Menu
Estimate work and scope decisions in the AI-coding era. Boil the Lake, AI compression ratios, three-layer search before building.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Working with AI coding agents — User Sovereignty, agreement-as-signal, Karpathy/Willison framing, per-model overlays, and the rule to measure your prompt nudges.
Compound knowledge across sessions. Plan-tune dual-track psychographic profile (declared vs behavior), retro philosophy that demotes LOC, the keep-or-toss test for learnings.
Code review, debugging, and incident discipline. Confidence calibration, root-cause iron law, alert-on-changes rule, the pre-existing blame protocol.
When to ship vs not ship. The single ship gate, six auto-decision principles for plan reviews, and the Confusion Protocol for when to stop and ask.
UX quality bar — Krug's three laws of usability, the eight DevEx first principles, time-to-hello-world tiers, the Goodwill Reservoir, the Pit of Success.
Decide what to build using YC's six forcing questions and the four CEO scope modes. Use before any new feature, product bet, or GTM angle.
| name | estimate-and-scope |
| author | 0xabrar |
| description | Estimate work and scope decisions in the AI-coding era. Boil the Lake, AI compression ratios, three-layer search before building. |
How to size work and decide between approaches when AI compresses the cost of completeness.
Source: gstack ETHOS.md, CLAUDE.md, ship/SKILL.md.
"AI-assisted coding makes the marginal cost of completeness near-zero. When the complete implementation costs minutes more than the shortcut — do the complete thing. Every time."
Lake vs ocean:
Boil lakes. Flag oceans as out of scope.
"'Ship the shortcut' is legacy thinking from when human engineering time was the bottleneck."
Always quote both human-time and AI-assisted time:
| Type of work | Compression |
|---|---|
| Boilerplate | ~100x |
| Tests | ~50x |
| Feature | ~30x |
| Bugfix + regression | ~20x |
| Architecture | ~5x |
| Research | ~3x |
Phrase as: "2 weeks human / ~1 hour AI-assisted."
When evaluating "approach A (full, ~150 LOC) vs approach B (90%, ~80 LOC)" — almost always choose A.
"The 1000x engineer's first instinct is 'has someone already solved this?' not 'let me design it from scratch.'"
Layer 1: Tried and true — built-ins, official docs, well-established libraries.
"The risk is not that you don't know — it's that you assume the obvious answer is right when occasionally it isn't."
Layer 2: New and popular — recent blog posts, trending patterns, popular libraries.
"Humans are subject to mania. Mr. Market is either too fearful or too greedy. Search results are inputs to your thinking, not answers."
Layer 3: First principles — your own reasoning from fundamentals.
"Prize them above everything else."
Trust ranking: Layer 3 > Layer 1 > Layer 2.
Most engineering culture says "don't reinvent the wheel" by default. This inverts that: "Once in a while, questioning the tried-and-true is where brilliance occurs."
{runtime} {thing} built-in{thing} best practice {current year}"The most valuable outcome of searching is not finding a solution to copy. It's finding a clear reason why the conventional approach is wrong... zig while others zag. When you find one, name it. Celebrate it. Build on it."
"The truly superlative projects are full of these moments — 11 out of 10."
When you find yourself thinking "ship the 90% version":
If it's a lake and the gap is hours not weeks → boil it.