Coding standards, frameworks, refactoring, and code review (16.5K skills)
Investigate crashes, hangs, incorrect responses, and other failures by testing hypotheses against observed runtime behavior. Confirm the cause, verify the fix with a reproducing test, check the real workflow, and remove temporary debugging artifacts.
Reproduce and fix LazyCodex or Codex defects in a temporary workspace. Verify the change with regression tests and real usage, then deliver an upstream Codex pull request or a LazyCodex issue containing the tested patch.
Use language servers, tools that understand code structure, to check errors, locate definitions, and find references in Codex. Check whether a symbol can be renamed and apply the rename across the workspace.
Finds and rewrites code by its syntax structure across 25 languages. Use it to locate matching calls or declarations, preview bulk changes, and run reusable YAML rules that check code or apply fixes.
Compare current code with the latest published npm releases to identify unpublished changes. Read actual code differences, explain their impact across shared components and agent environments, and recommend version updates for each release layer.
Guides coding work from planning and implementation through checks on actual screens, commands, or APIs. It adjusts verification to the change’s risk and records evidence, decisions, and cleanup so completion can be assessed against the requested outcome.
Turn a broad coding request into a concrete work plan grounded in the codebase. After user approval, it documents affected files, decisions, dependencies, and verification steps so a separate worker can carry out the implementation.
Explain tips shown in senpi or omo by checking the installed tip list, user settings, and implementation code. Learn what a feature actually does, why a tip appears, and which tips your setup can show.
Uses multiple agents with different critical roles to challenge assumptions, complexity, risks, and alternatives. Findings that withstand review go to a dedicated planner, who turns them into sequenced tasks with explicit success criteria.
Build or update a ZCode plugin and prepare a local marketplace catalog for testing. The skill checks the plugin files, provides the directory and IDs, and guides you through adding the marketplace, installing or updating the plugin, and trying it in the app.
Diagnose why a skill is missing, fails to load, or does not trigger in ZCode. Trace discovery order and configuration, inspect SKILL.md metadata and precedence, then follow a step-by-step workflow to identify and fix the cause.
Diagnose ZCode hook problems by checking configuration sources, supported events, matchers, scripts, output, and run logs. Follow a step-by-step workflow to identify why a hook fails to trigger, blocks a session, or produces an error, then apply a concrete fix.
Find and fix why a custom slash command is missing, overridden, malformed, or handling arguments incorrectly in the ZCode client. Inspect command discovery paths, naming, frontmatter, plugins, and precedence, then follow a step-by-step repair workflow.
Troubleshoot MCP server configuration in the ZCode client. Check server status, configuration scopes, field names, transport settings, and startup errors to explain why a server fails, tools are missing, or file edits have no effect, then identify a concrete repair.
Create or improve reusable agent skills by clarifying their purpose, drafting instructions, trying realistic prompts, and revising from results. It helps turn repeated workflows into skills and refine descriptions so they trigger in the intended situations.
Configure ZCode resources such as skills, commands, MCP servers, hooks, plugins, and AGENTS.md instructions. Learn where user and workspace settings live, how discovery and merge rules resolve conflicts, and which scope fits each resource.
Diagnose ZCode plugin problems by checking discovery, installation, enablement, manifests, dependencies, and configuration. Follow a symptom-based workflow to identify a concrete cause and repair plugin listings, missing components, marketplace failures, or settings that cannot be entered in the client.
Find topic-specific API guidance and implementation patterns for Three.js projects. Ten references cover scene setup, geometry, materials, lighting, textures, animation, loading models, custom visual effects, postprocessing, and mouse or touch interaction.
Guide Git operations with explicit authorization for history changes and destructive actions. It defines recovery snapshots before discarding work, careful handling of locks and index corruption, and checks that keep unexplained changes out of commits.
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.
Read current or previous Muse Code session logs to recover context, review decisions and tool results, or reconstruct lost files from recorded changes. It also helps locate the relevant session for a workspace.
Coordinate software investigations, implementation, code reviews, and testing through Codex tasks in desktop, remote, or cloud environments. Inspect pull requests and automated checks, follow up on authorized fixes, and report results with verification limits.
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.
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.