lightarktech
- 15 skills
- 0 followers
- 7 hours ago last updated
- ▌ Mainline · lightarktechPin what this session is for in a file, account for every detour, and balance the ledger before closing. Use when opening a session, picking up a handoff, noticing a problem outside the current job, or being asked "what are we actually doing".
- ▌ Bug Autopsy · lightarktech bundleStructured diagnosis for bugs — no guess-and-patch. Use when something is broken, throwing, failing, or slow and the cause isn't already proven.
- ▌ Grill Founder · lightarktechInterview a non-technical founder to surface blind spots before executing any deliverable — code or otherwise. Use before a feature request, a launch, publishing or any external content, marketing copy and positioning decisions, pricing, deploy, hosting, domain or migration work, infrastructure changes, or dispatching agents/subagents to do the building. Trigger on any vague instruction ("add a login page", "refresh the site", "make it feel warmer", "just ship it") and on any request with irreversible side effects or more than an hour of work.
- ▌ Loop Contract · lightarktechWrite an exit-condition contract before letting any AI run unattended — a background agent, a scheduled loop, a "keep going until it works" task. Use whenever work is handed off to run without a human watching.
- ▌ Model Tiering · lightarktechAssign the right model tier to each job — firepower matched to the difficulty, and the author and the verifier deliberately on different models. Use when dispatching any sub-agent, sending out a scout to explore or search, configuring a multi-agent workflow, or when quota pressure appears.
- ▌ Bad News First · lightarktechReport the true state of the work to the founder — failures plainly, no cheerleading, bad news before good. Load in every session with a founder; apply to every status report.
- ▌ Context Hygiene · lightarktechKeep AI sessions short, rules in files, and context fresh. Use when sessions grow long, quality drifts, rules seem forgotten, or the founder asks why the AI "got dumber".
- ▌ Decision Wiring · lightarktechRoute decisions correctly between a non-technical founder and their AI engineering lead. Load at the start of any working session with a non-technical founder, or whenever unsure whether to ask the founder or decide yourself.
- ▌ Red Light First · lightarktech bundleWrite the failing test before the fix or feature — never trust a green light you didn't first see red. Use when building any feature or fixing any bug.
- ▌ Two Axis Review · lightarktechReview finished work on two separate axes — craft quality and faithfulness to what was asked — and never let one axis excuse the other. Use before merging any meaningful change.
- ▌ Handoff Contract · lightarktechWrite a self-contained handoff when work moves to a new session, a different AI tool, or another person. Use when context is about to be lost — quota exhausted, switching tools, ending a session mid-project.
- ▌ Surgical Changes · lightarktechBehavioral discipline for every code change — think first, keep it simple, touch only what you must, aim at a checkable goal. Load whenever writing or modifying code.
- ▌ Vertical Tickets · lightarktech bundleSlice work into thin end-to-end feature tickets, never into technical layers. Use when breaking any plan, spec, or feature request into workable units.
- ▌ Dispatch Economics · lightarktechCost and quality discipline for dispatching sub-agents, background workers, or multi-agent workflows. Use before launching any agent fleet or long-running autonomous task, and whenever someone mentions burning through quota or budget.
- ▌ Rules As Mechanism · lightarktechA rule written in prose is a request; a rule wired into the harness is a guarantee. Use when a standing rule has been broken twice, when session-start context keeps growing, or when the AI must read huge specs before it can safely touch code.