This skill should be used when the user asks to "identify core need", "clarify requirements", "extract user intent", "validate distinctions", or when starting any research or analysis task that requires understanding what the user actually needs before proceeding.
/plugin marketplace add rafaelcalleja/claude-market-place/plugin install gitlab-tbc@claude-market-placeThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/process.mdExtract the fundamental requirement from user requests before any research or implementation.
Transform ambiguous or complex user requests into clear, actionable core needs with validated distinctions. Filter noise before it reaches the user.
User Request
│
├─ If ambiguous → AskUserQuestion to clarify
│
▼
Apply Behavioral Principles + Validation Log
│
▼
Core Need Output: action + target + triggers + validated distinctions
Read and follow references/process.md for the complete workflow.
The process includes:
| Principle | Application |
|---|---|
| FOCUS ON PRACTICAL | Address real objective directly |
| VALIDATE COMPARISONS | Each distinction must be relevant and correct |
| NO ARTIFICIAL DISTINCTIONS | Omit implementation details that don't change action |
| SIMPLICITY > COMPLEXITY | Simple solution without elaboration |
| VALIDATION QUESTION | "Does this change what user must DO?" |
The mandatory output includes:
Before proceeding, verify:
| Need | Reference |
|---|---|
| Complete process with examples | references/process.md |
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 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.