zcaceres

Answer in a simple, concise voice, no filler or hedging. Persisted per project or per user, in prose-only, prose+code, or laconic-code (code-first) mode. A per-turn reminder refocuses the voice mid-session (cadence configurable). Invoke via /laconic (on|off|status|mode|cadence).

Restate the last message in plain human language, with no jargon.

Surface unaddressed threads from the conversation — bugs mentioned but not fixed, deferred decisions, dropped nits, cross-workstream dependencies, unverified claims, and promised-but-not-done items — as a tight, skimmable report. Reports; never edits code. Use when the user says "loose ends", "any loose ends", "what did we leave hanging", "what didn't we get to", "what got dropped", "open threads", "unaddressed items", "what did we punt on", or "/loose-ends".

Interactive file cleanup for Downloads, Desktop, and Documents, plus stale git worktree cleanup. Goes item-by-item proposing delete, move, or keep. Use when user says "clean up my computer", "organize my downloads", "help me declutter", "what's in my Downloads", "file cleanup", or "clean up old worktrees".

Scan recent conversation transcripts for safe commands that could be auto-allowed by your CLI agent (Claude Code, Codex, Cursor, …), preview the proposed allowlist changes, then write them to the right config. Use when the user says "reduce permission prompts", "auto-allow safe commands", "optimize permissions", or "/optimize-permissions".

One skill for committing work and opening PRs. Two modes — normal (default) commits your conversation changes, pushes, and opens a single PR against the trunk; stacked turns the same command into a stacked-PR workflow (checkpoint slices, submit, sync, bottom-up merge). Toggle with /pr setup. Any PR can be opened as a draft with --draft (-d), or make drafts the default with /pr setup. Also ships a diff-size nudge hook toward /pr when the uncommitted diff grows large. Agent-callable — an agent working through a task should invoke this to ship a finished slice — `checkpoint`/`commit` at each logical seam to land a stacked PR and continue on a fresh branch, or `update` to commit and open/refresh a single PR. Reach for it when a unit of work is complete or the user asks to commit, push, checkpoint, or open a PR. Do not autonomously run `merge` (it lands PRs into trunk) unless the user asks. Runs under both Claude Code and Gemini CLI (install with --agent gemini). Uses git stack when installed, falls back to gh + g

Find large files and directories safe to delete — inactive node_modules, local AI models, Docker artifacts, package caches, old downloads. Use on "free up space", "disk space".

Explain a concept like the listener is five years old — short words, everyday analogies, zero jargon. Explains the current conversation by default, or a topic passed after the command. Invoke via /eli5.

Run Gemini Deep Research reports on any topic. Use when user says "deep research", "research report", "gemini research", or "run a research report on...". Generates comprehensive research reports using Google's Deep Research agent.

Search for recent news and updates about topics in your INTERESTS.md file (like Google Alerts). Use when user says "check my interests", "interests digest", "what's new", "news digest", or "update me on my interests". Generates a concise digest only when there's new information.

Organize and triage files from the Notion export folder. Use when user says "triage notion", "organize notion", "clean up notion", "notion cleanup", or "let's work on notion".

Updates the NOW.md dashboard in Obsidian by aggregating tasks from project TODO.md files. Use when user says "update my NOW", "refresh my dashboard", "what should I work on", or "let's do my weekly review". Supports quick regeneration mode and guided weekly review mode.

Generate text-heavy graphics (banners, social images, OG images) using Playwright to render HTML with real web fonts. Perfect for branded collateral where typography matters.

Multi-phase market research for evaluating a business idea. Runs ecosystem surveys, competitive deep dives, distribution analysis, and CAC estimation. Creates comprehensive summary documents. Use when user says "research business idea", "market research", "evaluate this market", or wants to understand competitors and unit economics.

Create new Claude Code skills with proper structure and documentation. Use when the user asks to create, design, or build a new skill, or needs help structuring skill files.

Automated SPY 0DTE call options trading bot using Robinhood. Monitors SPY price, buys a 0DTE call option, and sells at 3% profit. Use when user says 'run spy bot', 'trade spy', 'spy options', or 'start trading bot'.

Audit a third-party code repository (usually a GitHub URL) for security problems, malicious code, supply-chain risk, and low-quality / dangerous patterns before adopting or running it. Use when the user asks to "investigate this repo", "is this repo safe", "audit this GitHub repo", "look for malicious code in", "vet this dependency", or shares a repo URL and asks whether it's trustworthy.