warehouse-analysis SKILL.md skillA

warehouse-analysis from tam159/next-role is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add tam159/next-role/warehouse-analysis@git:20260906.5482ae7

Pins git:20260906.5482ae7 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
tam159/next-role
Path
backend/agents/analytics_agent/skills/analytics-agent/warehouse-analysis/SKILL.md
Versions recorded
1
Latest version
git:20260906.5482ae7, committed Sep 6, 2026
Size
5,035 bytes
Repository stars
62
License
MIT

Explore the NextRole ClickHouse warehouse and answer a question with SQL. Read this before writing your first query of a conversation — it carries the discovery loop and the ClickHouse syntax rules that differ from other dialects. Use for any question about product usage, activity, reliability, LLM cost, agent behaviour, users, runs, threads, or messages, and whenever a query errors, returns nothing, or returns a number that looks wrong.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Warehouse analysis

## The loop

Work in small steps and let each one inform the next. Do not write a long query
against a table you have not inspected.

1. **Orient.** `describe_data()` once per conversation. It lists the marts, what
   one row of each means, how large they are, and the syntax rules below.
2. **Inspect.** `describe_data("<table>")` before querying a table for the first
   time. Read the sort key and the caveats; they decide both correctness and
   speed.
3. **Count.** `SELECT count() FROM <table> WHERE <your filter>` — a cheap check
   that your filter matches anything at all, before you build on it.
4. **Sample.** `SELECT * FROM <table> WHERE <filter> LIMIT 5`. Actual values
   settle what enums contain, how dates are shaped, and where NULLs live.
5. **Aggregate.** Now write the real query, with an explicit date window and an
   `ORDER BY`.
6. **Verify.** Check a surprising result from a second angle before reporting
   it: a different grain, a neighbouring week, or a total that should match.

## Writing queries that stay fast

- Always filter on the table's sort key — the date column on every fact.
- Always qualify names: `nextrole_marts.fct_run`.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add tam159/next-role/warehouse-analysis@sha256:3848f948b67f5f50

The line at the top of this page pins the label git:20260906.5482ae7, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_cijzwfe4wzy6xpqr.svg)](https://markdownregistry.com/a/art_cijzwfe4wzy6xpqr)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 6, 2026.

versioncommittedcommitsizeaudit
git:20260906.5482ae7 latest2026-09-06 5482ae7 5,035 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5035 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

tam159/next-role · 62 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_cijzwfe4wzy6xpqr
GET https://markdownregistry.com/api/v1/resolve?ref=tam159/next-role/warehouse-analysis
GET https://markdownregistry.com/api/v1/blob/3848f948b67f5f504b4027f302e4779a09b544816b34426949389de5fe4bcc20

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from tam159/next-role

agent-browser SKILL.md skill
tam159/next-role · .agents/skills/agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
git:20260904.8ecceeb · audit A · 62 stars
archify-review SKILL.md skill
tam159/next-role · .agents/skills/archify-review/SKILL.md · Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions…
git:20261004.49b5e65 · audit A · 62 stars
archify SKILL.md skill
tam159/next-role · .agents/skills/archify/SKILL.md · Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable…
v3.0 · audit A · 62 stars
commit SKILL.md skill
tam159/next-role · .agents/skills/commit/SKILL.md · Stage current changes and create a Conventional Commits-style commit matching this repo's history. Use when the user…
git:20260710.ecf66e2 · audit A · 62 stars
drawio-skill SKILL.md skill
tam159/next-role · .agents/skills/drawio-skill/SKILL.md · Create and edit draw.io/diagrams.net diagrams as editable `.drawio` files. Covers architecture, UML/ERD/sequence, BPMN…
git:20261004.49b5e65 · audit A · 62 stars
frontend-design SKILL.md skill
tam159/next-role · .agents/skills/frontend-design/SKILL.md · Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to…
git:20260904.8ecceeb · audit A · 62 stars
quality SKILL.md skill
tam159/next-role · .agents/skills/quality/SKILL.md · Run the repo's quality gate — pre-commit on the files you changed by default, or the full `pre-commit run --all-files`…
git:20260921.0792dba · audit A · 62 stars
upgrade-backend-deps SKILL.md skill
tam159/next-role · .agents/skills/upgrade-backend-deps/SKILL.md · Upgrade Python backend dependencies to their latest compatible versions. Resolves the lockfile with `uv lock…
git:20260904.adadf35 · audit A · 62 stars
upgrade-frontend-deps SKILL.md skill
tam159/next-role · .agents/skills/upgrade-frontend-deps/SKILL.md · Upgrade the Next.js frontend's pnpm dependencies to their latest versions in verified waves. Inventories with `pnpm…
git:20260921.0792dba · audit A · 62 stars
write-prd SKILL.md skill
tam159/next-role · .agents/skills/write-prd/SKILL.md · Generate a concise PRD for the feature built in the current session and save it to docs/prd/. Use this skill whenever…
git:20260719.ec018ca · audit A · 62 stars
agent-browser SKILL.md skill
tam159/next-role · .claude/skills/agent-browser/SKILL.md · Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages…
git:20260430.c57e7d1 · audit A · 62 stars
archify-review SKILL.md skill
tam159/next-role · .claude/skills/archify-review/SKILL.md · Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions…
git:20261004.49b5e65 · audit A · 62 stars

Every file in tam159/next-role

Browse by kind, by grade A, or by owner.