openmausbot 0.1.55

package/package.json

@@ -0,0 +1,32 @@
+{
+  "name": "openmausbot",
+  "version": "0.1.55",
+  "description": "Run the OpenMausBot server anywhere and pair your devices to it",
+  "license": "Apache-2.0",
+  "type": "module",
+  "bin": {
+    "openmausbot": "cli.js"
+  },
+  "files": [
+    "cli.js",
+    "dist-server",
+    "dist",
+    "skills",
+    "LICENSE",
+    "README.md"
+  ],
+  "engines": {
+    "node": ">=24"
+  },
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/milind-soni/OpenMausBot.git"
+  },
+  "homepage": "https://github.com/milind-soni/OpenMausBot#readme",
+  "keywords": [
+    "openmausbot",
+    "agents",
+    "self-hosted",
+    "server"
+  ]
+}

package/skills/create-verification-skill/SKILL.md

@@ -0,0 +1,65 @@
+---
+name: create-verification-skill
+description: "Create one reviewed skill that teaches a bot how to launch, drive, and verify a specific app or project. Use only when the user explicitly asks for a verification skill."
+---
+
+# Create a verification skill
+
+Create one compact, project-specific `SKILL.md` through OpenMausBot's normal
+skill review flow. Do not install files directly, enable a skill yourself, or
+silently add scripts to the user's project.
+
+## 1. Inspect before drafting
+
+Use the tools already mounted on this bot to establish:
+
+- the exact project or app being verified;
+- its existing launch command and reliable ready signal;
+- the safest available control surface: existing project CLI, browser,
+  computer, phone, or shell;
+- one read-only health check;
+- up to three important user workflows and the observable result that proves
+  each one worked;
+- how to stop only the process or resource started by the verification run.
+
+Prefer an existing control surface. If the project has no dependable way to
+launch or drive the relevant workflow, report that prerequisite instead of
+inventing commands, selectors, APIs, or a new control program.
+
+## 2. Prove one workflow
+
+Run the real launch, health check, one representative workflow, evidence
+capture, and cleanup once. Use an isolated test profile or temporary data when
+available; never drive the user's live data merely to author the skill. If the
+workflow cannot be proved with the tools currently mounted, stop and explain
+which capability is missing.
+
+## 3. Draft one self-contained skill
+
+The proposed `SKILL.md` must contain YAML frontmatter and these sections:
+
+1. **Launch** — exact command, isolated data/profile, ready signal.
+2. **Doctor** — one read-only check with an actionable failure message.
+3. **Drive** — stable names, accessibility targets, routes, refs, or commands;
+   never recorded screen coordinates.
+4. **Evidence** — action plus resulting state and any important side effect.
+5. **Cleanup** — stop only what this run started; preserve the evidence.
+6. **Feature map** — at most three proven workflows, each with the user path,
+   control recipe, success proof, and known gotcha.
+7. **Maintenance** — re-run Doctor and the affected workflow when the app
+   changes; update drifted instructions but never hide a product failure.
+
+Keep it concise. A recording from Teach a skill may provide evidence for the
+user path, but it is input to the draft—not permission to retain secrets,
+audio, screenshots, or coordinates.
+
+## 4. Stage it for review
+
+Call `skills_list` first. If an existing skill already covers the project,
+report that and do not overwrite it. Otherwise call `skill_manage` with
+`action="create"`, the complete `skill_md`, a short `gist`, and the exact
+source used (repository path, URL, or `conversation`).
+
+`skill_manage` only stages the proposal. Tell the user its name and that it is
+inactive until they approve the in-app review card. Never claim it was enabled
+or scheduled automatically.

package/skills/create-verification-skill/manifest.json

@@ -0,0 +1,13 @@
+{
+  "id": "create-verification-skill",
+  "name": "Create Verification Skill",
+  "version": "0.1.0",
+  "description": "Stage one reviewed verification skill for a specific app or project.",
+  "defaultEnabled": true,
+  "triggerTerms": [
+    "/create-verification-skill",
+    "create a verification skill",
+    "make a verification skill"
+  ],
+  "requiredCapabilities": ["skillAuthoring"]
+}

package/skills/phone-harness/SKILL.md

@@ -0,0 +1,26 @@
+---
+name: phone-harness
+description: "Control, inspect, test, or automate a physical Android phone connected to OpenMausBot over authorized USB debugging. Use for explicit Android, USB phone, ADB, mobile-app, tapping, typing, swiping, scrolling, screenshot, or phone-screen requests."
+---
+
+# Phone Harness
+
+Use the `phone` tools for every requested Android action. Never replace them
+with Bash, raw `adb`, `subprocess`, an emulator, network ADB, or Tailscale.
+
+1. Call `status` before the first action. If the device is missing or
+   unauthorized, stop and relay the physical setup instruction.
+2. Call `open_app` with the human app name. Do not scan the launcher first.
+   Use `list_apps` only when the name is ambiguous.
+3. Call `read_screen` before choosing a target and after every action. Prefer
+   `tap_text`; use `screenshot` and pixel `tap` only when accessibility text
+   cannot identify the target.
+4. Use `swipe`, `type_text`, and `press` for interaction, verifying each step.
+
+The tools operate the user's real phone. Navigate and read only what the task
+needs. Stop before sending, posting, purchasing, booking, deleting, changing
+settings, entering protected information, or accepting an unexpected legal or
+security prompt unless the user has explicitly authorized that exact action.
+
+Never enter passwords, payment details, government identifiers, or one-time
+codes. Ask the user to complete protected-input steps directly on the phone.

package/skills/phone-harness/agents/openai.yaml

@@ -0,0 +1,13 @@
+interface:
+  display_name: "Phone Harness"
+  short_description: "Control a USB-connected Android phone"
+  default_prompt: "Use $phone-harness to open an app and complete a task on my connected Android phone."
+
+dependencies:
+  tools:
+    - type: "mcp"
+      value: "phone"
+      description: "OpenMausBot's bundled physical Android phone tools"
+
+policy:
+  allow_implicit_invocation: true

package/skills/phone-harness/manifest.json

@@ -0,0 +1,17 @@
+{
+  "id": "phone-harness",
+  "name": "Phone Harness",
+  "version": "0.1.0",
+  "description": "Control a physical Android phone connected over authorized USB debugging.",
+  "defaultEnabled": true,
+  "triggerTerms": [
+    "android",
+    "usb phone",
+    "usb debugging",
+    "adb",
+    "my phone",
+    "mobile app",
+    "on the phone"
+  ],
+  "requiredCapabilities": ["phoneMcp"]
+}