# vision

Adopt this skill: https://proskills.md/skills/other/kunchenguid-vision-skills-vision

Page: https://proskills.md/skills/other/kunchenguid-vision-skills-vision
This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required.

## File: skills/vision/SKILL.md
size: 8000
upstream: https://github.com/kunchenguid/vision/blob/main/skills/vision/SKILL.md

```text
---
name: vision
description: >
  Draft and stress-test a VISION.md for a repository, then iterate with the
  author on an interactive review board until approved. Use on /vision or when
  asked to create or refine a project vision.
user-invocable: true
metadata:
  short-description: "Evidence-mined, stress-tested VISION.md for any repo"
---

# /vision

You are running the **vision** skill. Produce a VISION.md the author can
approve: an acceptance policy for the project's future, grounded in what they
actually build, and sharpened by hypotheticals they answer on an interactive
review board.

VISION.md is the only committed alignment surface. A reviewer who has never
seen the board must be able to accept or resist a change from it alone.

This is not a writing exercise. Follow this file top to bottom.

## Host requirement

You need read access to the target repository and its real history:

- Prefer merged-PR history via a GitHub-class CLI (gh, gh-axi).
- If PRs are not accessible, fall back to git commit history on the default
  branch (git log): titles and messages still reveal what the author builds.
- Only if no real history is readable at all, **stop** and say so. Never
  fabricate the author's values, PR titles, or evidence. A vision built on
  invented evidence is worse than no vision.

The review loop runs on lavish-axi, executed directly through
`npx -y lavish-axi` - no install requirement. Simply try to launch it, and
report a blocker only if the launch itself fails.

## Hard rules

1. **Evidence over vibes.** Every principle in the draft must be traceable to
   concrete evidence: named PRs or commits, files, docs, or reasoning the
   author approved into VISION.md. Generic engineering virtues ("we value
   quality") are banned unless the history demonstrates them specifically.
2. **Check for an existing VISION.md first.** If one exists on the default
   branch, switch to delta mode: treat it as the approved baseline, propose
   line-level candidate changes from evidence newer than it, and never write a
   competing document.
3. **The author owns the vision.** You draft, stress-test, and fold in their
   verdicts; you never approve, never soften a hypothetical to please, and
   never fold in a principle they did not state or demonstrate.
4. **A vision is an acceptance policy.** Write testable accept/resist criteria
   in declarative present tense, with explicit non-goals, so a future reader,
   human or agent, can apply them to a concrete change from VISION.md alone.
5. **No softball hypotheticals.** Each one must sit on a genuine fault line
   where yes and no are both defensible, with both sides steelmanned. If you
   can predict the author's answer, replace the hypothetical.
6. **The review loop runs on lavish-axi, from the shipped template.** Draft
   and hypotheticals are presented as one board built from
   `assets/review-template.html` + `assets/review.css`, used as-is: black ink
   on white paper set like literature, full draft always fully visible, one
   hypothetical at a time in a card stack. Fill the template's slots; never
   restyle or restructure it, and never substitute another review surface.
7. **Iterate in batches, trace every edit.** Each author verdict maps to a
   named edit in a changelog; the author must be able to see exactly how their
   answer changed the text.
8. **Formatting.** One sentence per line. Plain hyphens, never em dashes. No
   roadmap, no feature list, no marketing voice.
9. **VISION.md is the single alignment surface.** Fold the author's reasoning
   into the prose wherever it matters, in whatever form reads best. Never copy
   hypotheticals or board transcripts into VISION.md. Never write, keep, or
   point to an answers file in the target repo. Board transcripts may live in
   the tool's scratch area and must never be committed.

## Pipeline

### Step 0 - Parse target and author

- Target repo: current working directory by default, or an explicit
  owner/repo.
- Author: the person whose vision this is; default to the repo owner. Their
  merged work is the evidence base.
- Ask one short question if the target or author is genuinely ambiguous.

### Step 1 - Learn the pattern

A VISION.md has a stable anatomy; hold the draft to it:

- Identity opener: "X exists so that ...", who it serves, and "It owns exactly
  one thing: ...".
- 3-6 principle sections with short declarative headings, each a set of
  testable present-tense commitments and refusals.
- Explicit non-goals, named concretely ("it is not a CI system, not a ...").
- A closing pair of tests: "A change aligns when ..." and "A change should be
  resisted when ...", concrete enough to apply to a real PR.
- Voice: declarative, present tense, zero marketing; length a page or two
  (40-70 lines). Author reasoning belongs in the prose wherever it matters,
  in whatever form reads best; never as a ledger of questions asked.

If the author names exemplar visions, read them; note shape, voice, length.

### Step 2 - Existing-vision check

- If the default branch has a VISION.md: delta mode (hard rule 2). Diff its
  age against the history and propose only evidence-backed candidate
  additions or edits, each independently acceptable.
- If not: from-scratch mode.
- If VISION-ANSWERS.md or any companion answers file exists, run Migration
  before drafting: fold any missing reasoning into VISION.md, delete the
  answers file, and remove pointers to it.

### Step 3 - Mine the evidence

- Repo analysis: README identity claims, architecture, stated non-goals,
  refusal paths, test discipline.
- History mining: list the author's merged PRs, aim for 30-100 titles, and
  read 8-15 full bodies spread across the range (for example
  `gh pr list --author <owner> --state merged --limit 100`, or the gh-axi
  equivalent). If PRs are inaccessible, walk default-branch commit history
  instead (`git log --author=<owner>`), reading messages for the same signal.
- Extract recurring revealed values: what gets built, what gets refused, what
  class of bug gets fixed at the root, what the author writes in intent
  statements.
- Produce a private evidence sheet: value -> supporting PRs, commits, or
  files. This sheet is the source of truth for every drafted line.

### Step 4 - Draft

- Follow the step 1 anatomy and the output template below.
- Every line must map to the evidence sheet. Length target: 40-70 lines.
- Delta mode instead yields: baseline unchanged + a numbered list of candidate
  line additions/edits, each with its evidence.

### Step 5 - Design the hypotheticals

- 8-12 concrete change proposals per vision, aimed at the draft's fault
  lines. Draw from this taxonomy:
  - tempting-but-off-mission features the author will plausibly be asked for;
  - principle collisions (simplicity vs capability, safety vs speed,
    generality vs focus, cost vs quality);
  - slippery slopes, where one reasonable step normalizes the next;
  - scope expansions (new users, new content types, new hosts, teams);
  - identity questions the draft leaves open.
- Format per hypothetical: id, title, the concrete proposal (2-4 sentences),
  the principle it tests (quote the draft), and why the answer is non-obvious
  (steelman both sides).
- Quality gate: delete and replace any hypothetical whose answer you can
  predict.

### Step 6 - Review loop (lavish-axi, from the shipped template)

- Copy `assets/review-template.html` and `assets/review.css` into the tool's
  scratch area (not the target repo), then fill only the template's marked
  slots: project name, run note, the full DRAFT markdown, and the CARDS array
  (id, title, proposal, tested principle, both-sides steelman per card).
- Change nothing else: the template already carries the house structure -
  full draft on the left, one card at a time on the right, the steelman in
  full view, one queued verdict per card - so no boilerplate is rewritten and
  no run is restyled.
- Launch with `npx -y lavish-axi <board.html>`, report the UR
```

## File: README.md
upstream: https://github.com/kunchenguid/vision/blob/main/README.md

````text
<h1 align="center">/vision</h1>

<p align="center">
  <a href="https://agentskills.io"
    ><img
      alt="Agent Skills"
      src="https://img.shields.io/badge/Agent%20Skills-package-blue?style=flat-square"
  /></a>
  <a href="LICENSE"
    ><img
      alt="License"
      src="https://img.shields.io/badge/license-MIT-green?style=flat-square"
  /></a>
  <a href="https://x.com/kunchenguid"
    ><img
      alt="X"
      src="https://img.shields.io/badge/X-@kunchenguid-black?style=flat-square"
  /></a>
  <a href="https://discord.gg/Wsy2NpnZDu"
    ><img
      alt="Discord"
      src="https://img.shields.io/discord/1439901831038763092?style=flat-square&label=discord"
  /></a>
</p>

<h3 align="center">What does your project refuse to become?</h3>

Your repo has values. They are in the two hundred PRs you merged, the features
you quietly declined, the bug you fixed at the root instead of the symptom.
They are just not written down - so every contributor, every coding agent, and
every future you re-litigates them from scratch.

**vision** is an [Agent Skill](https://agentskills.io) that mines what you
actually build, drafts a VISION.md as a testable acceptance policy, then
stress-tests it with hard hypotheticals - tempting-but-off-mission features,
principle collisions, slippery slopes - whose answers only you can give. You
answer them on an interactive review board, and the reasoning behind each
verdict is reflected in the writing, until VISION.md is sufficient on its
own for an accept/resist test.

- **Evidence over vibes** - every principle cites real merged PRs or commits;
  generic engineering virtues are banned. If your history is unreadable, the
  skill refuses rather than inventing your values.
- **Stress-tested, not brainstormed** - 8-12 fault-line hypotheticals per
  vision, both sides steelmanned; if your answer is predictable, the question
  gets replaced.
- **A house-style review surface** - the package ships a stylesheet and a
  board template the agent fills rather than rewrites: black ink on white
  paper set like literature, your full latest draft always visible,
  hypotheticals dealt one at a time from a stack of cards; a verdict flips the
  card and reveals the next.
- **One alignment surface** - VISION.md is what a reviewer uses; board
  transcripts stay ephemeral and are never committed next to the vision.

For what the result looks like, see
[firstmate's VISION.md](https://github.com/kunchenguid/firstmate/blob/main/VISION.md) -
produced by exactly this process.

## Quick Start

```sh
# install (global recommended)
$ npx skills add kunchenguid/vision -g

# in your agent, inside the target repo
/vision
# or: /vision owner/repo
```

## What it needs

- Read access to the repo and its history: merged PRs via `gh` or `gh-axi`
  when accessible, falling back to default-branch git commit history
  otherwise.
- The review board runs on [lavish-axi](https://www.npmjs.com/package/lavish-axi),
  launched directly through `npx -y lavish-axi` - nothing to install; a
  blocker is reported only if the launch itself fails.
- Any harness: no host-specific agent tools.

## How It Works

```
repo + author
      │
      ▼
┌───────────────────┐
│ learn the pattern │  exemplar visions · anatomy · voice
└─────────┬─────────┘
          ▼
┌───────────────────┐
│ existing vision?  │  yes → delta mode; migrate any answers file
└─────────┬─────────┘
          ▼
┌───────────────────┐
│ mine evidence     │  repo analysis · merged PRs or commit history · evidence sheet
└─────────┬─────────┘
          ▼
┌───────────────────┐
│ draft             │  identity · principles · non-goals · aligns/resisted tests
└─────────┬─────────┘
          ▼
┌───────────────────┐
│ hypotheticals     │  8-12 fault-line proposals, both sides steelmanned
└─────────┬─────────┘
          ▼
┌───────────────────┐
│ review board      │  card-stack verdicts → fold reasoning into draft → approval
└─────────┬─────────┘
          ▼
  VISION.md
```

## Usage

| Invoke | Example |
| ------ | ------- |
| Slash | `/vision` (in repo) or `/vision owner/repo` |
| Natural language | "help me write a VISION.md for this project" |

The agent should auto-invoke when asked to write, refine, or stress-test a
project vision or contribution-acceptance criteria.

## Package layout

```
skills/vision/
  SKILL.md                   # the complete agent contract, self-contained
  assets/
    review.css               # the house-style review surface, used as-is
    review-template.html     # the board template; agents fill slots, never restyle
```

Ships as an [`npx skills`](https://github.com/vercel-labs/skills) package.

## Development

```sh
# edit the skill
$EDITOR skills/vision/SKILL.md

# smoke-test discovery locally
npx skills add ./ -l

# install from this checkout
npx skills add ./ -g -y
```
````
