stevengonsalvez

Autonomous product factory — /make-a-goal in godmode. Point it at a north-star outcome and it runs the whole delivery machine unattended: brainstorm the feature landscape (Discover), put every idea through a Feasibility Court, cluster into a Roadmap of epics, then per epic Plan → adversarial review → Execute (model-paired build) → VERIFY (drive the real UI/TUI/API, not mocks) → ship a stacked PR, looping until the backlog is dry or a budget/time bound fires. One human gate (roadmap blessing), hard stop rules, always-on tabbed RAG dashboard, crash-proof resume from state files. Use when the user says 'godmode', 'run the factory', 'ship X to nirvana', 'execute this whole backlog autonomously', 'goals within goals', or wants a multi-epic programme driven end-to-end with real end-to-end verification. NOT for single features, one-off verification, or scoped builds — use /make-a-goal, browser/tmux verification skills, or a plain plan for those.

Sync user-level agent config changes back to the ainb-toolkit repo (works for Claude, Codex, Copilot)

Produce a self-contained, richly styled HTML explainer for any topic the user asks about. Picks the right template from a bundled set of 22 visual patterns (feature explainer, concept explainer, module map, PR review, ADR, options paper / trade-off analysis, system diagram, flow- chart, status report, slide deck, prototype, editor, etc.), fills it with real content, augments with inline diagrams via sister skills (/fireworks-tech-graph for architecture / flow / sequence diagrams, /graphify for knowledge graphs), applies a Claude-brand polish layer, and publishes it: by default onto the configured here.now custom domain (path mount + searchable categorised index + password lock per the config's protect rule, driven by ~/.herenow/explainers.json), or a plain here.now URL, or a GitHub gist (--gist / --gist --public). Local-only output is available with --local. Use when Stevie says "/explain-to-me", "explain-to-me X", "make me an explainer for X", "give me an HTML explainer", "render this as a webpage", "ADR for

Self-improvement through conversation analysis. Extracts learnings from corrections and success patterns, permanently encoding them into agent definitions. Philosophy - Correct once, never again.

Claude Code observability skill: analyze session traces stored in Langfuse, extract learnings from corrections, identify success patterns, and propose agent/skill improvements based on historical data. Powers self-improvement through trace analysis of Claude Code sessions.

Create well-formatted git commits for changes made during the session

Generate a handover document for transferring work to another developer or spawning an async agent

Interview the user about a plan file to extract detailed requirements, clarify ambiguities, and uncover edge cases. Uses iterative questioning to produce a comprehensive specification.

Argus — all-in-one information gathering & reconnaissance toolkit. 135 modules covering network infrastructure, web app analysis, and security/threat intelligence. Use for domain recon, subdomain enum, SSL analysis, tech stack detection, vulnerability scanning, and OSINT.

Manage secrets via Bitwarden CLI (bw). Use when pulling secrets into a shell session, creating/updating Secure Notes from .env files, listing vault items, or setting up Bitwarden on a new machine. Secrets live in Bitwarden, get loaded into memory on demand, and die with the shell session — no files on disk.

Develop a thorough, step-by-step specification for a given idea

Set up a recurring build tracker cron job for any GitHub repo. Runs a zero-LLM shell script to detect stale PRs, stale assigned issues, and phase progress, then posts to a Discord channel only when there's something actionable. Use when asked to "track this build every N hours", "prod agents on a project", "set up a build monitor", "watch this repo for stale work", or similar. The tracker is cheap to run — script does all the work, the agent only speaks when findings exist.

Run long-running coding tasks in cloud environments (Claude Code or Codex), with session teleporting and automatic PR creation.

Delegate coding tasks to subagents or run Claude Code/Codex in tmux sessions. Use the Task tool for focused multi-step coding work. Use tmux for long-running interactive sessions, parallel worktree-based fixes, and PR reviews. NOT for simple single-file edits — do those directly.

Create well-formatted git commits for changes made during the session

Get a Distinguished Engineer level technical critique of the current approach

Reclaim disk space by finding and deleting regenerable build/dependency directories (node_modules, target, .next, dist, build, .gradle, .turbo) and optionally running `cargo clean` and Docker prune. Dry-run by default, age-gated, and protects git-locked worktrees plus recently-touched work so active sessions are never clobbered. Use when disk is low, when `df` shows the volume near full, or when the user says "clean disk", "free up space", "disk-space-cleaner", or "what's eating my disk".

Write or debug tmux-driven end-to-end TUI tests ("tripwires") for the ainb terminal app. Use when the user asks to "write a tmux test", "add a tripwire", "verify the TUI in tmux", "test feature X by pressing key Y", "validate plugin Z renders", or when editing any file under `crates/ainb-core/tests/tripwire_*.rs`. Codifies the silent traps we hit during Phase 7 plugin testing — macOS AMFI SIGKILL of staged binaries (exit 137, no stderr), first-run wizard intercepting keystrokes, EnvFilter crate-name drift hiding logs, and substring-OR assertions that pass while the feature is broken. Use proactively before writing any new `tripwire_*.rs` test, and reference whenever an existing tripwire fails for non-obvious reasons.

Workflow-backed Jarvis control panel. Runs the deterministic `hangar` workflow with verb=needs (discover → enrich → prioritize), renders the Jarvis HUD from its render-ready cards, fires AskUserQuestion per blocked session, and routes each answer back via tmux send-keys (broker fallback only). Requires the workflow gate (CLAUDE_CODE_WORKFLOWS=1). If the gate is off, fall back to the prompt-driven `/ainb-fleet:needs` skill.

Show fleet status — every claude session running on the host, merged across ainb + claude-peers broker + background jobs. Use when you need to enumerate sessions before composing an action, check the `summary` of each session, or pipe the list into jq for filtering. (Writes go via tmux by default; a `peer_id` is just an extra discovery signal / fallback channel, not a routing requirement.) Default output: text table. Pass --format json for LLM consumption.

Fleet orchestration overview — the `ainb fleet ...` Rust subcommand namespace for driving every claude session on the host. Routes to the sub-skills (standup / broadcast / sequence / needs / daemon / atc). Invoke this for an at-a-glance map of what fleet can do; reach for the specific sub-skill for the verb you want.

Generate intricate hand-drawn sketchnote illustrations starring Popa, a cute pink blob with a green sprout and a notepad, on soft pastel scenes. One busy page of many linked boxes, notes, arrows and icons — busy but fully legible. Use for dev/product/system explainers, how-it-works, architecture, walkthroughs, and friendly social/blog/README art.

Generate intricate hand-drawn sketchnote illustrations starring Popa (a pink blob with a green sprout and a notepad). Use when the user wants illustrations/diagrams/explainer images/shot lists for an article, post, README, deck, system, or idea. Alias of illustration:popa.

ATC (Air Traffic Control) — the persistent orchestrating brain of the fleet. A plain `ainb` Claude session running a generated CLAUDE.md policy, woken on an OS-timer heartbeat (default 15 min) built from the LLM-free `fleet needs` read — which is itself HOOKS-PRIMARY (event-sourced): ATC learns ASK/WAIT/IDLE from the materialized `current_state` table, not by scraping panes, with a tmux fallback for non-Claude agents. `atc setup` installs the global Claude Code hooks into ~/.claude/settings.json. It auto-clears the safe/blocked sessions via the fleet verbs (confident ASK → broadcast; ERR → continue within a retry cap) and escalates the uncertain ones to the phone bridge. Supersedes the `daemon` skill for managed fleets. Use to provision / inspect / tear down an ATC instance.

Build a long-lived, filtered SLICE of the global learnings KB and answer a question-set over it ("ask the auth subsystem", "ask the migration log"). Unlike /reflect:recall (a fresh hybrid query each time), a corpus is a saved filter snapshotted to disk — prime it once, ask many questions, reprime when the KB drifts. Use when the user wants a durable Q&A session against one filtered area of their own code history rather than a one-shot search.

Report reflect drain spend over a time window — tokens split by cached (cache_read), uncached writes (cache_creation), and io (input+output), with a $ estimate, grouped by day / outcome / model / transcript. Reads the drainer's cost log and surfaces outlier runs and cache-reuse health (the 41.5M-token failure mode = low cache reuse + high cache writes). Also reports the recall followup rate (the recall-quality self-monitor: how often a session searched again within 30s and got disjoint results). Use to answer "what is reflection costing me" for the last day / week, or "is recall satisfying".

Export or import the reflect knowledge base as a deterministic, git-friendly tarball — the learnings markdown corpus plus the reflect.db rows in one snapshot. Use to back up the KB, move it to another machine, or restore it: `export` writes the tarball, `import` restores it (with an optional GraphRAG reindex). Answers "snapshot my reflect KB", "move my learnings to another machine", or "restore my knowledge base from a backup".

The global knowledge indexer. Harvests ALL memory sources across all tools (Claude, Codex, Copilot, Gemini) and all project types into the unified GraphRAG + QMD knowledge base. Archives originals, generates entity sidecars, and dual-indexes for future retrieval. This is THE command that makes the knowledge base comprehensive.

Full conversation scan for self-improvement. Detects behavioral corrections and knowledge signals, classifies them, proposes agent updates and knowledge notes with entity sidecars for GraphRAG indexing. Correct once, never again.

Retrieve relevant prior learnings from the global knowledge base. Hybrid vector + graph search over 170+ indexed learnings, reranked by confidence, recency, and tag overlap. Use when starting work, debugging a recurring problem, or before implementing a feature that may have prior art.

Show reflection metrics, pending reviews, sidecar coverage, and GraphRAG health. Read-only views into the reflect system state. Can also approve/reject pending low-confidence items.

Project-level memory consolidation. Merges orphaned worktree memory directories into a single .agents/MEMORY.md for the current project. Deduplicates, sections, and proposes cleanup of orphan dirs. Does NOT index into the global knowledge base — use reflect:ingest for that.

Browser automation and inspection for AI agents via WebSocket

Generate Ian-style body illustrations for articles. Use when the user asks to create "weird"/"Blot"/"hand-drawn"/"body illustration"/"article illustration"/"illustration suggestions"/"shot list"/"de-title/edit-image" assets for an article, post, blog, Notion doc, workflow doc, methodology, process, structure, state, metaphor, or argument. Defaults to the Blot IP, pure-white hand-drawn line art, sparse red/orange/blue annotations, and a clean but wildly imaginative visual style.