Run any Skill in Manus with one click

automation-browser-api-workflows

Class-level workflow for browser automation, API reverse-engineering, macOS UI automation, tmux/interactive CLI control, MCP tool calling, camera capture, and direct tool/API replacement of fragile UI flows. Use when asked to automate websites/apps, learn private site APIs from traffic, drive interactive CLIs, call MCP servers/tools, capture camera frames, or control macOS UI.

Run Skill in Manus

Stars10

Forks0

UpdatedMay 4, 2026 at 06:12

Source

davidtoby

davidtoby/agent-skills

View GitHub Repository View Creator Repositories

Install command

Download

Run Skill in Manus

Useful forSOC

Software DevelopersComputer and Mathematical Occupations15-1252L4

File Explorer

8 files

SKILL.md

readonly

More from this repository

same repository

opencode-litellm-gemini-provider

davidtoby/agent-skills

Configure official native OpenCode to add a local LiteLLM OpenAI-compatible Gemini model as a selectable provider using config-file secret references, without wrappers and without changing the current default model.

2026-05-1010

litellm-vertex-proxy-repair

davidtoby/agent-skills

Diagnose and repair a local LiteLLM + Vertex AI proxy on macOS, especially when `http://127.0.0.1:4000/` or `/v1` is down, startup hangs at `Waiting for application startup`, `/ui/login/` says `Authentication Error, Not connected to DB!`, or Prisma/PostgreSQL issues need to be isolated from the API proxy by splitting `lite` and `full` modes.

2026-05-0910

hermes-agent-litellm-vertex-gateway

davidtoby/agent-skills

Configure an existing Hermes Agent deployment to use a local LiteLLM Vertex Proxy as an additional model option, without disturbing the current Hermes configuration. Use when you need Hermes to access Gemini models via a local LiteLLM gateway already running at 127.0.0.1:4000.

2026-05-0910

openclaw-litellm-gemini-gateway

davidtoby/agent-skills

Configure OpenClaw to use an already-running local LiteLLM gateway for Gemini on macOS, with a low-risk add-as-option workflow, exact openclaw.json snippets, verification commands, rollback steps, and the real caveat that some per-run model overrides are rejected unless you use --local or switch the active alias first.

2026-05-0910

litellm-vertex-gemini-local-gateway

davidtoby/agent-skills

Build a local macOS LiteLLM gateway that exposes Google Cloud Vertex AI Gemini behind an Anthropic-compatible endpoint, then connect Claude Code and OpenClaw to it without breaking existing setups. Use when starting from a fresh machine, when you need a self-starting LaunchAgent service on 127.0.0.1, when Claude Code should route through LiteLLM, or when OpenClaw needs a selectable Gemini-via-LiteLLM model.

2026-05-0910

agent-skills-frontmatter-compatibility

davidtoby/agent-skills

Fix packaging and validation failures caused by fragile SKILL frontmatter when publishing or syncing skills into Toby's davidtoby/agent-skills repository. Use when rebuild_all_packages.py fails early on a promoted skill, especially after copying local-only community skills such as lark-* into the repo.

2026-05-0910

name	automation-browser-api-workflows
description	Class-level workflow for browser automation, API reverse-engineering, macOS UI automation, tmux/interactive CLI control, MCP tool calling, camera capture, and direct tool/API replacement of fragile UI flows. Use when asked to automate websites/apps, learn private site APIs from traffic, drive interactive CLIs, call MCP servers/tools, capture camera frames, or control macOS UI.

Automation, Browser, and API Workflows

Use this umbrella when the task is to operate an external interface repeatedly or replace brittle UI actions with a more reliable API/tool path.

Core workflow

Identify the interface: browser page, native macOS UI, interactive terminal app, MCP server, RTSP/ONVIF camera, or HTTP API.
Prefer structured APIs/CLIs over visual clicking when available.
If starting from browser automation, capture state, network traffic, and request/response shapes so the workflow can be converted to direct calls.
Keep credentials out of logs and references; store only redacted examples.
Build deterministic probes/scripts for repeated actions and verify outputs after each side effect.

Labeled playbooks

Browser automation

Use snapshots/selectors/click/type flows for one-off navigation. For repeated work, graduate to direct HTTP or a specialized CLI.

API learner

Record traffic, identify auth/session headers, replay with curl, minimize payloads, and document stable endpoints plus failure codes.

macOS UI automation

Use screenshot/element capture tools for apps that lack APIs. Verify focus and target window before sending keystrokes.

tmux and interactive CLI control

For long-lived or REPL-like tools, send keystrokes and scrape panes instead of running non-PTY commands that will hang.

MCP tool calling

List servers/tools, inspect schemas, then call with JSON arguments. Generate typed wrappers only after schemas are stable.

Camera capture

Probe stream URLs and capture short frames/clips with ffmpeg-compatible tools; avoid assuming camera availability.

Reference files

Exact CLI commands and session-specific endpoint notes are stored in references/from-*.md.