This skill should be used when the user wants to triage an issue, review a specification, or assess requirements completeness. Trigger when user mentions "triage", "review this spec", "is this requirement complete", "what questions should I ask", or provides a description/acceptance criteria that needs evaluation before implementation. The skill analyzes input against the codebase and project documentation to surface implicit requirements and generate clarifying questions.
/plugin marketplace add lttr/claude-marketplace/plugin install lttr-triage-plugins-triage@lttr/claude-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Analyze requirements, issues, or specifications for completeness. Explore the codebase to understand context, then generate targeted questions to fill gaps before implementation begins.
The user provides input as plain text - typically:
Extract and identify:
Use the Explore agent to understand:
Search for relevant documentation that may contain implicit requirements:
docs/, documentation/, wiki/ directoriesREADME.md, CONTRIBUTING.md, ARCHITECTURE.mdopenapi.yaml, swagger.json)If configured (see config.md), search external documentation systems for:
Evaluate the input against these dimensions:
| Dimension | Questions to Consider |
|---|---|
| Problem clarity | Is the problem/goal clearly stated? Why is this needed? |
| Scope definition | What's in scope? What's explicitly out of scope? |
| User impact | Who benefits? What user journey is affected? |
| Acceptance criteria | How do we know when it's done? What are success metrics? |
| Edge cases | What happens in error states? Empty states? Boundaries? |
| Technical scope | Which components/files are affected? API changes? |
| Dependencies | Blocked by anything? Needs coordination with other work? |
| Non-functional | Performance requirements? Security considerations? |
| Data | Schema changes? Migration needed? Data implications? |
| UX/UI | Designs provided? Interaction patterns defined? |
Rate overall completeness: Ready / Mostly Ready / Needs Clarification / Underspecified
Identify questions organized by:
Use AskUserQuestion tool to ask the user any questions they might be able to answer (especially blockers and scope questions).
Only questions the user couldn't answer go to the output file for stakeholder follow-up.
mkdir -p ./.aitools/triage
Save to ./.aitools/triage/<identifier>.md
Naming:
<ticket-id>-<slugified-title>.md<slugified-title>.mdSlugify: lowercase, spaces→hyphens, remove special chars, max 50 chars.
# Triage: [Short title]
**Source**: [Ticket ID/URL if available, or "Manual input"]
**Date**: [YYYY-MM-DD]
**Completeness**: [Ready | Mostly Ready | Needs Clarification | Underspecified]
## Summary
[1-sentence summary of what was provided]
### Understanding
[2-3 sentences capturing the core request and affected areas based on codebase exploration]
### What's Clear
- [Bullet points of well-defined aspects]
### Implicit Requirements (from docs)
- [Requirements found in documentation that the ticket assumes but doesn't state]
- [Business rules, constraints, or edge cases documented elsewhere]
### Gaps Identified
- [Bullet points of missing or ambiguous information]
### Questions
#### Blockers
1. [Question] — [Why this blocks progress]
#### Scope Clarification
1. [Question]
#### Technical Decisions
1. [Question]
#### Nice to Know
1. [Question]
Note: Only include questions the user couldn't answer during interactive clarification.
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 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.