Operating Soul for AI coding agents that captures how to think, not just rules — principle-over-rule, 7 delegation levels (Tell→Delegate), a git-gated learning loop. Built for Claude Code, portable to Cursor/Gemini/Kiro/Copilot via AGENTS.md. Smarter every session.
Command Claude Code
Run a SYSTEMATIC, exhaustive audit of .docs/common-issues/ (default) — or .docs/principles/ if $ARGUMENTS says "principles" (or "both"). Cross-session catalogs accrete overlap, broken links, and doc↔code drift that incremental passes miss; this finds them in one pass. Common-issues need this more often than principles…
Command Claude Code
Create a detailed step-by-step implementation plan for $ARGUMENTS with comprehensive before/after code examples create file at .docs/year(YYYY)/month(MM)/day(DD)/{number-in-DD-folder(01)}-{Feature Spec}/{Feature Spec}-implementation-plan.md if requirement is clear or no have follow up question. think hard and provide…
Command Claude Code
Create a Jira task ticket in the project for: $ARGUMENTS.
Command Claude Code
Perform comprehensive analysis of: $ARGUMENTS (or entire codebase if no specific area mentioned).
Command Claude Code
call agent design system for create a compose screen for $ARGUMENTS with follow KISS, DRY, SOLID, YAGNI, and atomic design principles — A Simple Guide to Some Principles of Software Engineering and Clean Code.
Command Claude Code
Command "do-implementation" from tomdwipo/claude-soul, covering do implementation command, flow diagram in ac (mandatory when flow changes), flow diagram, per-row execution and self-verdict, no asking.
Command Claude Code
Generate a compliance feature report for: $ARGUMENTS.
Command Claude Code
Perform comprehensive analysis of the entire codebase: $ARGUMENTS.
Command Claude Code
Run the engine in .docs/principles/how-to-learn.md on the most recent correction(s) in this session (or on $ARGUMENTS if given).
Command Claude Code
Create a mini PRD for $ARGUMENTS that includes goal, requirements, and acceptance criteria. create file at .docs/year(YYYY)/month(MM)/day(DD)/{number-in-DD-folder(01)}-{Feature Spec}/{Feature Spec}-spec.md. check real current date first. only 1 file. must follow the format specified in the example bellow. do not add…
Command Claude Code
Perform comprehensive mobile-focused analysis: $ARGUMENTS.
Command Claude Code
Think Hard and Give me a few options for a $ARGUMENTS, starting with the simplest first. Don't code yet - just outline the approach and ask me which direction to take.
Command Claude Code
Analyze, sync, and track PRD/TRD alignment with codebase: $ARGUMENTS.
Command Claude Code
Read Production Intelligence agent output, deduplicate findings against existing Jira tickets, and create actionable Task tickets in Backlog with full field mapping.
Command Claude Code
Execute the complete PR workflow: commit all changes, push to remote, create PR, and transition Jira ticket.
Command Claude Code
Generate a standalone QA alignment analysis for: $ARGUMENTS.
Command Claude Code
You are publishing a weekly quality report to Confluence.
Command Claude Code
Read weekly quality report output, deduplicate findings against existing Jira tickets, and create actionable Task tickets in Backlog with full field mapping.
Command Claude Code
Semantic + keyword search over this repository (source code and docs) via the local code-rag MCP tool (see tools/code-rag/). Natural-language query, any language.
Command Claude Code
Intelligent search for: $ARGUMENTS.
Command Claude Code
Command "search" from tomdwipo/claude-soul, covering advanced search command, search strategy (in order of priority), 1. vector database search, 2. fallback to codebase search and execution steps.
Command Claude Code
Produce a detailed system design for $ARGUMENTS using ASCII diagrams only (no Mermaid, no images — per workspace CLAUDE.md), with BEFORE/AFTER so the change is obvious. This is the architecture artifact ("what it is shaped like + why"), the upstream input to /breakdown-design (which turns it into step-by-step code).…
Command Claude Code
Generate a Technical Requirement Document for: $ARGUMENTS.
Command Claude Code
Run visual UI tests by comparing device screenshots against benchmark images. Supports ADB actions (tap, type, swipe, back, wait, launch) to navigate through app flows.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: