Skip to content
Back to search

vision

Agent skill that mines your repo's history to draft a VISION.md, stress-tests it with hard hypotheticals, and iterates with you on an interactive review board.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/kunchenguid/vision with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/kunchenguid/vision'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/kunchenguid--vision/badge.svg)](/listings/kunchenguid--vision)

HTML

<a href="/listings/kunchenguid--vision"><img src="/api/listings/kunchenguid--vision/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

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

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

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 154 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <h1 align="center">/vision</h1>
  2. <p align="center">
  3. <a href="https://agentskills.io"
  4. ><img
  5. alt="Agent Skills"
  6. src="https://img.shields.io/badge/Agent%20Skills-package-blue?style=flat-square"
  7. /></a>
  8. <a href="LICENSE"
  9. ><img
  10. alt="License"
  11. src="https://img.shields.io/badge/license-MIT-green?style=flat-square"
  12. /></a>
  13. <a href="https://x.com/kunchenguid"
  14. ><img
  15. alt="X"
  16. src="https://img.shields.io/badge/X-@kunchenguid-black?style=flat-square"
  17. /></a>
  18. <a href="https://discord.gg/Wsy2NpnZDu"
  19. ><img
  20. alt="Discord"
  21. src="https://img.shields.io/discord/1439901831038763092?style=flat-square&label=discord"
  22. /></a>
  23. </p>
  24. <h3 align="center">What does your project refuse to become?</h3>
  25. Your repo has values. They are in the two hundred PRs you merged, the features
  26. you quietly declined, the bug you fixed at the root instead of the symptom.
  27. They are just not written down - so every contributor, every coding agent, and
  28. every future you re-litigates them from scratch.
  29. **vision** is an [Agent Skill](https://agentskills.io) that mines what you
  30. actually build, drafts your project's vision as a testable acceptance policy, then
  31. stress-tests it with hard hypotheticals - tempting-but-off-mission features,
  32. principle collisions, slippery slopes - whose answers only you can give. You
  33. answer them on an interactive review board, and the reasoning behind each
  34. verdict is reflected in the writing, until the vision is sufficient on its
  35. own for an accept/resist test.
  36. The vision goes in VISION.md when your repo already has one. Otherwise it goes
  37. in a Vision section of STRATEGY.md, created if missing. The skill writes only
  38. that section and leaves every other section alone; where another section
  39. repeats the vision, it proposes a pointer or deletion and applies it only on
  40. your yes.
  41. - **Evidence over vibes** - every principle cites real merged PRs or commits;
  42. generic engineering virtues are banned. If your history is unreadable, the
  43. skill refuses rather than inventing your values.
  44. - **Stress-tested, not brainstormed** - 8-12 fault-line hypotheticals per
  45. vision, both sides steelmanned; if your answer is predictable, the question
  46. gets replaced.
  47. - **A house-style review surface** - the package ships a stylesheet and a
  48. board template the agent fills rather than rewrites: black ink on white
  49. paper set like literature, your full latest draft always visible,
  50. hypotheticals dealt one at a time from a stack of cards; a verdict flips the
  51. card and reveals the next.
  52. - **One alignment surface** - the vision (VISION.md, or the Vision section of
  53. STRATEGY.md) is what a reviewer uses; board
  54. transcripts stay ephemeral and are never committed next to the vision.
  55. For what the result looks like, see
  56. [firstmate's VISION.md](https://github.com/kunchenguid/firstmate/blob/main/VISION.md) -
  57. produced by exactly this process.
  58. ## Quick Start
  59. ```sh
  60. # install (global recommended)
  61. $ npx skills add kunchenguid/vision -g
  62. # in your agent, inside the target repo
  63. /vision
  64. # or: /vision owner/repo
  65. ```
  66. ## What it needs
  67. - Read access to the repo and its history: merged PRs via `gh` or `gh-axi`
  68. when accessible, falling back to default-branch git commit history
  69. otherwise.
  70. - The review board runs on [lavish-axi](https://www.npmjs.com/package/lavish-axi),
  71. launched directly through `npx -y lavish-axi` - nothing to install; a
  72. blocker is reported only if the launch itself fails.
  73. - Any harness: no host-specific agent tools.
  74. ## How It Works
  75. ```
  76. repo + author
  77. │
  78. ▼
  79. ┌───────────────────┐
  80. │ learn the pattern │ exemplar visions · anatomy · voice
  81. └─────────┬─────────┘
  82. ▼
  83. ┌───────────────────┐
  84. │ existing vision? │ yes → delta mode; migrate any answers file
  85. │ │ target: VISION.md if present, else STRATEGY.md's Vision section
  86. └─────────┬─────────┘
  87. ▼
  88. ┌───────────────────┐
  89. │ mine evidence │ repo analysis · merged PRs or commit history · evidence sheet
  90. └─────────┬─────────┘
  91. ▼
  92. ┌───────────────────┐
  93. │ draft │ identity · principles · non-goals · aligns/resisted tests
  94. └─────────┬─────────┘
  95. ▼
  96. ┌───────────────────┐
  97. │ hypotheticals │ 8-12 fault-line proposals, both sides steelmanned
  98. └─────────┬─────────┘
  99. ▼
  100. ┌───────────────────┐
  101. │ review board │ card-stack verdicts → fold reasoning into draft → approval
  102. └─────────┬─────────┘
  103. ▼
  104. VISION.md, or the Vision section of STRATEGY.md
  105. ```
  106. ## Usage
  107. | Invoke | Example |
  108. | ------ | ------- |
  109. | Slash | `/vision` (in repo) or `/vision owner/repo` |
  110. | Natural language | "help me write a vision for this project" |
  111. The agent should auto-invoke when asked to write, refine, or stress-test a
  112. project vision or contribution-acceptance criteria.
  113. ## Package layout
  114. ```
  115. skills/vision/
  116. SKILL.md # the complete agent contract, self-contained
  117. assets/
  118. review.css # the house-style review surface, used as-is
  119. review-template.html # the board template; agents fill slots, never restyle
  120. ```
  121. Ships as an [`npx skills`](https://github.com/vercel-labs/skills) package.
  122. ## Development
  123. ```sh
  124. # edit the skill
  125. $EDITOR skills/vision/SKILL.md
  126. # smoke-test discovery locally
  127. npx skills add ./ -l
  128. # install from this checkout
  129. npx skills add ./ -g -y
  130. ```

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.