This skill should be used when the user asks to "brainstorm", "explore an idea", "refine a concept", "crystallize thinking", "capture an idea", "develop a hypothesis", or needs guidance on structured ideation, concept development, or idea documentation.
/plugin marketplace add tbhb/oaps/plugin install oaps@oapsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/critique-patterns.mdreferences/document-structure.mdreferences/expansion-patterns.mdreferences/exploration-patterns.mdreferences/synthesis-patterns.mdtemplates/default.md.j2templates/process.md.j2templates/product.md.j2templates/research.md.j2templates/technical.md.j2This skill provides guidance for brainstorming, exploring, refining, and documenting ideas. It includes progressively-disclosed references on idea document structure, exploration patterns, expansion techniques, critique methods, and synthesis approaches for effective ideation.
Idea documents capture concepts at various stages of development, from initial seeds to crystallized insights. They follow a structured lifecycle (seed, exploring, refining, crystallized, archived) that supports iterative development and connection discovery between related ideas.
Storage location: All ideas are stored in .oaps/docs/ideas/ (hidden directory at project root).
ID format: YYYYMMDD-HHmmss-slug (e.g., 20251218-164449-worktree-management)
NEVER search for idea files manually using Glob, Grep, or find. ALWAYS use these CLI commands:
| Command | Description |
|---|---|
oaps idea list | List all ideas |
oaps idea search <query> | Search ideas by content |
oaps idea show <id> | View full idea (use FULL ID from list/search) |
oaps idea create "<title>" | Create new idea |
oaps idea resume [<id>] | Get resume summary |
MANDATORY STEPS FOR ALL IDEA WRITING TASKS
Gather context - Run oaps skill orient idea-writing to see available references and workflows
Identify relevant references - Review the references table from step 1 and select those matching your task
Load dynamic context and references - Run oaps skill context idea-writing --references <names...>
Review loaded references and commands - Read through the guidance. The Allowed commands table at the end of the output is authoritative for what commands can be run.
Follow the workflow - Adhere to the selected workflow's steps for capturing, exploring, refining, or crystallizing ideas.
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.