Skip to main content
The Momentic skills are SKILL.md files that teach a coding agent how to work with Momentic: the test file format, the MCP tools, the CLI, failure triage, and Mo. Each Momentic CLI ships only the skills for its product. Install them once per repository and commit the files. Skills are text the agent reads. The MCP server is the process the agent calls to act on a live browser or device when working on repository tests. Install both for test authoring and maintenance. The mo-qa skill starts Mo sessions through the hosted MCP server and uses the qa CLI for localhost and private targets. See Building with AI for how they compare.
These skills are for the coding agent in your editor. Skills for Momentic’s own runtime agents (triage and result classification) live in .momentic/skills. See Runtime agent skills.

​
Install

Run the command for each CLI you use. Each command adds its own skills and leaves the skills installed by other CLIs in place.
The command asks which coding agents you use, preselects the ones it detects in the repository or on your machine, and writes skills into each agent’s directory. For qa, the Cursor pointer is .cursor/rules/mo-skills.mdc. The pointer is a short block in the agent’s instructions file. It lists the skills from the CLI that wrote it and tells the agent to load the most relevant one before it works with Momentic. Each CLI rewrites only its own block, so your instructions and other CLIs’ blocks stay as they are.

​
Skip the prompts

Pass --target to choose agents without a prompt, or --yes to install for the agents detected in the repository or on your machine:
Both flags work in CI and in agent shells.

​
Installed skills

Each CLI installs only its own skills:

​
Use the skills

Some agents load installed skills on their own. Others load a skill only when you name it in the prompt. Invoke skills with a slash prefix, as the examples below show. For agents without slash commands, ask for the skill by name.

​
Authorship

Use momentic-test to create or extend Momentic tests:
Use momentic-mobile-test for Android and iOS. Naming the skill keeps the agent on Momentic’s test format and MCP tools instead of writing framework-specific code.

​
Maintenance

Use momentic-maintain to understand failures on a branch or main, review and challenge saved classifications, deflake quarantined or recovered tests, reduce retries, and repair stale test steps while preserving the intended behavior:
Use momentic-maintain to work through the quarantine backlog and produce a PR or report for the tests it repairs.

​
Request visual evidence

Web and mobile MCP tools return screenshots from live sessions and saved step results. Ask the agent to display them in the conversation when you want to see the evidence it used:
The web MCP can also record a live browser session. Ask the agent to enable video when it starts the reproduction and return the video output path after it terminates the session:
Mobile MCP sessions return screenshots and have no live session video option. The agent can still inspect the video attached to a completed mobile run when that artifact exists.

​
Spec-driven development

In the simplified format, Momentic tests read as product specs. Invoke momentic-spec when implementing a feature so the agent creates or updates the smallest set of affected Momentic tests before changing product code:
To make this the default behavior for your repository, also add a spec-driven section to your AGENTS.md (or .cursor/rules, etc.):
See Agentic testing for more on act and AI action V3.

​
Mo

Use mo-qa to start and control Mo sessions from a coding agent. It uses the hosted server at https://mcp.momentic.ai, and the qa CLI for localhost and private targets that need a tunnel. If the qa CLI is installed, qa skills installs only mo-qa in the skills directory for each agent you pick:
Without the CLI, install the skill on its own:
For a single Momentic plugin with repository-test skills, local and hosted MCP servers, and Mo, install the momentic plugin from the Momentic skills catalog:
It installs mo-qa, the browser and mobile repository-test skills, their local MCP servers, and the hosted momentic-hosted server at https://mcp.momentic.ai. mo-qa uses the hosted server for Mo sessions and the qa CLI for localhost and private targets that need a tunnel. Install the standalone skill with npx skills add https://github.com/momentic-ai/skills --skill mo-qa when you do not need the rest of the plugin.
The skill confirms effort and starts the session through the hosted server. For a localhost or private target, or when the hosted server isn’t connected, it checks the CLI, guides sign-in and starts the session with qa start, with a tunnel when the target needs one. It asks for missing scope or access only when needed. It does not invent scope, credentials, or acceptance criteria. See write a good brief, connect the hosted server and use the CLI.

​
Keep skills current

The skills ship inside the CLI package, so a CLI upgrade can carry new skill content. The first time you run momentic run, momentic app, momentic-mobile run, or qa start in a terminal after an upgrade with newer skills, the CLI asks once whether to update the installed files. Answer y to rewrite them for the agents you chose before. Answer n and it does not ask again for that skill version. Each CLI tracks its own skills, so an update from momentic leaves the files qa installed as they are. Reinstalling removes skills that this CLI generated earlier and no longer ships, unless another Momentic CLI’s pointer in the repository lists the same skills directory. The prompt appears only in an interactive terminal. It does not run in CI, in non-TTY shells, or when MOMENTIC_SKIP_SKILLS_PROMPT is set. To update without the prompt, run the install command again:
Install state lives in ~/.momentic/skills.json. Delete the file to see the first-run prompt again. Each installed SKILL.md ends with a footer such as Generated for momentic 3.53.0 (skills 1788291203). Read it to see which CLI version wrote the file, and compare it with npx momentic --version in a code review to spot a stale skill.