@uge/payo 0.1.7 → 0.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +33 -0
- package/dist/index.js +19 -19
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -24,6 +24,7 @@ project's conventions instead of guessing.
|
|
|
24
24
|
## Contents
|
|
25
25
|
|
|
26
26
|
- [What is Payo?](#what-is-payo)
|
|
27
|
+
- [Why Payo?](#why-payo)
|
|
27
28
|
- [Who is this for?](#who-is-this-for)
|
|
28
29
|
- [Quick Start](#quick-start)
|
|
29
30
|
- [How to use — a walkthrough](#how-to-use--a-walkthrough)
|
|
@@ -49,6 +50,38 @@ Where the assistant ships a headless CLI, Payo drives that tool's own AI to
|
|
|
49
50
|
write rich, project-specific docs; where it doesn't, Payo falls back to solid
|
|
50
51
|
templates — so you always end up with usable output.
|
|
51
52
|
|
|
53
|
+
## Why Payo?
|
|
54
|
+
|
|
55
|
+
Every AI coding session starts cold. Your assistant doesn't know you use Drizzle
|
|
56
|
+
over Prisma, that handlers live in `src/routes`, that you write Vitest specs
|
|
57
|
+
beside the file, or that commits follow Conventional Commits. So you re-explain
|
|
58
|
+
it — in chat after chat — and still get code that ignores half of it.
|
|
59
|
+
|
|
60
|
+
The fix is the guidance files each tool already reads (`CLAUDE.md`,
|
|
61
|
+
`.cursorrules`, `.github/copilot-instructions.md`, `AGENTS.md`). But writing them
|
|
62
|
+
by hand is tedious, easy to get wrong, and different for every tool. Most people
|
|
63
|
+
never do it, or do it once and let it rot.
|
|
64
|
+
|
|
65
|
+
Payo writes them for you in about two minutes — tailored to your actual stack,
|
|
66
|
+
in each tool's native format — so your assistant follows _your_ conventions from
|
|
67
|
+
the first prompt instead of guessing.
|
|
68
|
+
|
|
69
|
+
### Vibe coding, without the mess
|
|
70
|
+
|
|
71
|
+
Vibe coding is fast and fun — you prompt, the AI improvises, code appears. The
|
|
72
|
+
problem isn't the speed, it's that the assistant has no rules to improvise
|
|
73
|
+
_within_. So it guesses: a different ORM than the rest of the repo, files
|
|
74
|
+
scattered wherever, its own naming, your tests and commit conventions skipped.
|
|
75
|
+
Fine for a throwaway demo; on a real codebase it quietly piles up inconsistency
|
|
76
|
+
you pay for later in reviews, bugs, and refactors — and each new chat starts the
|
|
77
|
+
guessing over.
|
|
78
|
+
|
|
79
|
+
Payo gives that improvisation a guardrail. It generates the guidance files your
|
|
80
|
+
assistant already reads, so the AI reaches for _your_ framework, _your_ folder
|
|
81
|
+
layout, _your_ testing and git rules every time — without you stopping to explain
|
|
82
|
+
them. You keep vibe coding at full speed; the output just fits the project
|
|
83
|
+
instead of fighting it.
|
|
84
|
+
|
|
52
85
|
## Who is this for?
|
|
53
86
|
|
|
54
87
|
- **Devs starting a new repo** who want their AI assistant productive from
|