agentleFS
Sign inStart free
summationaisummationai/summation-plugin/skills/diagnose/SKILL.md

diagnose

Skill0 starsChanged 3 months agoMITView on GitHub

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.

  • Pipes a download into a shell

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use zoom-out, to-prd and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • victorgarciaesgiSkill

    zoom-out

    Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

    Also in 61 projects that use this

  • GoogleSkill

    to-prd

    Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.

    Also in 56 projects that use this

  • GoogleSkill

    to-issues

    Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.

    Also in 53 projects that use this

  • simo97Skill

    edit-article

    The user will invoke this skill to help them edit an article.

    Also in 17 projects that use this

  • simo97Skill

    write-a-skill

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

    Also in 44 projects that use this

  • AnasX7Skill

    setup-pre-commit

    Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

    Also in 27 projects that use this

  • +4 more from simo97

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 174 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call whoami on summation.

    line 12
  2. Very specific:

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

    line 31
  3. Very specific:

    If support is needed and a request_id exists, include it after a plain explanation.

    line 39
  4. Distinctive:

    Do not download OpenAPI or debug connector key names here.

    line 47
  5. Distinctive:

    Do not dump internal tool ids into chat.

    line 48
  6. Very specific:

    Do not run python3 ../api/scripts/sum_api.py doctor (or any relative ../api/...

    line 49
  7. Very specific:

    If they ask “is X supported?”, fetch https://docs.summation.com/llms.txt then the linked page (see ../api/references/product.md).

    line 50

“Common” is measured: kept by at least 6 in 10 of the 174 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Summation Diagnose

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

1. Identity

Call whoami on summation.

ResultWhat to tell the user
Identity + org“You’re signed in as … in org …”
Needs sign-in / 401Hand off to the signin skill
Tools missingEnable/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).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free