skill-pilot

Reverse-engineer an existing software project so the user can understand the code logic, architecture, workflows, design decisions, and potential issues. Use this when the user provides a GitHub repo, local codebase, zip file, or existing project and wants architecture understanding, Mermaid diagrams, remake guidance in another language, or expert design/performance evaluation.

Perform deep research from a research requirement or instruction file and produce research outputs in the same folder, including Markdown plus an index.html visual report with Mermaid diagrams when useful.

Open and operate the local Skill Pilot WebUI through the browser for demos, walkthroughs, settings changes, task execution, and terminal-based education flows. Use when the user wants the agent to drive Skill Pilot as a human would in the browser, open a specific WebUI feature, or jump directly into shell or agent terminal views.

Use this skill when acting as a Black-Box Code Agent Supervisor. The supervisor uses coding agent CLIs such as Claude Code, Codex, OpenCode, Gemini CLI, or other AI coding agents through tmux terminal windows to finish a coding task or project. The supervisor works like a real developer using AI agents: giving instructions, checking the running result, using browser/curl/logs, finding issues, and sending feedback back to the coding agent. The supervisor does not directly inspect source code, write code, or write code-level tests.

Manage the full lifecycle of a Vibe Coding project — create, refine, brainstorm, initialize, plan, implement, review, test, deploy, update, and fix issues. Use when the user wants to start a new project from a prompt, evolve its requirements, plan or write code, validate or deploy it, or apply updates and bug fixes against an existing project.

Create interactive courses and assignments for students in the project's markdown format. Use when asked to create a new course, educational module, or assignment.

Execute a task in the background with a prompt through the core engine LLM provider and return plain text output. Use when the user wants to run a prompt as a background task via the Agent CLI.

Initialize and verify AI Agent for web browser setup with Chrome for browser automation.

Cloud infrastructure operations for AWS and RunPod. Use when managing EC2 instances, configuring AWS credentials, SSH connections, port forwarding, or managing RunPod GPU pods and serverless endpoints. Supports AWS and RunPod; extensible to other providers.

Create a Discord server and bot application with browser automation, collect the bot token, server ID, and user ID, then save credentials to .env via the keys-safe-guard skill. Skip if OPENCLAW_DISCORD_BOT_TOKEN is already set. Use for any project that needs a Discord bot.

Manage LLM security key protection for config/.env or an explicit .env/.env.* file using core/bin/keys-safe-guard actions (enable, disable, get_key_names, get_key_value, put_key_values), and govern all other agent-invoked sudo commands (software installs, system config) via the general sudo rule. Prefers native GUI elevation; never relies on hidden terminal password prompts.

Web browser automation CLI for AI agents. Use when the user needs to initialize or verify browser automation, interact with websites, navigate pages, fill forms, click buttons, take screenshots, extract data, test web apps, log in to sites, or automate any browser task.

Create, update, find, or dynamically use agent skills and Skill Pilot subagents. Use when the user asks to create or edit a skill, create or edit a subagent, rename or reorganize instructions, find an agent skill, find a subagent, or use a mentioned skill or subagent that is not active.

Create, update, run, resume, or continue agent workflows. Use when the user asks to create or fix workflow JSON, execute an existing workflow, run a workflow with a prompt, resume a workflow run, or continue the next node in a waiting multi-step workflow.

Create slideshow videos from ordered images using FFmpeg. Supports three modes: silent slideshow with xfade transitions, slideshow with a single background audio (trimmed or looped), and slideshow where each image is paired with its own audio file and its on-screen duration equals that audio's duration. Use when users ask to generate image-to-video slideshows.

Create AI-generated image or text-to-speech audio files and return local file paths. Use when the user asks to generate raster visuals such as icons, thumbnails, covers, mockups, or posters, or asks to turn plain text into audio formats such as mp3 or wav.

Manage Skill Pilot codeware operations and feature lifecycle work. Use when the user wants to sync or restore codeware, configure a personal fork, contribute upstream, create a private workspace repo, or run feature development steps such as create, refine, initial, plan, implement, review, test, merge, freeze, update, or fix issues.

Start a new agent session by stopping the current agent process and launching a new prompt in the latest web or native terminal bash session.

Handle Git and GitHub work including commits, conventional commit message drafting, partial file or folder merges, and squash merges, Github Actions CI/CD with AWS.

Produce simple number and string outputs for workflow tests. Use when testing workflow nodes that need random numbers, random strings, number-string concatenation, digit extraction, or conditional plain-text number detection.

Generate and process media: text-to-image, text-to-video, text-to-speech, text-to-song, image or video animation, lipsync, vocal extraction, upscaling, and audio transcription.

Execute and suggest AWS CLI commands with validation, batch execution, and multi-region support.

Run shell commands, manage interactive terminal sessions, SSH tunnels, file transfers, and tmux sessions on local or remote hosts.

Expert social media content creator for Twitter/X, LinkedIn, and more.

Create, schedule, and publish content for LinkedIn, Xiaohongshu (小红书), and X. Handles platform-specific copywriting, engagement frequency tracking via local history, and browser-based publishing.

Convert files or URLs to Markdown. Supports PDF, DOCX, PPTX, XLS, XLSX, HTML, CSV, JSON, XML, Images, and YouTube URLs.

Create, update, install, uninstall, or use Skill Pilot extensions under `extensions/`, including optional extension-specific agent guidance.

Control the computer by taking screenshots, moving the mouse, clicking, and typing. Use this skill when you need to interact with GUI applications or perform actions that require visual feedback.

Analyze a local image with the local OpenAI-compatible vision endpoint to describe screenshot, video scenes, answer image questions, extract visible text, or perform OCR-style image-to-text tasks.

Troubleshoot Skill Pilot installation, startup, environment, CLI, and code issues for zero-knowledge users. Use when the user is stuck with install.sh, skillpilot.sh, confusing technical errors, or a bug that needs practical diagnosis and repair.

Create or resume a multiple-scene video workflow from a requirement or an existing output directory. Use when the user wants a generated video with multiple scenes, image and audio support, educational or presentation-style structure, HTML-style animation and visual storytelling, or crash recovery for an interrupted video run.

Generate draw.io diagrams as .drawio files, optionally export to PNG/SVG/PDF with embedded XML

Convert text to audio and play it completely before returning.

Automates web browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Write tests for project code using either real code tests or mock-up tests. Use when creating or updating tests, default to real code tests unless the user explicitly asks for mock-up tests.

Capture and apply user corrections, preferences, and workflow instructions. Use when the user asks to use a different agent skill or tool, says to handle tasks this way in the future, wants to avoid a repeated mistake, or explicitly corrects how future tasks should be handled.

Use when a task needs to install a new Python package, run a Python helper script, or a Python package CLI.

Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages and use Python tools such as reportlab, pdfplumber, and pypdf for generation and extraction.

Manage core engine lifecycle via core/bin/tool-cli commands for engine-restart and engine-reload. Only use this skill when the user explicitly asks to restart or reload the engine; never trigger it automatically from another agent skill.

Install AI code agent CLI tools including claude-code, gemini-cli, codex, and github copilot-cli. Use when setting up AI coding assistants or when the user asks to install an AI code agent.