qa
Enter Q&A mode for answering technical (code, architecture, programming) or business (domain, business logic) questions about the current project.
Skill by bymatej
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/bymatej-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: testing, productivity
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
- Enter Q&A mode for answering technical (code, architecture, programming) or business (domain, business logic) questions about the current project. Use when the user wants a focused Q&A session, asks to "enter Q&A mode", or wants short, fast answers to project questions.
- License
- MIT
- Instructions
- 42 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Q&A Mode You are now in Q&A mode. Stay in this mode until the user says otherwise. ## Rules - Answer each question as briefly as possible - Yes/no if the question allows it - 1-3 sentences max for explanations - No preamble, no trailing summaries, no "great question" - If you don't know, say "don't know" and offer to look it up ## Finding Answers Use whatever tools are available to answer accurately — never guess on factual questions: - Read codebase files directly - Search for symbols, file paths, or patterns across the repo - Query Jira or Confluence if available - Search the web if available and relevant - Use any other installed skills for specialized lookups ## Format | Question type | Answer style | |---------------|--------------| | Yes/no | "Yes." or "No." + one sentence if useful | | How/what | 1-3 sentences, no headers | | Architecture | Short answer + one-line rationale | | Code location | File path + line number | ## Agent compatibility | Feature | Claude Code | Codex / no MCP | |---------|-------------|----------------| | Codebase lookup | Read files, grep, MCP tools | Read files and grep directly | | External context | Jira/Confluence MCP | Skip external sources; note the limitation | | Web search | WebSearch if available | Skip if unavailable | Now wait for the first question.
From bymatej/skills, MIT.
More from bymatej/skills
- 0.529score
mental-model
bymatej
Build a concise, evidence-grounded mental model from an RFC, design document, code change, GitHub pull request, large refactor, or system question.
SkillBFreshness: BClaude Code +9 - 0.474score
auto-grill
bymatej
Stress-tests a plan against the real codebase without manual tab-switching.
SkillCFreshness: CClaude Code +9 - 0.469score
focused-skill-authoring
bymatej
Use when creating or updating skills in this repository so the result stays concise, installable, and portable across coding agents.
SkillCFreshness: CClaude Code +9 - 0.450score
design-an-interface
bymatej
Generate multiple radically different interface designs for a module using parallel sub-agents.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 29, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/bymatej/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from bymatej
- 0.529score
mental-model
bymatej
Build a concise, evidence-grounded mental model from an RFC, design document, code change, GitHub pull request, large refactor, or system question.
SkillBFreshness: BClaude Code +9 - 0.474score
auto-grill
bymatej
Stress-tests a plan against the real codebase without manual tab-switching.
SkillCFreshness: CClaude Code +9 - 0.469score
focused-skill-authoring
bymatej
Use when creating or updating skills in this repository so the result stays concise, installable, and portable across coding agents.
SkillCFreshness: CClaude Code +9 - 0.450score
design-an-interface
bymatej
Generate multiple radically different interface designs for a module using parallel sub-agents.
SkillCFreshness: CClaude Code +9
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/bymatej-qa (last updated 2026-10-24)