This skill should be used when performing quick project overview exploration at the start of ultrawork sessions. Executes directly without agent spawn for fast codebase understanding.
/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/examples.mdreferences/templates.mdQuick project overview exploration executed directly without agent spawn.
Check for language/framework config files:
Glob(pattern="package.json") # Node.js/JS
Glob(pattern="go.mod") # Go
Glob(pattern="requirements.txt") # Python
Glob(pattern="Cargo.toml") # Rust
Glob(pattern="pom.xml") # Java/Maven
Read discovered files to understand dependencies and framework.
# Top-level structure
Glob(pattern="*", path=".")
# Main source directories
Glob(pattern="src/*")
Glob(pattern="app/*")
Glob(pattern="lib/*")
# Find entry points (language-specific)
Grep(pattern="export default|module.exports", type="ts")
Grep(pattern="def main|if __name__", type="py")
Grep(pattern="func main", type="go")
# Check for existing patterns
Grep(pattern="auth|login|session", output_mode="files_with_matches")
Read(file_path="README.md")
Read(file_path="CLAUDE.md")
Summarize findings in structured format:
## Overview Exploration Results
**Project Type**: {framework/language}
**Tech Stack**:
- Language: {language and version}
- Framework: {framework}
- Database: {if found}
- Test: {test framework}
**Directory Structure**:
{tree representation}
**Key Entry Points**:
- {main files}
**Existing Patterns**:
- {auth, database, api patterns found}
**Relevant Files** (based on Goal):
- {files relevant to the user's goal}
See references/templates.md for complete template.
When running within an ultrawork session:
overviewexploration/overview.mdcontext.jsonanalyzingSCRIPTS="${CLAUDE_PLUGIN_ROOT}/scripts"
# Update stage
$SCRIPTS/session-update.sh --session {SESSION_ID} --exploration-stage overview
# Get session directory and write findings
SESSION_DIR=$($SCRIPTS/session-get.sh --session {SESSION_ID} --dir)
# Write overview.md...
# Add to context
$SCRIPTS/context-add.sh --session {SESSION_ID} \
--explorer-id "overview" \
--file "exploration/overview.md" \
--summary "{summary}" \
--key-files "{files}" \
--patterns "{patterns}"
# Advance stage
$SCRIPTS/session-update.sh --session {SESSION_ID} --exploration-stage analyzing
No excessive exploration - overview aims for quick understanding. Targeted exploration handles detailed investigation.
After overview completion:
Task(subagent_type="ultrawork:explorer")references/examples.md - Complete exploration examples for different project typesreferences/templates.md - Output templates and session integration commandsThis 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 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 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.