AGENT SKILL

principle-foundational-thinking

Foundational thinking. Apply when before writing logic, when choosing core types and data structures or ordering scaffold against features.

License 许可
MIT
最近更新
2026-11-15
Stars
★ 2
Forks
0

01 前言 Front Matter

name
principle-foundational-thinking
license
MIT
metadata
{ "source": "pstack principle-foundational-thinking, MIT, Copyright (c) 2026 Lauren Tan, github.com/cursor/plugins, adapted; checked against pstack 0.15.36 at commit 0bb6f37" }
description
Foundational thinking. Apply when before writing logic, when choosing core types and data structures or ordering scaffold against features.

03 SKILL.md 正文

<!-- Generated by scripts/build.mjs from the sources; edit the source, then run npm run build. -->

Foundational thinking

Structural decisions protect your options later. Code-level decisions protect simplicity.

Data structures first. Get the shape of the data right before writing logic. Define the core types early, trace every way the data is accessed, and choose structures that fit the dominant paths. Once the data is right, the code around it becomes obvious.

At code level, avoid repeating structure, not every line. Types and data models should converge. Three similar statements still beat a premature abstraction. Prefer explicit over clever. Test behaviour and edge cases, not line counts.

Shared state. Before two actors share state, ask what happens if another one changes it at the same time. If the answer is not "nothing", isolate.

Scaffold first. If something helps every later phase, do it first: build and test infrastructure, shared types, a check that runs on every change. Setup before features, tests before fixes. Keep each change small and single-purpose. Each increment should land one coherent abstraction or deepen one that exists, not spread a new capability across callers as special cases.

Subtraction comes before scaffolding: remove dead code first, then lay foundations.

04 同仓库更多 Skills

erickb336
erickb336/sage-stack

writing-standard

Write at 80% of Simplified Technical English. Apply to any text an agent writes for a person: messages, reports, specs, findings, reviews, plans.

★ 2
erickb336
erickb336/sage-stack

sage

The state tool of sage mode: records tasks, routes, agent runs, findings, verdicts by head SHA and the user's gates in ~/.claude/sage/<project>/. Use in sage mode for every change of a task's state, and before any merge. Claude Code only.

★ 2
erickb336
erickb336/sage-stack

sage-help

Help with sage: how to set it up, switch sage mode and autopilot, read the board, answer the chief's questions, pick a skill or a principle, fix a run that went wrong, and find where sage keeps its files. The user types /sage:sage-help (or /sage-help) with a question. Load it only when the user types it; do not load it on your own. Claude Code only.

★ 2
erickb336
erickb336/sage-stack

report

The report that every sage agent ends with: STATUS, RESULT, EVIDENCE, FINDINGS, QUESTIONS, NOT VERIFIED, BRANCH. Use at the end of any task that the sage chief of staff gave you. Claude Code only.

★ 2
erickb336
erickb336/sage-stack

remote-control

Set up Remote Control, so that the user can follow, steer and start Claude Code sessions from the Claude app on a phone. It turns Remote Control on for every new session, and it can run a server in a folder (such as ~/workspace) that starts at each login. Use when the user asks to reach sessions or start new ones from a phone, or to set up, check or undo Remote Control. Claude Code only.

★ 2
erickb336
erickb336/sage-stack

readme-guide

Write a project README. Apply when you write, change or review a README of any project, in any language.

★ 2