digital-stoic-marketplace

Creates and modifies Claude Code sub-agents following best practices. Use when user requests creating, updating, modifying, improving, or editing sub-agents. Triggers include "create/make/new agent", "sub-agent for X", file paths with /agents/, "update/modify/improve agent Y". Handles agent structure, YAML frontmatter (name, description, tools, model), system prompt design, tool restrictions (minimal permissions), isolated context benefits. Delegates to edit-tool orchestrator if uncertain about tool type (agent vs skill vs command vs script).

Creates, updates, or optimizes CLAUDE.md files following Anthropic best practices. Use when user requests creating, updating, improving, or optimizing CLAUDE.md files for project context, coding standards, or persistent memory.

Creates and modifies Claude Code slash commands following best practices. Use when user requests creating, updating, modifying, improving, or editing slash commands. Triggers include "create/make/new command", "slash command", "/command-name", file paths with /commands/, "update/modify/improve command X". Handles command structure, YAML frontmatter (description, allowed-tools, argument-hint, model), argument patterns ($ARGUMENTS, $1 $2, @filepath), tool restrictions, discoverability. Delegates to edit-tool orchestrator if uncertain about tool type (command vs skill vs agent vs script).

Creates and modifies Claude Code skills following Anthropic best practices. Use when user requests creating, updating, modifying, improving, or editing skills. Triggers include "create/make/new skill", "skill for X", file paths ending in /skills/*/SKILL.md, "update/modify/improve skill Y". Handles skill structure, YAML frontmatter, progressive disclosure (SKILL.md + reference.md + scripts/), token optimization (<500 ideal), validation checklist, Anthropic patterns. Delegates to edit-tool orchestrator if uncertain about tool type. For plugins use edit-plugin instead.

Orchestrates creation of Claude Code tools (skills, commands, agents, scripts). Use when user requests creating, updating, or improving any Claude Code extension mechanism. Triggers include "create/make/new skill/command/agent/script", "tool for X", "slash command", "sub-agent", file paths with /skills/, /commands/, /agents/. Auto-triages based on token budget, frequency, context needs, and execution type. Delegates to edit-skill, edit-command, or edit-agent after explaining decision rationale.

Implement OpenSpec change proposals. Use when: implementing approved changes, working through task lists, or checking implementation progress.

Initialize OpenSpec in a project. Use when: user says 'init openspec', 'setup openspec', or asks to add OpenSpec to a project.

Create OpenSpec change proposals. Use when: user wants to plan a feature, create a proposal, or start a new OpenSpec change.

Pre-gate self-check for drift detection and philosophy alignment. Use when: preparing for human gate review, checking implementation quality, or detecting scope drift.

Adaptive refinement for blocked or drifted changes. Use when: implementation is blocked, scope drifts >20%, or direction needs to change.

Update docs and context for OpenSpec changes. Use when: saving session state, refreshing docs after implementation, or syncing change status.

Layered verification for OpenSpec changes. Use when: running tests after implementation, validating specific test layers, or checking test status.

Use when user reports an error, bug, or something not working. Search-first troubleshooting with diagnostic phase. Triggers: debug, error, broken, not working, failing, crash, exception.