the Quality Gate122123Check:124125- Existing tests still pass126- New tests are deterministic127- Acceptance criteria are covered where relevant128- Bug reports include evidence and reproduction steps129130## 5. Report131132Summarize:133134- What was tested135- Issues found136- Tests added or improved137- Coverage impact if relevant138- Recommended next steps139140## Integration141142- Companion skills: `test-strategy`, `run-tests`, `test-local`143- Common follow-up: `bugfix`, `feature-dev`, `pre-commit`
avav25