Provides the standard structure and format for Prompt-Response-Plan (PRP) documents. Use when creating, formatting, or validating PRP documents for systematic problem-solving workflows.
Provides standard PRP document structure for systematic problem-solving. Triggers when creating, formatting, or validating Prompt-Response-Plan documents with Prompt, Response, and Plan sections.
/plugin marketplace add L-Sypniewski/claude-code-toolkit/plugin install context-engineering@claude-code-toolkitThis skill inherits all available tools. When active, it can use any tool Claude has access to.
This skill defines the standard structure for Prompt-Response-Plan (PRP) documents used in context engineering workflows.
A well-formed PRP contains three main sections:
The initial problem statement or request that initiates the workflow:
## Prompt
[Clear, concise description of the problem or task]
### Context
- Background information
- Relevant constraints
- Success criteria
Analysis and proposed approach:
## Response
### Problem Analysis
- Key challenges identified
- Dependencies and prerequisites
- Risk factors
### Proposed Solution
- High-level approach
- Alternative approaches considered
- Rationale for chosen approach
Detailed execution plan with trackable steps:
## Plan
### Implementation Steps
1. [ ] Step 1: [Description]
- Sub-tasks if needed
- Expected outcome
2. [ ] Step 2: [Description]
- Dependencies: Step 1
- Expected outcome
3. [ ] Step 3: [Description]
### Testing Strategy
- Unit tests
- Integration tests
- Acceptance criteria
### Rollback Plan
- Contingency steps if issues arise
prp-[description]-[timestamp].md
Example: prp-refactor-auth-module-2025-11-21.md
This structure works seamlessly with:
context-engineering-prp-generator agent (generates PRPs)context-engineering-executor agent (executes plans)context-engineering-orchestrator agent (coordinates workflows)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.