How do I install the Run Agmente E2e skill?

Run npx skillmds@latest add tomevault-io/run-agmente-e2e in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Run Agmente E2e skill do?

Run Agmente iOS end-to-end tests against a local ACP agent (Gemini, Claude, Qwen, or Vibe), validate core RPC flow, and perform mandatory cleanup. Use when this capability is needed. It is listed under AI & ML on SkillMD.

Is Run Agmente E2e safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Run Agmente E2e?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Run Agmente E2e free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Run Agmente E2e?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Run Agmente E2e by tomevault-io — Agent Skill

Name: Run Agmente E2e
Author: tomevault-io

File contents

Run Agmente E2E

Use this skill when the user asks to run Agmente E2E or UI-level integration checks with a real ACP agent.

Inputs

agent: gemini (default), claude, qwen, or vibe
scenario: sanity (default), add-server, prompt-send
port: default 9000
simulatorID: default BE205EA8-B26C-44C2-B52B-B49141678273
npxTag: package tag for npx-based agents (latest by default). Override via third arg to start_agent.sh or AGMENTE_E2E_NPX_TAG.

Workflow

Start local ACP bridge in background:
- ./.github/skills/run-agmente-e2e/scripts/start_agent.sh <agent> <port>
Build and run in simulator:
- Use XcodeBuildMCP build_run_sim with Agmente defaults.
Execute UI steps:
- Follow references/ui-checklist.md.
- Call describe_ui before each tap.
- Use tap by id or label where available.
Validate protocol behavior:
- Confirm sequence: initialize -> session/list -> session/new -> session/prompt.
- Confirm capability badges and session list behavior.
Cleanup always (success or failure):
- ./.github/skills/run-agmente-e2e/scripts/cleanup.sh <simulatorID> <port>

Constraints

Do not skip cleanup.
Use a valid working directory on host machine (for Agmente server config).
Do not rely on guessed coordinates from screenshots.
Prefer deterministic selectors and describe_ui.

References

UI and validation checklist: references/ui-checklist.md

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

Frequently asked questions

Run Agmente E2e