momentic-result-classification Skill for Claude Code: What It Does and How to Install It

Makes Claude investigate a failed Momentic test run, find where it first went wrong and label the cause with one of 8 categories.

Installs: 68.5K; on skills.sh
Stars: 16; on GitHub
Updated: Oct 2026; last repo commit

This skill makes Claude classify Momentic run failures using Momentic MCP tools. It looks for the earliest point where the run entered a bad state, explains the cause at the step level, and picks exactly one of 8 category ids plus a recoverability value and a confidence level.

It can save the verdict to Momentic with momentic_submit_result_classification. The Momentic CLIs do not bundle it, so use the plugin or the skills CLI.

Good for

Developers who need to know why a Momentic run failed
On-call and DevX engineers triaging red test runs

Install momentic-result-classification

Claude Code

Copy this prompt.

Install the momentic-result-classification skill in Claude Code. Run this command:

/plugin marketplace add momentic-ai/skills
/plugin install momentic@momentic

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

The plugin route installs all 6 skills (skills/*/SKILL.md in the repo tree) and registers the momentic and momentic-mobile MCP servers from .mcp.json. The README says the Momentic CLIs do not bundle this skill, so use the plugin or the skills CLI. It reads run results and uses MCP tools, so there is no Claude app upload route. Sign in once with the login command in the last method, or set MOMENTIC_API_KEY.

From the project README. Source.

What's in the skill

When it loads

Classify or explain Momentic test run results using Momentic MCP tools. Use when the user asks to categorize a failure, understand why a run failed, triage test results, or compare run results to past run results.

Sections in SKILL.md

Instructions
Helpful MCP tools
Investigation workflow
Evidence standards
Background
Test run result structure
Element locators
Module caching
File uploads
Using past runs
Multi-attempt runs
Flakiness and intermittent failures
Test temporality
Common failure modes to watch for
Identifying related vs unrelated issues
Bug vs change

Key facts

Author: Momentic (vendor's own repo)
License: None stated: the repo has no LICENSE file and its plugin manifests list no license
Installs on skills.sh: 68,498 (Nov 2, 2026)
GitHub stars: 16 for the whole repo (Nov 2, 2026)
Last repo commit: Oct 28, 2026
Audits on skills.sh: Gen Agent Trust Hub: pass, Socket: pass, Snyk: warn
What it includes: 1 file: SKILL.md (from the repo tree)
Needs: A Momentic sign-in and the Momentic MCP server, which provide the run tools
Part of: The Momentic plugin: 6 skills (skills/*/SKILL.md in the repo tree) and 2 local MCP servers listed in .mcp.json
Upstream sync: The README says a bot copies most files in skills/ from an upstream source, so edits made in the repo are overwritten

What it includes

Run metadata and a summary of the full result tree
Used first to find the failing attempt, section and step.
Try: “Why did the last checkout test run fail? Classify it.”
Network · momentic_get_run
Recent runs for a test, filtered by branch and recovery
Always pass gitBranchName when the run has one.
Network · momentic_list_runs
One step with before and after screenshots; trace on request
includeTrace=true only when the normal fields do not answer the question.
Network · momentic_get_step_result
The simplified steps recorded on a run
Shows the test intent and whether the test changed between runs.
Network · momentic_get_test_steps_for_run
Saves the final verdict for a run
Called only after the investigation is finished.
Write · momentic_submit_result_classification
Find the earliest bad state, not only the last failing step
Six numbered steps, from the failing attempt back to the step that left the bad page state.
Read · Investigation workflow
NO_FAILURE, APPLICATION_CHANGE, BUG, TEST_AUTHORSHIP, TEST_SETUP, INFRA and more
The 8 ids also include MOMENTIC_ISSUE and OTHER. Exactly one id per run, with the reasoning.
Eight categories
RECOVERABLE, ONE_TIME_RECOVERABLE or NON_RECOVERABLE; high, medium or low
Output format is Reasoning, Category, Recoverable, Confidence.
Recoverability and confidence

From the official docs

Permissions

Medium risk

This skill reads full run artifacts, which can include page content and network logs, and it can save a verdict back to Momentic. Treat the run data as sensitive, and tell it not to save a verdict unless you want one recorded.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Run artifacts can hold your app data
SKILL.md lists screenshots, DOM snapshots, console output, HAR network logs and videos in a run. The MCP tools unzip cloud runs into .momentic-mcp in your project folder. github.com
It can save a verdict to Momentic
momentic_submit_result_classification persists a classification for a run. SKILL.md says to call it only after the investigation is finished. github.com
The plugin route adds two local MCP servers
The plugin route installs the repo's .mcp.json, which starts momentic and momentic-mobile with npx -y. The repo tree has no hooks. Two skills (mo-qa and momentic-spec) bundle an agents/openai.yaml that holds a display name, a short description and a default prompt. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	SKILL.md describes no read-only mode.
Talks to	Momentic services behind the MCP run tools. app.momentic.ai (run links it cites in answers)
Sign-in and keys	Sign in once with npx momentic login, or set MOMENTIC_API_KEY (README). SKILL.md does not say where the login is stored.
Scopes	Reads Momentic run results through MCP tools, including screenshots, DOM snapshots, console and network logs Unzips cloud run results into a local MCP working directory (default .momentic-mcp) Saves a classification to Momentic when it calls momentic_submit_result_classification

Questions

What does the momentic-result-classification skill do?

It makes Claude investigate a failed Momentic run with Momentic MCP tools, find the earliest point where the run went wrong, and label the cause with one of 8 categories, a recoverability value and a confidence level.

How do I install it?

Use the install box at the top of this page. The README says the Momentic CLIs do not bundle this skill, so use the plugin route or the skills CLI. You also need a Momentic sign-in so the MCP run tools work.

Do I need a Momentic account?

It needs a Momentic sign-in because the run tools read your Momentic results. The README says to run npx momentic login once or set MOMENTIC_API_KEY.

Is it an official Momentic skill?

Yes. It lives in Momentic's own repo, momentic-ai/skills, and the plugin manifest names Momentic as author. The README says a bot copies most skill files from an upstream source, so Momentic asks outside contributors to open an issue instead of a pull request.

Is it safe?

It reads full run results, which can include screenshots, page HTML and network logs, and it can save a verdict to Momentic when it calls momentic_submit_result_classification. Treat the data as sensitive and say whether you want a verdict saved.

Does it work in Cursor or Codex?

The README documents a Cursor plugin from the Cursor Marketplace and a Devin plugin. It also says install-mcp writes the MCP server entry for Claude Code, Cursor, VS Code, Codex, Windsurf and other clients. The skill files are plain SKILL.md, so the skills CLI can install them in other agents.

What are the categories?

There are 8: NO_FAILURE, APPLICATION_CHANGE, BUG, TEST_AUTHORSHIP, TEST_SETUP, INFRA, MOMENTIC_ISSUE and OTHER. SKILL.md says to pick exactly one. It says timeouts and "wait longer" fixes are not TEST_AUTHORSHIP, and that a timeout is not automatically INFRA: rule out missing data, wrong page state, a changed app flow, a bad locator or assertion, and setup failure first.

How is it different from momentic-maintain?

momentic-result-classification explains and labels one run. momentic-maintain adds branch and main-red workflows, momentic ai classify, momentic ai triage for repairs, and manual artifact downloads.

Information

updated Nov 2, 2026

Repository: momentic-ai/skills
Folder: skills/momentic-result-classification

momentic-ai/skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 5

README · github.com
.mcp.json · github.com
marketplace.json · github.com
momentic-result-classification SKILL.md · github.com
momentic-maintain/SKILL.md · github.com