---
title: "analyst"
description: "Data analyst agent: pipeline checks, query writing, and recurring report integrity"
canonical: https://agentpluginsdirectory.com/plugins/analyst
last-updated: 2026-09-28
---

# analyst
Data analyst agent: pipeline checks, query writing, and recurring report integrity
- Slug: analyst
- Publisher: nanocoai
- Repository: https://github.com/nanocoai/nanoclaw-templates
- Manifest: data/analyst/plugin.json
- Version: 1.0.0
- Category (editorial): databases
- Skills: 5 (pipeline-check, query-writing, report-onboarding, report-spec, schema-and-cleanup)
- MCP servers: 0
- Stars: 16
- Repository created: 2026-06-29
- Repository last pushed: 2026-09-15
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/analyst
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What analyst does, in the publisher's words

A NanoClaw template for a data analyst / reporting assistant serving one principal: keep the reporting pipeline healthy, keep metric definitions consistent, and turn report requests into buildable, validated deliverables. It ships as a seed and grows around one principal's stack, no bundled tools, no hard-wired databases.

Learned state does not live in the template, it lives in memory/, described by ai.nanoco.nanoclaw/context/additional_context/memory-structure.md and built as the agent works. The skills and tasks read from and write to these paths:

- memory/principal.md: who the analyst serves, the platforms and pipelines they own, and where the line sits between handled and escalated.
- memory/conventions/metrics.md: one entry per metric: definition, source, and where it is computed. Metrics computed in two places are the root of most reporting disagreements, so this file records where each one lives.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/nanocoai/nanoclaw-templates/HEAD/data/analyst/README.md

## Skills

- pipeline-check: Check that the scheduled data work behind the reports actually ran and produced something sensible: the daily reshaping scripts, the API pulls, the tables the reports read from. Use each morning before anyone opens a report, when a report looks wrong and nobody knows whether it is the data or the q…
- query-writing: Write the SQL or MongoDB query that answers a question and keeps answering it: the right grain, no fan out, parameterised window, checked against something known. Use when a number is needed that no report carries, when an existing query returns something that looks wrong, when a query is slow or e…
- report-onboarding: Stand up reporting for a new audience, an external client, a business unit, a region, an executive team, end to end: what they need to see, whether the data exists, access and scoping, their place in the pipeline, the standard report set, and validation against numbers they can check themselves.…
- report-spec: Turn a request for a report or a dashboard widget into something buildable: the question it answers, the metric and its definition, where the data comes from, the query shape, and what it will not answer. Use when a new report or dashboard is requested, when an existing one needs a metric added or…
- schema-and-cleanup: Fix data that has gone wrong and change shape without breaking what reads it: duplicates, nulls, inconsistent document shapes, a field that means two things, a column that has to change. Use when a report cannot be built because the data is not in the right shape, when duplicates, nulls or inconsis…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.