This skill should be used when the user asks to "create a spec", "write a specification", "review a spec", "update a spec", "review spec organization", "split a spec", "add a page to spec", "remove a page from spec", "move requirements between pages", "add requirements", "review requirements", "update requirements", "delete requirements", "add tests", "add test cases", "review tests", "update tests", "delete tests", or needs guidance on spec structure, formatting, or spec writing best practices.
/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/artifacts.mdreferences/feature-specs.mdreferences/formatting.mdreferences/identification.mdreferences/metadata.mdreferences/requirement-writing.mdreferences/review-checklist.mdreferences/spec-structure.mdreferences/technical-specs.mdreferences/test-design.mdreferences/writing-rules.mdtemplates/api-spec.mdtemplates/feature-spec.mdtemplates/feature.md.j2templates/formal.md.j2templates/lightweight.md.j2templates/review-feedback.mdtemplates/technical.md.j2templates/test-case.mdThis skill provides guidance for creating, reviewing, and improving technical specifications. It includes progressively-disclosed references on spec structure, formatting, requirement writing, test case design, and best practices for clear and effective specification documents.
Specifications define formal requirements, behaviors, and interfaces for components, systems, or processes. They serve as authoritative references for development, testing, and validation activities.
MANDATORY STEPS FOR ALL SPEC WRITING TASKS
Gather context - Run oaps skill orient spec-writing to see available references
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 spec-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 structuring, writing, reviewing, or improving the specification.
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.