ryanportfolio/Local-CPU-only-PTT

impartial-review

Use when the user asks to review, audit, or stress-test recent code changes with fresh independent agents; requires exposed multi-agent tools or an authenticated Codex CLI.

addskill

Add a new skill to this repo so it's available in every Claude Code web session. Use when the user says $addskill, asks to "add a skill", "install a skill", "create a skill", or wants a third-party skill (e.g. superpowers, impeccable) to show up in the…

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy.

enhance-prompt

Rewrite a rough or under-specified request into a polished, copy/paste-ready prompt that any agent or LLM can act on cold. Use when the user gives a quick description of something they want done and asks for it to be turned into a better prompt — e.g., "make…

handoff-audit

Generate a self-contained, copy/paste-ready audit prompt so a SEPARATE fresh session can independently verify a change made in the current session. Use when the user says $handoff-audit, or asks to "double-check this in another session", "have another session…

merge

Turn on Auto-Merge Mode for the session — going forward, every completed task is automatically committed, pushed, opened as a PR, and merged into main (with conflict resolution), no per-merge confirmation. Use when the user says $merge, "auto-merge for the…

optimize-context

Reduce per-turn context/token cost (the always-loaded weight: CLAUDE.md kernel, MEMORY.md index, the deferred MCP tool-name list, MCP instruction blocks, and the injected available-skills list) — then propagate the portable, generic wins up to the…

recall

Look up project-specific reference and capture new learnings for this codebase. Use when starting work in an unfamiliar area, when the user asks "what do we know about X" / "any pitfalls with Y" / "remind me how Z works", says "remember this" / "save this…

sync-starter

Sync this project with the claude-starter template repo — pull skill/hook/settings improvements down from the template, or push a generic improvement made here back up to it. Use when the user says $sync-starter, "pull template updates", "update skills from…

why

Honest second look at the recommendation the model just made — why it matters, the real reasoning behind it, and (the point) what it could be missing, quick and well-rounded. ONLY use when the user explicitly types the `$why` slash command. Do NOT trigger on…

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

humanizer

Remove AI writing patterns and add human voice. Use when the user says /humanizer, /unslop, asks to "humanize", "de-AI", "de-slop", or "un-ChatGPT" text, wants a draft rewritten (blog, essay, PR, docs, memo, email), voice-matched writing, or an AI-tell review…

impeccable

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells,…

optimize-context

Reduce per-turn context/token cost (the always-loaded weight: CLAUDE.md kernel, MEMORY.md index, the deferred MCP tool-name list, MCP instruction blocks, and the injected available-skills list) — then propagate the portable, generic wins up to the…

writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment