Skip to content
Agentmart
Submit a tool

diagnose

Check whether Summation is connected and what data is visible.

Skill by summationai

IndexedMIT
Write a review

Chalk Labs

Need help deploying diagnose?

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.

Book a call

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/summationai-diagnose

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.

We use your email only for this newsletter. Privacy

About

Check whether Summation is connected and what data is visible. Use when tools fail, sign-in seems broken, or the user asks if setup is OK.

Use cases: data

No 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/diagnose

What's inside

Skill name
diagnose
Description
Check whether Summation is connected and what data is visible. Use when tools fail, sign-in seems broken, or the user asks if setup is OK.
License
MIT
Instructions
47 lines in SKILL.md · view on GitHub

Before installing

  • Instructions call the network

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Summation Diagnose

Give a **plain-language health check** for customers and data scientists — not an API essay.

## 1. Identity

Call **`whoami`** on **`summation`**.

| Result | What to tell the user |
|---|---|
| Identity + org | “You’re signed in as … in org …” |
| Needs sign-in / 401 | Hand off to the `signin` skill |
| Tools missing | Enable/reload the **summation** plugin and restart the host |

## 2. What’s visible

As available: `get_org`, `list_projects`, `get_default_project`, `list_data_connections`, `list_connection_datasets` / `search_tables`.

Short card:

- Who / org  
- Connections (friendly names)  
- Tables ready for analysis (friendly names)  
- 2–3 sample questions that fit **those** tables  

If empty: “You’re signed in, but there’s no business data yet” → the `connect` skill or Connections in the web app.

## 3. Interpreting problems (user language)

- **Can’t authenticate** → sign in again in the browser.  
- **Signed in but no data** → connect a source in Summation, then attach tables with clear names.  
- **Permission denied** → their role/org may not allow that action; try another org (sign out / sign in after switching in the web app) or ask an admin.  
- **Long report / analysis** → still normal for several minutes; keep the user informed.  
- If support is needed and a `request_id` exists, include it **after** a plain explanation.

## 4. CLI

sumcli is the preferred surface when a shell is available (plugin minimum **0.1.3**); MCP is the fallback for shell-less hosts. When a shell is present, also check the CLI session: `sumcli auth whoami` — 401 → `sumcli auth login` (separate credential; a successful MCP sign-in does not sign in the CLI). If sumcli is missing or failed: follow `../api/references/sumcli.md` — install at first need, after an explicit yes. On Windows use the PowerShell or cmd.exe bootstrap, never `curl | sh`.

## Rules

- Do **not** download OpenAPI or debug connector key names here.  
- Do **not** dump internal tool ids into chat.  
- Do **not** run `python3 ../api/scripts/sum_api.py doctor` (or any relative `../api/...` path) — relative paths break when skills mount as `summation:api`.  
- If they ask “is X supported?”, fetch **`https://docs.summation.com/llms.txt`** then the linked page (see `../api/references/product.md`).

From summationai/summation-plugin, MIT.

More from summationai/summation-plugin

Signals

Stars
0
Forks
2
Open issues
0
Last commit (this folder)
Aug 19, 2026 (2 months ago)
Last release
Aug 19, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from summationai

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 diagnose 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying diagnose?

CallGet help
Cite this page

diagnose skill. Agent Mart. https://agentmart.dev/skills/summationai-diagnose (last updated 2026-10-24)