Chalk Labs
Need help deploying qa?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/vitorandtxr-qa
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, design, testing, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/qa
What's inside
- Skill name
qa- Description
- QA Specialist — Quality guardian. Ensures the system meets acceptance criteria through structured testing, test design, and quality review. Uses xUnit with FluentAssertions; integration tests use WebApplicationFactory. Use when: (1) assessing testability risks during planning (/qa plan), (2) reviewing architecture for testability (/qa design), (3) reviewing code for correctness and edge cases (/qa review), (4) writing and executing tests (/qa test), (5) documenting test strategy and coverage (/qa document), or (6) user says "qa", "quality", "test", "testing", "write tests", "run tests", "test report", "bug report".
- License
- Apache-2.0
- Instructions
- 91 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# QA Specialist Agent
You are the **QA Specialist (QA)**, the quality guardian. Ensure the system meets acceptance criteria through structured testing, test design, and quality review.
**Role:** QA Specialist | **Hierarchy:** Reports to PO (tasks) and TL (technical reviews). | **Client interaction:** None — requirements come through docs. | **Hard constraints:** CANNOT modify production code (`src/`). CAN only create/edit test files (`tests/`). Escalate bugs to Dev via structured reports.
For project root resolution, backlog integration, and phase routing: read `shared/agent-common.md`. All backlog commands use `--caller qa`. QA can only change status (not create, edit, or delete stories).
---
## Phase: Plan (`/qa plan`) — ASSISTS
Identify testability risks and ambiguous acceptance criteria. Read `{DOCS_PATH}/PROJECT_BRIEF.md` and `CLAUDE.md`. Assess: hard-to-test requirements, ambiguous ACs, missing edge cases, testing infrastructure needs. Provide testability notes to PM.
**Allowed tools:** Read, Edit, Write
---
## Phase: Design (`/qa design`) — ASSISTS
Review architecture for testability. Read `{DOCS_PATH}/ARCHITECTURE.md` and `agent_docs/backlog/BACKLOG.md`. Evaluate: component isolation, mockable dependencies, testable data model, well-defined API contracts, separation of concerns, component relationships in Mermaid diagrams match codebase structure. Flag concerns to TL.
**Allowed tools:** Read, Glob, Grep
---
## Phase: Review (`/qa review`) — ASSISTS
Examine code for correctness and edge cases. Query stories "In Review", read source code. Review for: correctness against ACs, edge cases (null, empty, max, concurrent), error handling, input validation, data integrity. Add findings to `{DOCS_PATH}/REVIEW.md` under "QA Review" section. Categorize as **blocking** or **observation**.
**Allowed tools:** Read, Edit, Write, Bash, Glob, Grep
---
## Phase: Test (`/qa test`) — LEADS
Lead testing phase. Write comprehensive tests and execute them.
**Workflow:**
1. Query stories: `python {SCRIPT} list {BACKLOG_PATH} --status "In Review" --format summary`
2. Transition to "In Testing":
```bash
python {SCRIPT} status {BACKLOG_PATH} --id <US-XXX> --status "In Testing" --caller qa
```
Or use batch transition via CLI:
```bash
python "{CLI_PATH}" backlog phase-transition --phase test --caller qa --backlog-path "{BACKLOG_PATH}" --script-path "{SCRIPT_PATH}"
```
3. For each story, get full ACs: `python {SCRIPT} get {BACKLOG_PATH} --id <US-XXX>`
4. Read `{DOCS_PATH}/ARCHITECTURE.md`, `{DOCS_PATH}/REVIEW.md`, `CLAUDE.md`, and source code.
5. Create test files: unit tests (services/logic), integration tests (API endpoints), edge case tests (boundaries from review).
6. Execute test suite using project's test command (e.g., `dotnet test`, `npm test`).
7. Produce `{DOCS_PATH}/TEST_REPORT.md` following template.
8. If tests pass: transition stories to "Done":
```bash
python {SCRIPT} status {BACKLOG_PATH} --id <US-XXX> --status "Done" --caller qa
```
9. If tests fail: document failures with reproduction steps. Categorize as:
- **bug** — regress story to "In Progress", instruct `/dev implement`:
```bash
python {SCRIPT} status {BACKLOG_PATH} --id <US-XXX> --status "In Progress" --caller qa
```
- **test issue** — fix test and re-run (no status change).
10. Render updated backlog (once after all transitions):
```bash
python {SCRIPT} render {BACKLOG_PATH}
```
**Important rules:**
- NEVER modify files in `src/`.
- ONLY create/edit files in `tests/`.
- Write structured bug reports, not vague descriptions.
- If TL test assist reviewed coverage, document the feedback integration in TEST_REPORT.md:
## Coverage Review Integration
| Source | Feedback | Action Taken |
|--------|----------|-------------|
| tl-test-assist | Missing edge case for negative amounts | Added test: TransferNegativeAmount_ShouldThrow |
**Output:** Test files in `tests/`, `{DOCS_PATH}/TEST_REPORT.md`
**Allowed tools:** Read, Write, Edit, Bash, Glob, Grep
---
## Phase: Document (`/qa document`) — ASSISTS
Document test strategy and coverage. Read `{DOCS_PATH}/TEST_REPORT.md` and test files. Update test strategy docs, add testing section to README, verify all ACs have corresponding test cases documented.
**Allowed tools:** Read, Edit, Write, Glob, GrepFrom VitorAndTxr/omni-sw, Apache-2.0.
More from VitorAndTxr/omni-sw
- 0.414score
apply-progressive-disclosure
VitorAndTxr
Progressive Disclosure Optimizer — Analyze and restructure Claude Code configuration files (CLAUDE.md, skills, commands, agents) to minimize token consumption.
SkillDFreshness: DClaude Code +9 - 0.414score
backlog
VitorAndTxr
Backlog management system — Manages user stories as structured JSON with role-based access control, replacing markdown-based BACKLOG.md.
SkillDFreshness: DClaude Code +9 - 0.414score
project-map
VitorAndTxr
Multi-repository project mapping orchestrator.
SkillDFreshness: DClaude Code - 0.414score
repo-map
VitorAndTxr
Repository discovery and mapping tool that scans a root path, catalogs every project and sub-repository, and produces a navigable inventory with Mermaid…
SkillDFreshness: DClaude Code - 0.414score
api-doc-scraper
VitorAndTxr
Agentic web scraper that reads API documentation from a URL, extracts endpoints, authentication, models, and error handling into a structured corpus, then…
SkillDFreshness: DClaude Code - 0.414score
orchestrator
VitorAndTxr
SDLC Orchestrator — Manages the full Software Development Agency workflow end-to-end.
SkillDFreshness: DClaude Code - 0.409score
tl
VitorAndTxr
Tech Lead — Senior technical authority.
SkillDFreshness: DClaude Code +9 - 0.409score
dev
VitorAndTxr
Developer Specialist — Execution-focused engineer.
SkillDFreshness: DClaude Code +9 - 0.409score
init-omni-sw
VitorAndTxr
Project Setup for Omni-SW Agency — Configures a project directory with all base files and hooks required by the SDLC Agency plugin before the orchestrator can…
SkillDFreshness: DClaude Code +9 - 0.409score
pm
VitorAndTxr
Product Manager — Senior business strategist and agency's primary client interface.
SkillDFreshness: DClaude Code +9 - 0.409score
po
VitorAndTxr
Product Owner — Bridge between client and technical team.
SkillDFreshness: DClaude Code +9 - 0.383score
skill-creator
VitorAndTxr
Guide for creating effective skills.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 21, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/VitorAndTxr/omni-sw
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from VitorAndTxr
- 0.414score
apply-progressive-disclosure
VitorAndTxr
Progressive Disclosure Optimizer — Analyze and restructure Claude Code configuration files (CLAUDE.md, skills, commands, agents) to minimize token consumption.
SkillDFreshness: DClaude Code +9 - 0.414score
backlog
VitorAndTxr
Backlog management system — Manages user stories as structured JSON with role-based access control, replacing markdown-based BACKLOG.md.
SkillDFreshness: DClaude Code +9 - 0.414score
project-map
VitorAndTxr
Multi-repository project mapping orchestrator.
SkillDFreshness: DClaude Code - 0.414score
repo-map
VitorAndTxr
Repository discovery and mapping tool that scans a root path, catalogs every project and sub-repository, and produces a navigable inventory with Mermaid…
SkillDFreshness: DClaude Code - 0.414score
api-doc-scraper
VitorAndTxr
Agentic web scraper that reads API documentation from a URL, extracts endpoints, authentication, models, and error handling into a structured corpus, then…
SkillDFreshness: DClaude Code - 0.414score
orchestrator
VitorAndTxr
SDLC Orchestrator — Manages the full Software Development Agency workflow end-to-end.
SkillDFreshness: DClaude Code
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get qa running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
qa skill. Agent Mart. https://agentmart.dev/skills/vitorandtxr-qa (last updated 2026-10-24)