This skill should be used when the user has a large, complex task requiring: (1) multi-file or multi-step implementation, (2) major refactoring or architecture changes, (3) new feature spanning multiple components. This skill should NOT be used for simple fixes, single-file edits, or quick questions. Activates strict verification with planning, success criteria, and evidence collection.
/plugin marketplace add mnthe/hardworker-marketplace/plugin install ultrawork-js@hardworker-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/blocked-patterns.mdreferences/state-schema.mdreferences/verification-protocol.mdUltrawork enforces verification-first development - a strict mode where every completion claim requires concrete evidence.
PLANNING → EXECUTION → VERIFICATION → COMPLETE
↑ │
└── (Ralph Loop on fail) ←┘
| Phase | Description | Key Outputs |
|---|---|---|
| Planning | Explore → Design → Task decomposition | design.md, tasks/*.json |
| Execution | Workers implement tasks in parallel waves | Code changes, evidence |
| Verification | Verifier audits ALL evidence against criteria | PASS/FAIL decision |
Start ultrawork with the /ultrawork command:
/ultrawork "your goal" # Interactive: asks questions, user approves plan
/ultrawork --auto "your goal" # Auto: decides autonomously, no confirmations
/ultrawork --plan-only "goal" # Planning only, no execution
| Mode | Best For | User Interaction |
|---|---|---|
| Interactive (default) | Complex features, unclear requirements | Questions + approval |
Auto (--auto) | Well-defined tasks, CI/CD | None |
Plan-only (--plan-only) | Design review before implementation | Planning only |
USE ultrawork for:
DON'T use ultrawork for:
Verification automatically FAILS if output contains blocked patterns.
See references/blocked-patterns.md for complete list.
Common blocked phrases:
Every completion claim requires concrete proof.
| Claim | Required Evidence |
|---|---|
| "Tests pass" | npm test output with exit code 0 |
| "Build succeeds" | Build command output with exit code 0 |
| "Feature works" | Demo, test output, or screenshot |
| "Bug fixed" | Before/after comparison |
See references/verification-protocol.md for detailed verification requirements.
Each session has isolated state in ~/.claude/ultrawork/sessions/{SESSION_ID}/.
See references/state-schema.md for complete schema documentation.
Key files:
session.json - Phase, options, metadatacontext.json - Exploration summariesexploration/*.md - Detailed findingstasks/*.json - Task definitions and evidence| Command | Purpose |
|---|---|
/ultrawork-status | Check current phase and progress |
/ultrawork-evidence | View collected evidence log |
/ultrawork-cancel | Cancel active session |
/ultrawork-exec | Execute existing plan |
/ultrawork-plan | Planning phase only |
references/blocked-patterns.md - Complete list of blocked phrases and whyreferences/verification-protocol.md - Detailed verification requirementsreferences/state-schema.md - Session and task JSON schemasThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.