Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From gstack-distilled
Estimate work and scope decisions in the AI-coding era. Boil the Lake, AI compression ratios, three-layer search before building.
npx claudepluginhub 0xabrar/gstack-distilled --plugin gstack-distilledHow this skill is triggered — by the user, by Claude, or both
Slash command
/gstack-distilled:estimate-and-scopeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
How to size work and decide between approaches when AI compresses the cost of completeness.
Scores implementation options with Thoroughness Ratings (1-10) to favor high-quality choices, since AI minimizes time costs. Includes scope checks for contained vs unbounded work.
Use when a user requests new work - features, components, integrations, or additions - to challenge assumptions, evaluate effort, surface alternatives, and ensure the work is worth doing before committing to it
Explores 2-3 solution approaches, evaluates tradeoffs like code size and deps, picks simplest after research verification, then implements. Triggers: build, implement, create, feature, add.
Share bugs, ideas, or general feedback.
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.