Skip to content
Back to search

aispy

MarketplaceWorks with Claude CodeGitHubIncomplete

Safety scan

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

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/stevensmith-design--aispy/badge.svg)](/listings/stevensmith-design--aispy)

HTML

<a href="/listings/stevensmith-design--aispy"><img src="/api/listings/stevensmith-design--aispy/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

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

**From a clone or download** (nothing to install into Claude Code):

1. **Get AIspy:** `git clone https://github.com/stevensmith-design/aispy.git`, or download the ZIP from GitHub and rename the unzipped folder (`aispy-main`) to `aispy`. Open Claude Code in the folder that contains `aispy` (your project, for example), or connect the `aispy` folder to a session alongside your project. 2. **Ask Claude:** "Set up AIspy for my first review". It installs the screenshot helper and tests a scripted browser; approve the install and browser commands when it asks. 3. **Ask for a review:** "Use the AIspy kit in ./aispy to review https://example.com. Start separate agents for the lenses and checks." With the folder connected separately, say "the AIspy kit in the connected aispy folder".

**Or install it as a plugin:**

1. **Get AIspy:** `/plugin marketplace add stevensmith-design/aispy`, then `/plugin install aispy@aispy`. From a local copy: `/plugin marketplace add ./aispy`, then the same install command. 2. **Ask Claude:** "Set up AIspy for my first review". It offers to install the screenshot helper and test the browser; say yes and approve the commands. 3. **Ask for a review:** "Use the AIspy kit to review https://example.com. Start separate agents for the lenses and checks."

Each review starts with a setup check (agents, the browser reaching your site, screenshots, the kit) and stops if anything fails. The manual commands are under [Install](#install).

クイックスタート(日本語)

**クローンまたはダウンロードして使う**(Claude Code へのインストールは不要)

1. **AIspy を入手する:** `git clone https://github.com/stevensmith-design/aispy.git` を実行するか、 GitHub から ZIP をダウンロードし、展開したフォルダ(`aispy-main`)の名前を `aispy` に変更します。 `aispy` が入っているフォルダ(作業中のプロジェクトなど)で Claude Code を開くか、`aispy` フォルダをプロジェクトと一緒にセッションに接続します。 2. **Claude に依頼する:**「AIspy の初回レビューの準備をして」。スクリーンショット用のツールを インストールし、ブラウザの自動操作をテストします。インストールやブラウザのコマンドの許可を 求められたら承認してください。 3. **レビューを依頼する:**「./aispy の AIspy キットで https://example.com をレビューして。 レビュー観点とチェックは別々のエージェントで実行して。」フォルダを別に接続している場合は 「接続した aispy フォルダの AIspy キットで」と伝えます。

**プラグインとしてインストールして使う**

1. **AIspy を入手する:** `/plugin marketplace add stevensmith-design/aispy` を実行したあと、 `/plugin install aispy@aispy` を実行します。ローカルのコピーから入れる場合は `/plugin marketplace add ./aispy` のあと、同じインストールコマンドを実行します。 2. **Claude に依頼する:**「AIspy の初回レビューの準備をして」。スクリーンショット用のツールの インストールとブラウザのテストを提案してくるので、了承してコマンドを承認してください。 3. **レビューを依頼する:**「AIspy キットで https://example.com をレビューして。レビュー観点と チェックは別々のエージェントで実行して。」

レビューは毎回、セットアップチェック(エージェント、サイトへのブラウザ接続、スクリーンショット、 キット)から始まり、どれかが失敗するとそこで止まります。手動で実行するコマンドは [Install](#install) にあります。

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.

.claude-plugin/marketplace.json · Manifest · 13 lines
  1. {
  2. "name": "aispy",
  3. "owner": {
  4. "name": "Steven Smith"
  5. },
  6. "plugins": [
  7. {
  8. "name": "aispy",
  9. "source": "./",
  10. "description": "UX/UI/IA review of a live website or app, with an optional market-localisation layer, styled in the product's own design system."
  11. }
  12. ]
  13. }
README.md · README · 276 lines
  1. # AIspy
  2. ![The AIspy team: a retro computer with a magnifying glass, three magnifying-glass review agents and five numbered map pins](.github/assets/hero.png)
  3. **A full UX, UI and IA review from your AI crew.**
  4. Made by Steven Smith. More on AIspy and my other work: [stevensmith.dev/aispy](https://stevensmith.dev/aispy?utm_source=github&utm_campaign=aispy)
  5. | Review report | IA analysis | Mock |
  6. |---|---|---|
  7. | ![The example review report's cover: headline finding, scope and reviewer](docs/images/example-report.png) | ![The example IA analysis's cover: headline and task-path results](docs/images/example-ia.png) | ![The example mock: current and proposed product page side by side, with numbered markers and notes](docs/images/example-mock.png) |
  8. <sub>Real output from a full AIspy run on Brolga, a fictional running-shoe brand selling in Japan. The standard every run is held to is [`examples/mareo/`](examples/mareo/), the reference review recreated on a fictional store. More under [Examples](#examples).</sub>
  9. For product managers, founders, developers and marketers without a senior designer to hand, and for designers and agent-led teams who want a full review to start from.
  10. AIspy is a skill pack for Claude Code that runs a professional UX/UI/IA review with an optional market-localisation layer. Give it a product; it captures the pages, extracts the design system, researches the market and benchmarks, runs three independent review lenses, and
  11. delivers:
  12. - a **review report**: findings grouped by cause, each with annotated evidence and a site that does it well;
  13. - an **IA analysis**: navigation, page layout by type, heading hierarchy, task paths, label audit and a proposed structure;
  14. - a **current-vs-proposed mock** of the key screen, built in the product's own design system;
  15. - an **index page** that ties the three together.
  16. All four are styled in the reviewed product's own design system. AIspy replicates a reference
  17. review made by a senior designer, and was tested against it (November 2026): its research and
  18. findings at least match the reference, and its documents follow the same form.
  19. It supports a reviewer; it doesn't replace one. It stops for your review after the report,
  20. again after the mock, and before packaging.
  21. ## Quick start
  22. **From a clone or download** (nothing to install into Claude Code):
  23. 1. **Get AIspy:** `git clone https://github.com/stevensmith-design/aispy.git`, or download the ZIP
  24. from GitHub and rename the unzipped folder (`aispy-main`) to `aispy`. Open Claude Code in the
  25. folder that contains `aispy` (your project, for example), or connect the `aispy` folder to a
  26. session alongside your project.
  27. 2. **Ask Claude:** "Set up AIspy for my first review". It installs the screenshot helper and tests
  28. a scripted browser; approve the install and browser commands when it asks.
  29. 3. **Ask for a review:** "Use the AIspy kit in ./aispy to review https://example.com. Start
  30. separate agents for the lenses and checks." With the folder connected separately, say "the
  31. AIspy kit in the connected aispy folder".
  32. **Or install it as a plugin:**
  33. 1. **Get AIspy:** `/plugin marketplace add stevensmith-design/aispy`, then
  34. `/plugin install aispy@aispy`. From a local copy: `/plugin marketplace add ./aispy`, then the
  35. same install command.
  36. 2. **Ask Claude:** "Set up AIspy for my first review". It offers to install the screenshot helper
  37. and test the browser; say yes and approve the commands.
  38. 3. **Ask for a review:** "Use the AIspy kit to review https://example.com. Start separate agents
  39. for the lenses and checks."
  40. Each review starts with a setup check (agents, the browser reaching your site, screenshots, the
  41. kit) and stops if anything fails. The manual commands are under [Install](#install).
  42. ### クイックスタート(日本語)
  43. **クローンまたはダウンロードして使う**(Claude Code へのインストールは不要)
  44. 1. **AIspy を入手する:** `git clone https://github.com/stevensmith-design/aispy.git` を実行するか、
  45. GitHub から ZIP をダウンロードし、展開したフォルダ(`aispy-main`)の名前を `aispy` に変更します。
  46. `aispy` が入っているフォルダ(作業中のプロジェクトなど)で Claude Code を開くか、`aispy`
  47. フォルダをプロジェクトと一緒にセッションに接続します。
  48. 2. **Claude に依頼する:**「AIspy の初回レビューの準備をして」。スクリーンショット用のツールを
  49. インストールし、ブラウザの自動操作をテストします。インストールやブラウザのコマンドの許可を
  50. 求められたら承認してください。
  51. 3. **レビューを依頼する:**「./aispy の AIspy キットで https://example.com をレビューして。
  52. レビュー観点とチェックは別々のエージェントで実行して。」フォルダを別に接続している場合は
  53. 「接続した aispy フォルダの AIspy キットで」と伝えます。
  54. **プラグインとしてインストールして使う**
  55. 1. **AIspy を入手する:** `/plugin marketplace add stevensmith-design/aispy` を実行したあと、
  56. `/plugin install aispy@aispy` を実行します。ローカルのコピーから入れる場合は
  57. `/plugin marketplace add ./aispy` のあと、同じインストールコマンドを実行します。
  58. 2. **Claude に依頼する:**「AIspy の初回レビューの準備をして」。スクリーンショット用のツールの
  59. インストールとブラウザのテストを提案してくるので、了承してコマンドを承認してください。
  60. 3. **レビューを依頼する:**「AIspy キットで https://example.com をレビューして。レビュー観点と
  61. チェックは別々のエージェントで実行して。」
  62. レビューは毎回、セットアップチェック(エージェント、サイトへのブラウザ接続、スクリーンショット、
  63. キット)から始まり、どれかが失敗するとそこで止まります。手動で実行するコマンドは
  64. [Install](#install) にあります。
  65. ## Examples
  66. Two example packages. Each document is one self-contained HTML file; open `index.html` in a
  67. browser to start.
  68. | | [`examples/mareo/`](examples/mareo/) | [`examples/brolga/`](examples/brolga/) |
  69. |---|---|---|
  70. | What it is | The review AIspy was built and tested against, recreated on a fictional Danish sofa brand selling in Japan. It isn't a kit run: it shows what the kit aims at. | A full AIspy run on a fictional Australian running-shoe brand selling in Japan, reviewed once by a person. |
  71. | Scope | One product page at 390 px, with the header, menu drawer and search. Sections that need other pages are kept and labelled "out of scope in this example". | The top page, all shoes, three product pages and the size guide; phone first, desktop where a finding differs. |
  72. | What it shows | The standard the skill matches by default: document form, density of argument, how evidence is marked, and the mock. Also the store's product page before and after. | What a complete multi-page package looks like, from intake to the finished documents. |
  73. | Documents | Index, localisation review (13 findings), IA analysis, mock, mock spec | Index, review report (18 findings), IA analysis, mock, mock spec |
  74. Both pass the pack's checks (`scripts/checks/`). The examples' stores and products are made up;
  75. real Japanese sites appear only as benchmarks.
  76. ## Install
  77. Requires [Claude Code](https://code.claude.com), in the terminal or the desktop app's Code tab,
  78. Node 22.23.5 or newer, and Python 3 (for the design-system validator, `validate-tokens.py`).
  79. AIspy installs into Claude Code as a skill pack. Either:
  80. **With Claude Code's `/plugin` command:**
  81. ```
  82. /plugin marketplace add stevensmith-design/aispy
  83. /plugin install aispy@aispy
  84. ```
  85. **Or from a clone**, starting Claude Code with it loaded:
  86. ```
  87. git clone https://github.com/stevensmith-design/aispy.git
  88. claude --plugin-dir ./aispy
  89. ```
  90. To keep it with a project, put the folder inside it and start Claude Code with `--plugin-dir` and
  91. that path. Keep the folder whole: the skills find their scripts two folders up.
  92. Either way, eight skills become available: `product-review` and `review-scoping`, plus the six
  93. design-kit skills they call (`ui-design-system`, `ui-design-review`, `ia-review`, `design-refine`,
  94. `ui-design-principles`, `distinctiveness-review`). The design kit is bundled. To confirm AIspy is
  95. loaded, run `/plugin` (or `claude --plugin-dir ./aispy plugin details aispy`) and look for the
  96. eight skills; tested, the bare names resolve to AIspy's copies even when other copies of the kit
  97. are installed.
  98. **Before the first review**, set up what the setup check needs, or it stops:
  99. 1. **Screenshots:** install the capture helper (Playwright), which makes the evidence crops. Run
  100. it in the pack's `scripts/capture/` folder:
  101. - **From a clone**, in the folder where you ran `git clone`:
  102. ```
  103. cd aispy/scripts/capture && npm install && npx playwright install chromium
  104. ```
  105. - **With `/plugin` from a local copy** (`/plugin marketplace add ./aispy`): as from a clone. The
  106. plugin runs from that folder.
  107. - **With `/plugin` from GitHub**, in any folder. Claude Code keeps the plugin in a folder named
  108. after the installed version; this picks the newest installed version. Run it again after each
  109. update:
  110. ```
  111. cd "$(ls -d ~/.claude/plugins/cache/aispy/aispy/*/ | sort -V | tail -1)scripts/capture" && npm install && npx playwright install chromium
  112. ```
  113. 2. **A browser the session can drive**, such as Claude in Chrome or Playwright, with its commands
  114. allowed in your permissions so it can open the site.
  115. 3. **Agents:** say "start separate agents for the lenses and checks" in your request.
  116. ## How to start
  117. The only thing it needs is the product: a URL, a store link, or screens.
  118. ```
  119. Review https://example.com and propose improvements. Start separate agents for the lenses and checks.
  120. ```
  121. ```
  122. Here's the brief: <paste>. My direction: focus on mobile checkout, and the store is
  123. launching in Japan, so include a localisation review. Report in English.
  124. ```
  125. ```
  126. Extract the brand and design system from https://example.com first; we'll review afterwards.
  127. ```
  128. It takes a quick look, then asks one batch of questions with a proposed default for each, so "go"
  129. is enough. Before reviewing, it runs a setup check (agents, browser, screenshots, kit) and stops if
  130. anything fails.
  131. ### 始め方(日本語)
  132. 必要なのはプロダクトだけです。URL、ストアのリンク、または画面のどれかを渡してください。
  133. ```
  134. https://example.com をレビューして、改善案を出して。レビュー観点とチェックは別々のエージェントで実行して。
  135. ```
  136. ```
  137. ブリーフはこちら:<貼り付け>。方針:モバイルの購入手続きを重点的に見てほしい。日本市場でローンチ
  138. するので、ローカライズのレビューも含めて。レポートは日本語で。
  139. ```
  140. ```
  141. まず https://example.com からブランドとデザインシステムを抽出して。レビューはそのあとで。
  142. ```
  143. まずサイトをざっと確認し、質問をまとめて一度に送ります。各質問には既定の案が付いているので、
  144. 「進めて」と返すだけで構いません。レビューの前にセットアップチェック(エージェント、ブラウザ、
  145. スクリーンショット、キット)を行い、どれかが失敗するとそこで止まります。
  146. ## How to use
  147. [docs/how-to-use.md](docs/how-to-use.md) covers it in full. In short:
  148. - **Live site:** the URL is enough. Better, also save each page in scope as HTML ("Save page as",
  149. complete) and connect the folder.
  150. - **Staging or local site:** give the served build or a reachable URL, never the source project
  151. (the source holds the design intent and biases the review).
  152. - **Logged-in areas:** you sign in yourself in the browser; the pack never handles credentials.
  153. - **Native app:** a simulator or emulator the session can see and operate, or exported screens per
  154. flow with the sweep done by hand. Tap areas are less exact than on the web.
  155. - **Say in the request:** review type (general, or plus localisation), priority device, pages or
  156. flows, language, and "start separate agents for the lenses and checks".
  157. ## What to expect
  158. Three stops, one review round from you at each:
  159. 1. **Review report and IA analysis.** The deliverables step takes about 40 minutes from a finished review.
  160. 2. **Mock spec, then the mock.** About 25 minutes, including the spec and checks.
  161. 3. **Packaging:** the index page and the final package.
  162. Times are from the test runs. Everything is written to `review/<product>-<date>/` in the folder you
  163. connected, with a run log.
  164. **Accessibility:** it checks contrast, text size, tap targets, alt text, screen-reader strings,
  165. headings and motion. It is not a full WCAG audit, and it doesn't do a screen-reader or
  166. keyboard-only walk unless you ask.
  167. ## Contents
  168. ```
  169. .claude-plugin/ plugin and marketplace manifests
  170. skills/
  171. product-review/ SKILL.md (the workflow), references/ (checklist, review questions,
  172. deliverable outlines), templates/ (the four documents; see templates/README.md)
  173. review-scoping/ optional: inventory a big site and pick pages by type
  174. design-kit/ the six design-kit skills the pack calls (see design-kit/PROVENANCE.md)
  175. scripts/ optional helpers, not required steps
  176. capture/ capture.mjs, extract-in-page.js, sweep-in-page.js, annotate.mjs (evidence crops)
  177. (tests: node --test scripts/capture/test/)
  178. inventory/ inventory.mjs (sitemap, page types, broken URLs)
  179. build/ theme-from-tokens.mjs, assemble.mjs, layout-bars.mjs
  180. checks/ check-deliverable.mjs, check-report.mjs, check-mock.mjs, forbid.mjs
  181. (tests: node --test scripts/checks/test/)
  182. examples/mareo/ the reference review recreated on a fictional store (default standard)
  183. examples/brolga/ a complete multi-page example run
  184. docs/how-to-use.md inputs by product type, and what to expect
  185. ```
  186. ## How AIspy is designed
  187. Consistent results come from defining the deliverables, not from leaving them to the agent.
  188. 1. **Goals:** what each deliverable is for and who reads it.
  189. 2. **Data required:** what evidence, research, benchmarks and extraction each one needs.
  190. 3. **How it's put together:** the required contents, structure and layout of the report, IA
  191. analysis, mock and index, as rules, templates and examples. This is the baseline; an agent may
  192. add something new with a stated reason, but never starts from a blank page.
  193. 4. **Methods:** how to capture, extract, research, benchmark and review. This is where the agent's
  194. judgement works: what it finds, how serious it is, and what to propose.
  195. ## How it improves
  196. Through use, measured against the reference review. Treat any report that something is missing or
  197. worse as a gap in replicating the reference: check what the reference does, then repair the
  198. existing instruction or reference file. When a real run misses something, add one line to
  199. `skills/product-review/references/checklist.md`. A new requirement or step goes in only for a
  200. demonstrated gap, or when a run shows it beats the reference on quality or cost.
  201. ## Status
  202. 0.8.7. See [CHANGELOG.md](CHANGELOG.md) for the history and the
  203. [open issues](https://github.com/stevensmith-design/aispy/issues) for what's next.
  204. ## Licence
  205. Code, skills and templates: [MIT](LICENSE). The bundled design kit keeps its own MIT licence and
  206. notice (`skills/design-kit/LICENSE`, `NOTICE`). The example packages are
  207. CC BY 4.0: [`examples/mareo/`](examples/mareo/LICENSE.md) and
  208. [`examples/brolga/`](examples/brolga/LICENSE.md). The Barlow Condensed font embedded in
  209. Brolga's documents is under the SIL Open Font License 1.1, not CC BY (see its `LICENSE.md`).
  210. The AIspy name, logo and character artwork (including the image at the top of this page) are
  211. not covered by these licences.

Ratings and comments

Sign in to rate this skill.

Sign in

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