New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Nteract Diagnostics

by nteract in nteract/nteract

Pull and triage submitted nteract diagnostics archives from Cloudflare using a diagnostics id/token.

BSD-3-ClauseAuto-check passed

Install Nteract Diagnostics

skills CLI
$ npx skills add nteract/nteract --skill nteract-diagnostics -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install nteract/nteract nteract-diagnostics --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/nteract/nteract.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/nteract-diagnostics .claude/skills/nteract-diagnostics && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
nteract-diagnostics
GitHub stars
179
Token cost
~1.1k tokens
SKILL.md length
355 words
Files
2
Skills in repo
10
Repo updated
First seen
Licence
BSD-3-Clause

At a glance

Pull and triage submitted nteract diagnostics archives from Cloudflare using a diagnostics id/token.

  • Investigating submit logs reports
  • SKILL.md covers Fetch Archive, Triage Workflow and Reporting the diagnosis
  • Calls jq, wrangler and rg; needs DIAG_TOKEN
  • Runtimed/notebook/MCP diagnostic archives

What it does

Nteract Diagnostics is an agent skill from nteract/nteract. Pull and triage submitted nteract diagnostics archives from Cloudflare using a diagnostics id/token. Use when investigating "submit logs" reports, runtimed/notebook/MCP diagnostic archives, telemetry diagnostics uploads, or failures where the user gives an id and token.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It works with Cloudflare and Model Context Protocol. The repository describes itself as: We're back! Now firing notebooks out of a t-shirt gun. The licence is BSD-3-Clause.

When your agent uses it

  • Investigating submit logs reports
  • Runtimed/notebook/MCP diagnostic archives
  • Telemetry diagnostics uploads
  • Failures where the user gives an id and token

Example prompts

  • “submit logs”
  • “/nteract-diagnostics”

Requirements

  • A credential in DIAG_TOKEN
  • A credential in OBJECT_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 32e010b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • jq
    • wrangler
    • rg

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use wrangler, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • DIAG_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nteract Diagnostics loads about 1.1k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 355 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from nteract/nteract at commit 32e010b, republished under its BSD-3-Clause licence (© nteract). 355 words, ~1,062 tokens.

Download SKILL.mdSave it as .claude/skills/nteract-diagnostics/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
nteract-diagnostics
description
Pull and triage submitted nteract diagnostics archives from Cloudflare using a diagnostics id/token. Use when investigating "submit logs" reports, runtimed/notebook/MCP diagnostic archives, telemetry diagnostics uploads, or failures where the user gives an id and token.

Nteract Diagnostics

Use this skill to fetch a diagnostics archive from the Cloudflare-backed nteract diagnostics service. You do not need the telemetry repo checkout; Wrangler access to the Runt Prototype Cloudflare account is enough.

Never include the diagnostics token in final output, issue comments, PR comments, logs you paste back, or committed files. The upload row query below intentionally does not select the token.

Fetch Archive

Use a temporary directory outside the repo unless the user asks for durable repo-local artifacts.

bash
export CLOUDFLARE_ACCOUNT_ID=1cfb529b94b3d6cde3aaf49d1d6ed5e6
export DIAG_ID="<paste id here>"
export DIAG_TOKEN="<paste token here>"

mkdir -p "/tmp/nteract-diag-$DIAG_ID"
cd "/tmp/nteract-diag-$DIAG_ID"

wrangler d1 execute telemetry --remote --json --command "
SELECT id, state, object_key, expected_size, uploaded_size, size_limit,
       app_version, commit_sha, platform, arch, channel, source_flow,
       created_at, expires_at, uploaded_at, retained_until
  FROM diagnostics_uploads
 WHERE id = '$DIAG_ID' AND token = '$DIAG_TOKEN'
 LIMIT 1;
" | tee upload-row.json

Check the row before fetching R2:

bash
jq '.[0].results[0] // null' upload-row.json
export DIAG_STATE="$(jq -r '.[0].results[0].state // empty' upload-row.json)"

If no row is returned, report that the diagnostics reference was not found or the token did not match. If DIAG_STATE is not uploaded, report that state and stop.

When uploaded, fetch and extract the archive:

bash
export OBJECT_KEY="$(jq -r '.[0].results[0].object_key // empty' upload-row.json)"

wrangler r2 object get "nteract-diagnostics/$OBJECT_KEY" --remote --file diagnostics.tar.gz
tar -tzf diagnostics.tar.gz | tee entries.txt
mkdir -p extracted
tar -xzf diagnostics.tar.gz -C extracted

If the installed Wrangler rejects --remote for r2 object get, retry the same command without --remote.

Triage Workflow

Start with:

bash
find extracted -maxdepth 3 -type f | sort
jq '.[0].results[0] | del(.token)' upload-row.json

Common archive files include:

  • runtimed.log, runtimed.log.1: daemon lifecycle, kernel/env prep, room sync, crashes.
  • notebook.log, notebook.log.1: desktop app and window-level behavior.
  • mcp-logs/*.log: MCP tool calls, session connect/reconnect, sync readiness.
  • daemon-status.json, doctor.json, system-info.json: health snapshot, runtime version, platform.

Search for high-signal evidence before broad log reading:

bash
rg -n "ERROR|WARN|panic|timed out|timeout|Failed|failed|MissingOps|STARTUP|Daemon exited|Slow runt-mcp tool call|await_session_ready" extracted

Use timestamps to distinguish the reported incident from older noise. Convert Unix timestamps in upload-row.json when useful:

bash
date -u -d "@$(jq -r '.[0].results[0].created_at' upload-row.json)"
date -u -d "@$(jq -r '.[0].results[0].uploaded_at' upload-row.json)"
Show full SKILL.md (151 more words)Show less

Reporting the diagnosis

Keep upload-row.json and entries.txt with the investigation artifacts so the upload metadata (excluding the token) and complete archive inventory remain available. In the reply, explain the likely cause with short evidence snippets and file references. Include metadata and archive entries that help assess the incident, and link the saved artifacts when useful. If the archive does not cover the reported time window, say what is missing and which check comes next.

For example, when logs start after the incident:

The daemon was healthy when these logs were captured, but runtimed.log starts after the reported freeze. This archive can't establish its cause. The next check is the rotated runtimed.log.1 from that time window.

Do not overfit to the first scary error. Check whether the daemon was healthy at capture time, whether the logs include the reported timestamp, and whether later user messages make an earlier error a red herring.

© nteract, BSD-3-Clause. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .agents/skills/nteract-diagnostics of nteract/nteract.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 32e010b

Compare with similar skills

Nteract Diagnostics next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Nteract Diagnostics compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nteract Diagnostics this skillnteract/nteract179—~1.1kAutomated safety check: PassBSD-3-Clause
Agents SDKcloudflare/skills3k2 repos~3kAutomated safety check: PassApache-2.0
BrowserStack Live Testinghandsontable/handsontable22k—~950Automated safety check: PassCustom licence
Browser SearchJohell1NS/browser-search529—~2.5kAutomated safety check: PassMIT
Codex Chatgpt BridgeZhenyu98/codex-chatgpt-bridge277—~4kAutomated safety check: PassMIT
Prepare Cloudflare Production DeploymentLubomirGeorgiev/cloudflare-workers-nextjs-saas-template786—~5.9kAutomated safety check: NotesMIT

Similar skills

  • Agents SDK

    cloudflare/skills

    Official

    Build, debug, or review Cloudflare Agents SDK applications using the agents package.

    3k GitHub starsUsed in 2 repos~3k tokens
    Agent WorkflowsAuto-check passed

  • BrowserStack Live Testing

    handsontable/handsontable

    Opens a live BrowserStack session on a real Android, iOS or desktop browser for a local or public URL, tunneling localhost through Cloudflare when needed.

    22k GitHub stars~950 tokensUpdated today
    Testing & QAAuto-check passed

  • Browser Search

    Johell1NS/browser-search

    Multi-engine web search (SearXNG) + browsing/scraping (Camofox, CloakBrowser).

    529 GitHub stars~2.5k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed

  • Codex Chatgpt Bridge

    Zhenyu98/codex-chatgpt-bridge

    A skill your agent uses when Codex needs to coordinate ChatGPT, Chrome, Cloudflare tunnels, verified bridge Restart/Reboot recovery, or task routing between local code execution and ChatGPT…

    277 GitHub stars~4k tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed

  • Prepare Cloudflare Production Deployment

    LubomirGeorgiev/cloudflare-workers-nextjs-saas-template

    Source-of-truth runbook for preparing this Vinext Cloudflare Workers SaaS template for production deployment.

    786 GitHub stars~5.9k tokensUpdated 2 days ago
    DevOps & CloudAuto-check: notes

  • Observability Triage

    every-app/open-seo

    Triage OpenSEO production errors in Cloudflare Workers Observability — verified query recipes, counting gotchas, and a known-noise filter list applied automatically.

    23k GitHub stars~1.7k tokensUpdated today
    DevOps & CloudAuto-check passed

More from nteract/nteract

All 10 skills in this repo

  • Automerge Sync

    nteract/nteract

    Automerge sync protocol internals, document model (OpSet, ChangeGraph, fork/merge, save/load lifecycle), and higher-level protocol design patterns.

    179 GitHub stars~4.5k tokensUpdated today
    Auto-check passed

  • Daemon Dev

    nteract/nteract

    Develop, debug, and manage the runtimed daemon, Python bindings, and build system.

    179 GitHub stars~3k tokensUpdated today
    Auto-check passed

  • Execution Pipeline

    nteract/nteract

    The end-to-end cell execution pipeline from MCP tool call through daemon to kernel and back.

    179 GitHub stars~2.7k tokensUpdated today
    Auto-check passed

  • Repl

    nteract/nteract

    Use nteract notebooks as a persistent Python REPL. An agent skill from nteract/nteract.

    179 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Testing

    nteract/nteract

    Run tests, verify changes, and collect diagnostics. An agent skill from nteract/nteract.

    179 GitHub stars~2.2k tokensUpdated today
    Auto-check passed

  • Architecture

    nteract/nteract

    Architecture and documentation framing for cross-cutting repo decisions, docs taxonomy placement, ADRs, memos, PRDs, implementation plans, audits, measurements, runbooks, and source-grounded…

    179 GitHub stars~497 tokensUpdated today
    Auto-check passed

Works with

Questions about Nteract Diagnostics

What does Nteract Diagnostics do?

Pull and triage submitted nteract diagnostics archives from Cloudflare using a diagnostics id/token. Nteract Diagnostics is an agent skill from nteract/nteract. Pull and triage submitted nteract diagnostics archives from Cloudflare using a diagnostics id/token.

When should I use Nteract Diagnostics?

Nteract Diagnostics fits situations like: investigating submit logs reports; runtimed/notebook/MCP diagnostic archives; telemetry diagnostics uploads; failures where the user gives an id and token.

How do I install Nteract Diagnostics in Claude Code?

Run `npx skills add nteract/nteract --skill nteract-diagnostics -a claude-code`. Or copy the skill folder (.agents/skills/nteract-diagnostics in nteract/nteract) into .claude/skills/nteract-diagnostics in your project. Claude Code loads it when a task matches its description.

How do I install Nteract Diagnostics in Codex?

Run `npx skills add nteract/nteract --skill nteract-diagnostics -a codex`. Or copy the skill folder (.agents/skills/nteract-diagnostics in nteract/nteract) into .agents/skills/nteract-diagnostics in your project. Codex loads it when a task matches its description.

Can I use Nteract Diagnostics in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add nteract/nteract --skill nteract-diagnostics -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nteract-diagnostics, .gemini/skills/nteract-diagnostics, .github/skills/nteract-diagnostics and .opencode/skills/nteract-diagnostics in your project.

What does Nteract Diagnostics need to run?

Going by SKILL.md and its folder, Nteract Diagnostics needs the command-line tools its instructions call (jq, wrangler and rg) and credentials named DIAG_TOKEN. Our summary lists: A credential in DIAG_TOKEN; A credential in OBJECT_KEY.

Does Nteract Diagnostics access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Nteract Diagnostics safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Nteract Diagnostics use?

Nteract Diagnostics is published under the BSD-3-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Nteract Diagnostics use?

About 1.1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Nteract Diagnostics?

Skills that share tags, products or a category with Nteract Diagnostics: Agents SDK (cloudflare/skills, 3k stars), BrowserStack Live Testing (handsontable/handsontable, 22k stars), Browser Search (Johell1NS/browser-search, 529 stars) and Codex Chatgpt Bridge (Zhenyu98/codex-chatgpt-bridge, 277 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nteract Diagnostics?

nteract (a GitHub organization) maintains it in nteract/nteract, which has 179 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 9, 2026.

Source: nteract/nteract on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.