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

Create Test Run

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

Create a Kobiton test run from a test case or suite, then offer to monitor it.

MITAuto-check passedTesting & QA

Install Create Test Run

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill create-test-run -a claude-code

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

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace create-test-run --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/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/testing/kobiton-automate/skills/create-test-run .claude/skills/create-test-run && 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
create-test-run
GitHub stars
2.8k
Token cost
~3k tokens
SKILL.md length
1,416 words
Files
1
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Create a Kobiton test run from a test case or suite, then offer to monitor it.

  • Works in 5 steps: Resolve the target and its platform → Fill defaults for anything unspecified → Show the summary and confirm (skip the… → …
  • Gives only partial details (or just a test case id)
  • SKILL.md covers Prerequisites, Overview, Inputs and Steps, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Create Test Run is an agent skill from jeremylongshore/tons-of-skills-marketplace. Create a Kobiton test run from a test case or suite, then offer to monitor it. When the user gives only partial details (or just a test case id), fill the rest with sensible defaults that match the createTestRun schema, show a summary of what will run, and ask to proceed or customize before creating. After the run is created, offer monitoring in a single prompt — monitor + auto-open live remediation (only when the org's live-remediation flag is ON), monitor only, or don't monitor — and hand off to the…

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Runs on any MCP-aware host, including hosts with no local filesystem — this is the plugin's only pure-MCP skill, needing no local file, binary, or shell. Uses…

It sits in Testing & QA, covering Test generation and MCP servers. It works with Model Context Protocol. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Gives only partial details (or just a test case id)
  • Fill the rest with sensible defaults that match the createTestRun schema
  • Show a summary of what will run
  • Customize before creating

Example prompts

  • “s live-remediation flag is ON), monitor only, or don”
  • “create / kick off / start / run a test run”
  • “run test case X on N devices”
  • “/create-test-run”

Requirements

  • Compatibility (from SKILL.md): Runs on any MCP-aware host, including hosts with no local filesystem — this is the plugin's only pure-MCP skill, needing no local file, binary, or shell. Uses the Kobiton MCP tools createTestRun, getTestCase/getTestSuite, listDevices, and getOrgSettings; requires an authenticated Kobiton MCP connection. Delegates monitoring to the monitor-test-run skill (same plugin), which does need a local poller — so on a filesystem-less host, create the run and report its id rather than offering to watch it.
  • Pre-approved tools (allowed-tools): Read, Skill

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Resolve the target and its platform
  2. Fill defaults for anything unspecified
  3. Show the summary and confirm (skip the prompt only if the user already gave full, explicit details)
  4. Create the run
  5. Offer monitoring — one prompt, then delegate

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Skill

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

  • Compatibility

    Runs on any MCP-aware host, including hosts with no local filesystem — this is the plugin's only pure-MCP skill, needing no local file, binary, or shell. Uses the Kobiton MCP tools createTestRun, getTestCase/getTestSuite, listDevices, and getOrgSettings; requires an authenticated Kobiton MCP connection. Delegates monitoring to the monitor-test-run skill (same plugin), which does need a local poller — so on a filesystem-less host, create the run and report its id rather than offering to watch it.

    From compatibility in the SKILL.md frontmatter.

Context cost

Create Test Run loads about 3k tokens when it runs. Until then it costs about 199 tokens; SKILL.md has 1,416 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~199
When it runs · the whole SKILL.md, loaded when a task matches
~3k

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 jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 1,416 words, ~2,963 tokens.

Download SKILL.mdSave it as .claude/skills/create-test-run/SKILL.md (or your agent's skills folder).
name
create-test-run
description
Create a Kobiton test run from a test case or suite, then offer to monitor it. When the user gives only partial details (or just a test case id), fill the rest with sensible defaults that match the createTestRun schema, show a summary of what will run, and ask to proceed or customize before creating. After the run is created, offer monitoring in a single prompt — monitor + auto-open live remediation (only when the org's live-remediation flag is ON), monitor only, or don't monitor — and hand off to the monitor-test-run skill if chosen. Use when the user asks to "create / kick off / start / run a test run", "run test case X on N devices", or similar. Wraps the createTestRun MCP tool (and getOrgSettings / listDevices for defaults); delegates the watch to monitor-test-run.
allowed-tools
Read, Skill
compatibility
Runs on any MCP-aware host, including hosts with no local filesystem — this is the plugin's only pure-MCP skill, needing no local file, binary, or shell. Uses the Kobiton MCP tools createTestRun, getTestCase/getTestSuite, listDevices, and getOrgSettings; requires an authenticated Kobiton MCP connection. Delegates monitoring to the monitor-test-run skill (same plugin), which does need a local poller — so on a filesystem-less host, create the run and report its id rather than offering to watch it.
version
1.0.0
author
Kobiton Inc.
license
MIT
tags
testing, test-run, create, monitoring, live-remediation, kobiton

Prerequisites

Needs only an authenticated Kobiton MCP connection — no local filesystem, no credentials file, no binary, no shell. It is the plugin's only pure-MCP skill, so it is the only one that works where the host supplies nothing else. The monitoring hand-off in Step 5 is the exception: monitor-test-run runs a local poller, so where you can't run a local command at all, create the run and report its id instead of offering to watch it (Step 5 carries the wording). Where you can, hand off and let that skill check its own credentials and streaming options — it degrades rather than refusing. See the Skill compatibility matrix in CLAUDE.md.

Overview

Turn a "run this" request into a created test run with as little friction as the user wants, then offer to watch it. Two phases:

  1. Build + confirm the run. Resolve what to run (test case or suite), on which devices, with what app — filling any unspecified field with a documented default — then show a one-screen summary and create on confirmation.
  2. Offer monitoring once. After creation, present the monitor choice in a single prompt and delegate to monitor-test-run if the user wants it.

Tool naming. Kobiton MCP tools are referenced by bare name (createTestRun, getOrgSettings, listDevices, getTestCase, getTestSuite). The host resolves the prefix (mcp__plugin_automate_kobiton__createTestRun, mcp__kobiton__createTestRun, etc.).

Inputs

InputRequiredNotes
test case id or test suite idone ofA test case id → TEST_CASE selection; a suite id → TEST_SUITE. If the user named neither, ask for it (it's the one thing with no sensible default).
device count / specific devicesnoDefault: 1 device matching the test case/suite platform. The user may say "3 devices", name models, or give UDIDs.
run name / app version / allocationnoAll defaulted (see Step 2).

Steps

1. Resolve the target and its platform
  • A test case id → fetch it (getTestCase) to learn its platform and the app under test. Selection will be TEST_CASE with testCaseSelections: [{ testCaseId, version }] (default to the latest version if the user didn't pin one).
  • A test suite id → fetch it (getTestSuite) for platform + member test cases. Selection will be TEST_SUITE with testSuiteId.
  • If the user gave neither a case nor a suite id, ask for one — there's no sensible default for what to run. Everything else can be defaulted.
2. Fill defaults for anything unspecified

Apply these defaults so a bare request ("run test case X") becomes a complete, valid createTestRun payload. Use the exact enum values below — they are upper-case and case-sensitive; the API rejects lower-case variants (test_case, specific_devices, …).

FieldDefaultNotes
testSelection.typeTEST_CASE (case) / TEST_SUITE (suite)per Step 1
test case versionlatest version of the casefrom getTestCase
deviceSelection.typeINDIVIDUAL_DEVICESprefer explicit devices over a bundle (avoids stale-bundle surprises)
devices1 available device matching the target's platformcall listDevices(platform=<platform>, available=true) and pick online, unbooked, non-cloud devices; if the user asked for N, pick N distinct ones. Pass each as { udid, isCloud }.
appSelectionsthe test case's app under test, latest versionderive appPackage + appVersionId from getTestCase (the case records its app); omit only if the target carries no app.
deviceAllocationStrategyCROSS_DEVICE"All Permutations" — run each test case on each device (see label map below)
name"<test case/suite name> — <N> device(s) — <YYYY-MM-DD HH:mm>"human-readable; the user can override
descriptionomitoptional

Enum reference (exact API values — upper-case, case-sensitive):

  • testSelection.type: TEST_CASE | TEST_SUITE
  • deviceSelection.type: INDIVIDUAL_DEVICES | DEVICE_BUNDLE
  • deviceAllocationStrategy: CROSS_DEVICE | SINGLE_DEVICE

Allocation-strategy labels (show the human label to the user, send the enum to the API). Mirror the Portal's "Device Allocation Strategy" dropdown wording:

API enumShow to the user
CROSS_DEVICEAll Permutations — run each test case on each device
SINGLE_DEVICERandom Allocation — run each test case once, randomly chosen from the selected devices

Never surface the bare enum (CROSS_DEVICE) in the summary or prompts — it's meaningless to the user.

3. Show the summary and confirm (skip the prompt only if the user already gave full, explicit details)

Post a compact summary of exactly what will be created, e.g.:

About to create this test run:
  Test case : API Demos  (id 019ef40b…, version 2, Android)
  Devices   : 3 × Android (Pixel 8 · Galaxy S24 Ultra · Pixel 4)
  App       : io.appium.android.apis  (version 73202)
  Allocation: All Permutations — run each test case on each device
  Name      : "API Demos — 3 devices — 2026-06-24 11:20"

(Allocation shows the human label, not the CROSS_DEVICE enum.)

Then ask to proceed or customize in one prompt — offer "Proceed", "Change devices", "Change allocation", "Change name", and let the user free-type any other tweak. When the user wants to change allocation, present the two human-labeled choices (All Permutations / Random Allocation) and map their pick back to the enum. Re-summarize and re-ask only if they change something. If the user's original request was already fully explicit (every field named), you may create directly and just state what you created.

4. Create the run

Call createTestRun with the assembled payload (camelCase keys as in the tool schema; the exact enum values from Step 2). On success it returns the test run id + queued sessions. Report the id and a one-line confirmation.

If createTestRun returns a validation error, fix it from the error text and the Step-2 enum reference rather than guessing — do not retry the same body.

Show full SKILL.md (605 more words)Show less
5. Offer monitoring — one prompt, then delegate

First, decide whether monitoring is even possible here. monitor-test-run runs a bundled Node poller, so it needs a local filesystem, a shell, and ~/.kobiton/.credentials. You can't probe for those from this skill (it has no shell of its own), so judge from what your host has given you: if you have no way to run a local command, monitoring is out — don't present the choices below, because offering a watch you can't perform is the trap the matrix in CLAUDE.md warns about. Close out instead:

Run created (<testRunId>) — <portal link>. I can't watch it from here (monitoring needs to run a local poller, which isn't available in this environment), so follow it in the portal — or ask me again from a host with a shell and I'll monitor it for you.

Then stop. If you can run local commands, continue below and let monitor-test-run handle the rest: it checks for the credentials file itself and reports the /automate:setup remedy, and it degrades to a foreground loop on hosts without a streamed-output affordance rather than refusing. Don't pre-empt either of those decisions here.

Read the live-remediation flag first: call getOrgSettings once and note live_remediation_enabled (flagOn). This decides whether the auto-open option is meaningful.

Then offer monitoring in a single message (don't fire multiple separate questions — that's the annoying part). Present the choices inline and let the user pick one:

  • Monitor + auto-open live remediation — only list this option when flagOn = true. Watches the run and, when an execution blocks, automatically opens the live-remediation window for the device.
  • Monitor only — watches the run and surfaces blockers / the final summary, but doesn't auto-open windows (you print the URL instead).
  • Don't monitor — stop here; give the user the test run id (and the portal link if handy) so they can watch it themselves later.

Phrase it as one prompt, e.g. (flag ON):

Run created (<testRunId>). Want me to monitor it? (a) monitor + auto-open the live-remediation window when a blocker hits, (b) monitor only (I'll surface blockers + the URL), or (c) don't monitor. Reply a / b / c.

(flag OFF — drop option a, since there's no live window to open):

Run created (<testRunId>). Want me to monitor it? (b) monitor only (I'll surface blockers + the portal URL), or (c) don't monitor. Reply b / c.

On the user's answer:

  • (a) or (b) → invoke the monitor-test-run skill for <testRunId>. Pass along the auto-open intent: for (a), the user has already opted into auto-open, so tell monitor-test-run to skip its own up-front auto-open question and treat autoOpen = yes; for (b), autoOpen = no. monitor-test-run owns the watch loop (the bundled poller, blocker surfacing, post-mortem) from here.
  • (c) → done. Report the test run id and how to watch later (monitor-test-run <testRunId>), then stop.

Errors

ConditionHandling
No test case/suite id givenAsk for one — it's the only field with no default.
createTestRun validation error (bad enum, missing pair)Correct from the error + the Step-2 enum reference; don't blind-retry.
No available devices for the platformTell the user; offer to widen (cloud devices) or wait. Don't create a run that can't dispatch.
getOrgSettings fails before the monitor offerAssume flagOn = false (drop the auto-open option); still offer monitor-only / don't-monitor.

Notes

  • This skill creates the run and hands off the watch; it does not implement monitoring itself — that's monitor-test-run (same plugin), which runs the bundled emit-on-change poller.
  • Default to the smallest run that satisfies the request (1 device unless asked for more) — creating real device sessions consumes minutes/concurrency.
  • Prefer INDIVIDUAL_DEVICES with explicit { udid, isCloud } over a device bundle, so the exact devices are known and a stale/oversized bundle can't surprise the run.

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/testing/kobiton-automate/skills/create-test-run of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287

Compare with similar skills

Create Test Run 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.

Create Test Run compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Create Test Run this skilljeremylongshore/tons-of-skills-marketplace2.8k—~3kAutomated safety check: PassMIT
Chatgpt App Submissionnteract/semiotic2.7k—~2.8kAutomated safety check: PassApache-2.0
Opik Verifycomet-ml/opik-mcp220—~2.8kAutomated safety check: NotesApache-2.0
Opik Testcomet-ml/opik-mcp220—~2.8kAutomated safety check: NotesApache-2.0
Ue Test AuthoringJasonMa0012/MooaToon750—~2.1kAutomated safety check: NotesCustom licence
Opik Comparecomet-ml/opik-mcp220—~2.6kAutomated safety check: NotesApache-2.0

Similar skills

  • Chatgpt App Submission

    nteract/semiotic

    Inspect a ChatGPT Apps MCP server codebase and generate chatgpt-app-submission.json with app info suggestions, tool hint justifications, test cases, and negative test cases, then report review-check…

    2.7k GitHub stars~2.8k tokensUpdated today
    Testing & QAAuto-check passed

  • Opik Verify

    comet-ml/opik-mcp

    Decide ship or hold for a candidate from the compare skill's numbers, against an explicit release policy — regressions, pass rate, safety-tagged cases, subgroup consistency, latency and cost…

    220 GitHub stars~2.8k tokensUpdated yesterday
    Testing & QAAuto-check: notes

  • Opik Test

    comet-ml/opik-mcp

    Turn a failing Opik trace (or a described failure) into a repeatable regression check — a test-suite item with the trace's input and one or two binary assertions — so a fix can be verified by the…

    220 GitHub stars~2.8k tokensUpdated yesterday
    Testing & QAAuto-check: notes

  • Ue Test Authoring

    JasonMa0012/MooaToon

    A skill your agent uses when writing or modifying UE automated tests (Automation, CQTest, Functional, Gauntlet, LowLevel) with Rider MCP available.

    750 GitHub stars~2.1k tokensUpdated 21 days ago
    Testing & QAAuto-check: notes

  • Opik Compare

    comet-ml/opik-mcp

    Run a candidate against the baseline over an Opik test suite and read the numbers back — which cases broke, which got fixed, the per-metric deltas, worst rows, and whether the two runs are…

    220 GitHub stars~2.6k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes

  • Zizkadb Test

    ZIZKA-AI-SL/ZizkaDB

    Run the full ZizkaDB test suite across all layers — lint, Python unit tests, SDK tests, MCP tests, TypeScript tests, and dashboard build verification.

    130 GitHub stars~358 tokensUpdated 3 days ago
    Testing & QAAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo

  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes

  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed

  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Create Test Run

What does Create Test Run do?

Create a Kobiton test run from a test case or suite, then offer to monitor it. Create Test Run is an agent skill from jeremylongshore/tons-of-skills-marketplace. Create a Kobiton test run from a test case or suite, then offer to monitor it.

When should I use Create Test Run?

Create Test Run fits situations like: gives only partial details (or just a test case id); fill the rest with sensible defaults that match the createTestRun schema; show a summary of what will run; customize before creating.

How do I install Create Test Run in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill create-test-run -a claude-code`. Or copy the skill folder (plugins/testing/kobiton-automate/skills/create-test-run in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/create-test-run in your project. Claude Code loads it when a task matches its description.

How do I install Create Test Run in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill create-test-run -a codex`. Or copy the skill folder (plugins/testing/kobiton-automate/skills/create-test-run in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/create-test-run in your project. Codex loads it when a task matches its description.

Can I use Create Test Run 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 jeremylongshore/tons-of-skills-marketplace --skill create-test-run -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/create-test-run, .gemini/skills/create-test-run, .github/skills/create-test-run and .opencode/skills/create-test-run in your project.

What does Create Test Run need to run?

SKILL.md names no scripts, command-line tools or credentials: Create Test Run is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Skill. Compatibility (from SKILL.md): Runs on any MCP-aware host, including hosts with no local filesystem — this is the plugin's only pure-MCP skill, needing no local file, binary, or shell. Uses the Kobiton MCP tools createTestRun, getTestCase/getTestSuite, listDevices, and getOrgSettings; requires an authenticated Kobiton MCP connection. Delegates monitoring to the monitor-test-run skill (same plugin), which does need a local poller — so on a filesystem-less host, create the run and report its id rather than offering to watch it..

Does Create Test Run 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 Create Test Run 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 Create Test Run use?

Create Test Run is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Create Test Run use?

About 3k tokens (SKILL.md is roughly 12k 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 Create Test Run?

Skills that share tags, products or a category with Create Test Run: Chatgpt App Submission (nteract/semiotic, 2.7k stars), Opik Verify (comet-ml/opik-mcp, 220 stars), Opik Test (comet-ml/opik-mcp, 220 stars) and Ue Test Authoring (JasonMa0012/MooaToon, 750 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Create Test Run?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.