lancejames221b

Mark a logical phase completion in haivemind. More formal than /snapshot — used at step/phase boundaries in multi-phase work. Creates a named, resumable point that /continue can restore from. Triggered by /checkpoint, "checkpoint this", "mark this as a checkpoint", or at phase boundaries in long-running tasks.

Run the Qwen Code CLI as a one-shot bounded executor in a plan/do/verify loop. A frontier model (or you) plans the next bounded step and verifies the result; qwen-do makes a local model do exactly that one step, smoke-test first, then stop. Use when you want a cheap local model to do grunt coding while a smarter orchestrator keeps it on rails.

Scan git commits for PII, credentials, API keys, and passwords before they are pushed. Automatically gates commits via a pre-commit hook. Use when installing PII scanning on a repo, manually scanning a file or diff for credentials, or when a commit is blocked by the hook and remediation is needed. Triggers on "scan for PII", "check for credentials", "install PII guard", "pii hook", or when a commit is blocked by a PII check.

Runs a full CORE-EEAT 80-item content quality audit, scoring content across 8 dimensions with weighted scoring by content type. Produces a detailed report with per-item scores, dimension analysis, and a prioritized action plan.

Deep analysis and debugging with Opus. Systematically investigate problems, identify root causes, and recommend fixes with evidence.

PR review skill. Two modes: /pr [link] = internal thoughts only, what to look for, what to test — NO GitHub action ever. /pr-comment [link] "make it so #1" = draft a GitHub PR comment in <USER_NAME>s voice, present for approval, post only on explicit "go". Passphrase + "go" are both required before any GitHub write. Without both gates, nothing leaves the building.

Deep reflection and optimization with Opus. Two modes — /self-reflect analyzes completed work, extracts root causes, and stores lessons. /optimize analyzes a process or system, determines the right model and approach, then executes improvements. Use when reflecting on what happened, extracting lessons, optimizing workflows, or improving approaches. Triggers on "self-reflect", "reflect on", "optimize", "what went wrong", "what can we improve", "lessons learned".

Deep static analysis and bug hunting for any codebase.

Manage the Kanban task board — create, start, list, and trash tasks from Discord or voice. Wraps the kanban CLI to give Jarvis full board access without opening a browser.

Route Jarvis audio responses to a Sonos speaker. Mic stays on Discord/phone — only the output is redirected. Supports per-message routing and a persistent speaker mode that stays active until turned off.

Launch a safe Claude Code subagent development session for a repo. Use when the user wants to start building a feature, write code, or kick off a coding task. Opens an isolated branch with safety guardrails — agents commit freely but cannot push, open PRs, or touch main.

Send a Jarvis-voiced TTS announcement to a Sonos speaker in the house. Uses Chatterbox for voice generation. Use when the user wants to send a spoken message to someone in another room via a Sonos speaker.

Interactive Jarvis Voice installer. Walks through the complete setup from clone to first voice response, including tier selection and skill installation. Use when someone says install Jarvis, set up Jarvis voice, install Jarvis voice, or wants to get the voice bot running.

Interactive voiceprint enrollment for Jarvis Voice. Guides the user through enrolling their voice so only they can command Jarvis. Use when someone says enroll my voice, set up voiceprint, train Jarvis to recognize me, or voice enrollment.

Install and configure Jarvis Voice — a real-time Discord voice assistant for OpenClaw. Speak in a Discord voice channel and your OpenClaw agent responds by voice.

Unified communications check — iMessage texts, Signal messages, recent phone calls, and optional voicemail. Invocable on-demand or from voice. Produces TL;DR for voice and full report for Discord.

Orchestrate multi-model consensus (Gemini 3 Pro/Flash, Sonnet 4.6, Codex 5.3, Opus 4.6) for i2i/MCIP design, protocol analysis, and implementation decisions in OpenClaw. Use when you need higher-confidence outputs by collecting independent model opinions, reconciling disagreements, and producing a single consensus recommendation with rationale and confidence.