@uge/payo 2.4.9 → 2.5.1

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.
Files changed (3) hide show
  1. package/README.md +60 -15
  2. package/dist/index.js +179 -171
  3. package/package.json +12 -4
package/README.md CHANGED
@@ -2,7 +2,7 @@
2
2
 
3
3
  <img src="https://raw.githubusercontent.com/uttam-gelot/payo/main/assets/logo.png" alt="Payo" width="200" />
4
4
 
5
- **Generate project-tailored AI assistant rules & skills in minutes.**
5
+ **One interview. Rules your AI can't skip.**
6
6
 
7
7
  Payo interviews you about your stack, then writes the guidance files your AI
8
8
  coding assistant reads — so Claude, Cursor, Copilot, and friends follow _your_
@@ -32,6 +32,7 @@ project's conventions instead of guessing.
32
32
  - [Already have a project? Payo detects your stack](#already-have-a-project-payo-detects-your-stack)
33
33
  - [What gets generated](#what-gets-generated)
34
34
  - [What it asks about](#what-it-asks-about)
35
+ - [Code and PR reviews](#code-and-pr-reviews)
35
36
  - [AI vs. template generation](#ai-vs-template-generation)
36
37
  - [Bootstrap prompt](#bootstrap-prompt)
37
38
  - [Resume anytime](#resume-anytime)
@@ -56,6 +57,9 @@ templates — so you always end up with usable output.
56
57
 
57
58
  And for those wondering what Payo means, in Gujarati it means foundation — what a building or project is built on.
58
59
 
60
+ Why I built it, and what I learned along the way:
61
+ [Getting an AI assistant to follow your repo's rules, not just read them](https://uttamgelot.com/notes/why-i-built-payo/).
62
+
59
63
  ## Why Payo?
60
64
 
61
65
  Every AI coding session starts cold. Your assistant doesn't know you use Drizzle
@@ -136,6 +140,8 @@ Copilot, Codex, and Antigravity. It plans both
136
140
  layers together, so each check runs in exactly one place — the agent is told not
137
141
  to re-run what a hook already runs.
138
142
 
143
+ ![change-audit blocks a push because the column lastVerifiedAt breaks the snake_case rule](https://raw.githubusercontent.com/uttam-gelot/payo/main/assets/change-audit-block.png)
144
+
139
145
  **6. One canonical copy, every tool.** One `SKILL.md` per topic under
140
146
  `.agents/skills/`, with Claude Code and Windsurf pointed at it by symlink. No
141
147
  per-tool duplicates to edit twice and no copies to drift apart — which is
@@ -220,6 +226,9 @@ guidance files straight into your repo.
220
226
  answers produced — every one preselected — so you can uncheck anything you
221
227
  don't want a file for before a single one is written. Skipped when there's
222
228
  only zero or one skill to decide between.
229
+
230
+ <img src="https://raw.githubusercontent.com/uttam-gelot/payo/main/assets/skill-list.png" alt="Payo shows the stack summary, then the list of skills it will generate, each preselected" width="720" />
231
+
223
232
  6. **Payo generates the guidance.** It writes one universal layout that every
224
233
  skills-compatible tool reads (see the table below). With an agent CLI
225
234
  installed, skills are generated in parallel by the AI; otherwise solid
@@ -331,6 +340,9 @@ agent uses it at that point to check your pending change against the relevant pr
331
340
  skills and flag anything that conflicts. It reads the diff and reports — it never runs
332
341
  your tests, linter or formatter, because your git hook already does.
333
342
 
343
+ Payo can also add a **pr-review** skill for code and PR reviews. See
344
+ [Code and PR reviews](#code-and-pr-reviews).
345
+
334
346
  ### Guardrails enforced by hooks, not just prose
335
347
 
336
348
  Skills are guidance the assistant _should_ follow — but an agent can skip prose. So
@@ -406,6 +418,43 @@ your stack needs. Dimensions covered:
406
418
  every push)
407
419
  - **Change audit** _(optional)_ — opt into a skill that checks your pending
408
420
  change against the project skills before commit or push
421
+ - **Code review** _(optional)_: opt into a skill for on-demand reviews, then set
422
+ the team defaults: what you review, which focus areas to recommend, how findings
423
+ read, and a team checklist every review checks
424
+
425
+ ## Code and PR reviews
426
+
427
+ Ask a plain assistant to "review this PR" and you get a generic review. It doesn't
428
+ know your conventions, it re-runs checks your git hooks already run, and it reports
429
+ findings it never verified. Payo can add a **pr-review** skill
430
+ (`.agents/skills/pr-review/SKILL.md`) that fixes that. One question turns it on, and
431
+ one gate sets your team's defaults: what you review, which focus areas to recommend,
432
+ how findings read, and an optional team checklist.
433
+
434
+ ![pr-review asks about focus areas, review level and project skills before it reads any code](https://raw.githubusercontent.com/uttam-gelot/payo/main/assets/pr-review-flow.gif)
435
+
436
+ **What it reviews.** Your local changes, the current branch, or a GitHub / GitLab PR
437
+ or MR by number. It never assumes `main` is the base.
438
+
439
+ **It asks before it reads any code.** What to focus on (bugs, security, code quality,
440
+ tests), which level of findings you want, and whether to check the change against
441
+ your project skills. In Claude Code that is one `AskUserQuestion` prompt.
442
+
443
+ **Verified, labeled, ordered.** It checks each finding against the surrounding code
444
+ before reporting it, labels it the [Conventional Comments](https://conventionalcomments.org/)
445
+ way (`issue (blocking):`, `suggestion:`, `nitpick:`, and so on), and puts the worst
446
+ first.
447
+
448
+ **You pick what happens next.** Stop, let it fix the issues in your own change, post
449
+ one review on the PR / MR after a confirm, or get inline comments to paste yourself.
450
+
451
+ **Safe with untrusted code.** It fetches a PR with plain git into a temporary ref, and
452
+ never checks it out or runs its code. It needs `gh` or `glab` only to read a PR
453
+ description or to post, and it never approves a PR or requests changes.
454
+
455
+ **How to start it.** Ask in words ("review PR 42") or type `/pr-review`. Claude Code's
456
+ `/code-review` and Codex's `/review` are built-in commands, so typing them runs those
457
+ instead.
409
458
 
410
459
  ## AI vs. template generation
411
460
 
@@ -448,20 +497,16 @@ generating what's missing. Finished runs clean the directory up automatically.
448
497
 
449
498
  Payo works today, but it's still early. Here's where it's headed:
450
499
 
451
- - **Deeper monorepo support.** Payo now enumerates workspace members — including
452
- nested workspaces the root never declared — detects each package's stack,
453
- classifies hybrid repos (frontend + backend languages) as one full-stack
454
- project, and writes per-package notes into one root config (see
455
- [Already have a project?](#already-have-a-project-payo-detects-your-stack)).
456
- Next is going further: per-package skills and guidance for repos where each
457
- workspace wants its own conventions, and workspace enumeration for the
458
- remaining ecosystems (Python, PHP, .NET, Ruby).
459
- - **Broader stack coverage.** More languages, frameworks, ORMs, databases, and
460
- AI tools, plus deeper, more opinionated defaults for the ones already
461
- supported — so the guidance fits more of the ecosystem out of the box.
462
- - **A smoother flow.** Faster, clearer prompts; better defaults and grouping;
463
- tighter summaries and confirmations; and a generation step that's quicker and
464
- more transparent about what it's doing.
500
+ - **Add one skill without the full interview.** Today Payo asks every question,
501
+ even if you only want pr-review. Next, you name the skill and answer only its
502
+ questions.
503
+ - **More languages, libraries and frameworks**, with recommendations from people
504
+ who work in those stacks every day.
505
+ - **An audit flow.** Payo compares your skills with the current codebase and
506
+ shows where they no longer match.
507
+ - **A better flow for existing projects**, including per-package skills for
508
+ monorepos where each workspace wants its own conventions, and workspace
509
+ enumeration for the remaining ecosystems (Python, PHP, .NET, Ruby).
465
510
 
466
511
  Have a stack you want supported or an idea to make the flow better?
467
512
  [Open an issue](https://github.com/uttam-gelot/payo/issues) or see