data-qa
Audit data quality for analysis, dashboards, or models, checking duplicates, nulls, outliers, joins, freshness, timezone, units, currencies, late-arriving…
Skill by wdzhwsh4067
Chalk Labs
Need help deploying data-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/wdzhwsh4067-data-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, data, security
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/data-qa
What's inside
- Skill name
data-qa- Description
- Audit data quality for analysis, dashboards, or models, checking duplicates, nulls, outliers, joins, freshness, timezone, units, currencies, late-arriving data, schema drift, and source-of-truth conflicts.
- License
- MIT
- Instructions
- 19 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Data QA Use this skill before trusting a dataset or metric. ## Workflow 1. Identify dataset grain, source, owner, refresh schedule, and downstream use. 2. Check row counts, uniqueness, missingness, outliers, referential integrity, freshness, timezone, units, and schema changes. 3. Prioritize issues by decision impact. 4. Create reproducible QA queries or notebook checks. ## Output Return `QA checklist`, `Test queries`, `Issue severity`, `Fix recommendations`, and `Trust level`.
From wdzhwsh4067/data-analyst-skills, MIT.
More from wdzhwsh4067/data-analyst-skills
- 0.471score
data-analyst
wdzhwsh4067
End-to-end data analyst workflow for business, product, operations, and growth questions.
SkillCFreshness: C★ 2Claude Code +9 - 0.471score
experiment-readout
wdzhwsh4067
Analyze and communicate A/B tests or product experiments, including hypothesis, guardrails, sample ratio, metric definitions, effect size, uncertainty…
SkillCFreshness: C★ 2Claude Code +9 - 0.467score
dashboard-spec
wdzhwsh4067
Design dashboard specifications for executives, product teams, sales, finance, operations, and support, including audience, metrics, filters, visuals, refresh…
SkillCFreshness: C★ 2Claude Code +9 - 0.467score
executive-memo
wdzhwsh4067
Turn analysis into executive-ready memos with answer-first summary, evidence, charts to include, assumptions, caveats, recommendation, owner, and next decision.
SkillCFreshness: C★ 2Claude Code +9 - 0.467score
metric-definition
wdzhwsh4067
Define business, product, growth, finance, and operations metrics with grain, denominator, filters, time window, edge cases, owner, and decision use.
SkillCFreshness: C★ 2Claude Code +9 - 0.467score
sql-analysis
wdzhwsh4067
Plan and write SQL analysis for product, business, cohort, funnel, retention, revenue, and operations questions with explicit joins, grain, QA checks, and…
SkillCFreshness: C★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 15, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from wdzhwsh4067
- 0.471score
data-analyst
wdzhwsh4067
End-to-end data analyst workflow for business, product, operations, and growth questions.
SkillCFreshness: C★ 2Claude Code +9 - 0.471score
experiment-readout
wdzhwsh4067
Analyze and communicate A/B tests or product experiments, including hypothesis, guardrails, sample ratio, metric definitions, effect size, uncertainty…
SkillCFreshness: C★ 2Claude Code +9 - 0.467score
metric-definition
wdzhwsh4067
Define business, product, growth, finance, and operations metrics with grain, denominator, filters, time window, edge cases, owner, and decision use.
SkillCFreshness: C★ 2Claude Code +9 - 0.467score
dashboard-spec
wdzhwsh4067
Design dashboard specifications for executives, product teams, sales, finance, operations, and support, including audience, metrics, filters, visuals, refresh…
SkillCFreshness: C★ 2Claude Code +9 - 0.467score
executive-memo
wdzhwsh4067
Turn analysis into executive-ready memos with answer-first summary, evidence, charts to include, assumptions, caveats, recommendation, owner, and next decision.
SkillCFreshness: C★ 2Claude Code +9 - 0.467score
sql-analysis
wdzhwsh4067
Plan and write SQL analysis for product, business, cohort, funnel, retention, revenue, and operations questions with explicit joins, grain, QA checks, and…
SkillCFreshness: C★ 2Claude 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 data-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
data-qa skill. Agent Mart. https://agentmart.dev/skills/wdzhwsh4067-data-qa (last updated 2026-10-24)