Coding standards, frameworks, refactoring, and code review (16.5K skills)
Manage coding-agent sessions across connected machines through Herdr, tmux, and MSP. See which sessions need attention, review their output, open sessions with a brief, send instructions, answer approval dialogs, and stop or close sessions.
Set up a Python environment inside the project and install its packages. Follow existing environment tools when present, avoid changing the system Python, and provide commands that work from a fresh shell.
Recover context from local coding-agent transcripts and produce a checkpoint covering the objective, completed work, blockers, and next step. Explicit import requests support read-only recovery, with continuation governed by the current workspace rules and the user's request.
Inspect Muse Code’s saved settings and defaults, then make targeted changes when explicitly requested. Explain reasoning and display options while distinguishing persistent configuration from the settings currently active in a running session.
Move useful memory notes and MCP server settings from Claude Code or Codex into Muse Code. MCP servers connect agents to external tools; the skill checks compatibility and reports settings that need attention.
Clarify unresolved product decisions before implementation, such as scope, supported platforms, or API agreements. Use a small set of focused questions to establish the intended outcome, while leaving routine technical choices to the agent.
Prepare a local browser app or standalone browser file for handoff. Verify its start behavior where supported, then provide exact commands and a reachable URL, or the artifact path, with an honest account of what was checked.
Create or update a workspace skill with a clear purpose, useful trigger phrases, and concise instructions. Organize reference documents, templates, and helper code so the main skill file contains the guidance needed for the task.
Create a new native Muse plugin package with its manifest and requested capability files, then validate it using the installed muse CLI. Receive a file inventory, validation results, and an installation proposal for later use.
Inspect stored Muse records when regular product tools do not reveal enough detail. Use read-only database queries to investigate missing records, trace execution history, and check relationships or inconsistencies across different product areas.
Work with apps on Replit through its official MCP server. The skill checks connection status and permissions, then uses available tools to read, create, update, or publish apps within the approved scope.
Create one new Muse skill with a self-contained SKILL.md and validate it. Build a project skill in the workspace, or prepare a personal skill draft with the command needed to install it.
Turn a product brief into a working website or prototype in Lovable. Inspect existing project code, update pages and features, and publish changes through Lovable’s official MCP server, with separate permissions for editing and publishing.
Search and work with GitHub repositories through GitHub’s official MCP server, which connects agents to available tools. The skill guides account authorization, repository access selection, and tool use, with separate controls for reading and making changes.
Package the current design into one downloadable HTML file that works offline. It gathers images, styles, scripts, and other assets, prepares a loading preview, and checks the bundled page for missing resources and runtime errors.
Create or improve a project-specific skill with verified build, launch, and interaction steps. Package concise instructions with scripts or existing command-line tools so future agents can run and exercise the application.
Prepare a repository for Claude Code on the web by creating a startup hook that installs project dependencies. Register the hook and check that it runs successfully, along with a sample test and code quality check.
Create and improve agent skills by defining tasks, writing instructions, and testing realistic requests. Compare outputs, success rates, time, and token use, then refine the skill and its description so it triggers appropriately.
Review changed code from four angles: reuse, simplicity, efficiency, and whether fixes address the underlying mechanism. Applies suitable improvements within the reviewed scope while preserving intended behavior, and reports fixes or skipped findings.
Inspect a codebase and create concise project instructions for Claude Code. Review existing guidance, separate team rules from personal preferences, and propose reusable skills or hooks that run commands automatically.
Review code changes in a diff, pull request, branch, or file path to identify bugs and cleanup opportunities. Findings include file locations and concrete failure scenarios, with options to apply fixes or post comments.
Launch a project's actual app and interact with it to check a change in use. Follow existing project launch instructions when available, or use patterns for command-line tools, servers, terminal interfaces, desktop apps, browser apps, and libraries.
Add interactive features to published Artifact pages using supported runtime capabilities, features granted by the viewer environment. Build saved checklists, shared data views, connector integrations, Claude-powered interactions, and file uploads or downloads with permission-aware behavior.
Enable debug logging in the current Claude Code session, inspect errors and warnings after reproducing a problem, and get a plain-language explanation of findings with concrete fixes or next steps.