一键在 Manus 中运行任何 Skill

scan

星标4

分支0

更新时间2026年4月28日 17:23

Fingerprint a codebase's design DNA and write dragoon.json. Use when the user wants to set up dragoon in a project, or asks to "scan", "fingerprint", or "analyze" the design system. Always run this first before /critique, /slop, or /review on a project that hasn't been scanned yet. Outputs detected stack, palette, type scale, spacing grid, motion curves, and accessibility metrics. Run as `node ~/.claude/skills/dragoon/skills/scan/scripts/scan.js [root]`.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

Dragoon0x

Dragoon0x/dragoon-skills

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

/scan

Generates dragoon.json, the canonical fingerprint of a codebase's design DNA. Every other dragoon skill reads or writes against this file.

When to use

Run /scan when:

The user is setting up dragoon in a new project for the first time
The user asks to "scan", "fingerprint", "audit the design system", "analyze the codebase"
Another dragoon command (/critique, /slop, /review) needs a manifest and one doesn't exist
The codebase has changed significantly and the existing manifest is stale

What it produces

A dragoon.json file at the project root with:

stack: framework (react/next/vue/svelte/etc), styling layer (tailwind/css/styled-components/etc), language, package manager
tokens.color: top distinct colors with usage counts and inferred roles
tokens.spacing: distinct spacing values, inferred grid (4/6/8/12/16px), confidence score
tokens.type: font families, font sizes, inferred scale ratio (golden, perfect-fourth, etc), confidence
tokens.radius / shadow / motion / breakpoints: top values with counts
metrics: file counts, component count estimate, accessibility signals (alt rate, button label rate, semantic tag use)
rules: derived defaults (grid size, type ratio, max variants per token, allowed colors). Edit by hand if needed.

Run it

node ~/.claude/skills/dragoon/skills/scan/scripts/scan.js [root]

Flags:

--out <path> write to a custom path
--json print manifest to stdout
--dry-run compute but don't write
--quiet no terminal output beyond errors
--help full usage

Notes

Pure regex scanning. No AST parser dependency. No network calls.
Skips node_modules, dist, build, .git automatically (gitignore-aware).
Caps at 5,000 files per scan and 2MB per file. Larger codebases get a representative sample.
Re-run /scan after major design changes to keep rules current.

同仓库更多 Skills

同仓库

useforgekit

Dragoon0x/dragoon-skills

Generate optimal Claude Code configuration for any project. Creates CLAUDE.md, settings.json, skills, hooks, agents, and commands tailored to your stack. Run /forge to start.

2026-05-014

accessibility

Dragoon0x/dragoon-skills

File-level accessibility audit with concrete line locations for every finding. Eight rules: img-missing-alt, button-without-label, link-without-text, input-without-label, positive-tabindex, click-handler-on-non-interactive, autofocus, low-contrast-token-pair. Use when the user wants to audit a11y, find accessibility regressions, or gate a PR on a11y. Run as `node ~/.claude/skills/dragoon/skills/accessibility/scripts/accessibility.js [path]`.

2026-04-284

autoplan

Dragoon0x/dragoon-skills

Run /brief, /plan-eng, and /plan-design in one shot to bootstrap a complete sprint plan. All three documents land in .dragoon/plans/ pre-filled with codebase facts. Use when the user wants to spin up a full plan quickly. Defaults to dry-run; pass --apply to write all three files. Run as `node ~/.claude/skills/dragoon/skills/autoplan/scripts/autoplan.js "<idea>"`.

2026-04-284

benchmark

Dragoon0x/dragoon-skills

Snapshot codebase metrics (file count, total lines, /critique scores) for trend tracking. Subcommands capture/list/compare/show. Snapshots stored as JSON in .dragoon/benchmarks/. Use to track design quality and codebase growth over time. Run as `node ~/.claude/skills/dragoon/skills/benchmark/scripts/benchmark.js <subcommand>`.

2026-04-284

brief

Dragoon0x/dragoon-skills

Generate a structured product brief markdown from a one-line idea, pre-filled with codebase facts (stack, type system, palette, components count) from dragoon.json. Use when the user is starting a new feature, project, or initiative and wants to think through it before coding. Output goes to .dragoon/plans/brief-{slug}-{date}.md. Defaults to dry-run preview; pass --apply to write. Run as `node ~/.claude/skills/dragoon/skills/brief/scripts/brief.js "<idea>"`.

2026-04-284

canary

Dragoon0x/dragoon-skills

Generate a curl-based canary watcher script for a deployed URL. Validates URL is http/https, status code is 100-599, interval is 5-86400 seconds. The generated script supports one-shot (default) and --watch (continuous loop) modes. Wire into cron or a CI scheduled job. Run as `node ~/.claude/skills/dragoon/skills/canary/scripts/canary.js <url>`.

2026-04-284

name	scan
description	Fingerprint a codebase's design DNA and write dragoon.json. Use when the user wants to set up dragoon in a project, or asks to "scan", "fingerprint", or "analyze" the design system. Always run this first before /critique, /slop, or /review on a project that hasn't been scanned yet. Outputs detected stack, palette, type scale, spacing grid, motion curves, and accessibility metrics. Run as `node ~/.claude/skills/dragoon/skills/scan/scripts/scan.js [root]`.
version	1.0.0

/scan

Generates dragoon.json, the canonical fingerprint of a codebase's design DNA. Every other dragoon skill reads or writes against this file.

When to use

Run /scan when:

The user is setting up dragoon in a new project for the first time
The user asks to "scan", "fingerprint", "audit the design system", "analyze the codebase"
Another dragoon command (/critique, /slop, /review) needs a manifest and one doesn't exist
The codebase has changed significantly and the existing manifest is stale

What it produces

A dragoon.json file at the project root with:

stack: framework (react/next/vue/svelte/etc), styling layer (tailwind/css/styled-components/etc), language, package manager
tokens.color: top distinct colors with usage counts and inferred roles
tokens.spacing: distinct spacing values, inferred grid (4/6/8/12/16px), confidence score
tokens.type: font families, font sizes, inferred scale ratio (golden, perfect-fourth, etc), confidence
tokens.radius / shadow / motion / breakpoints: top values with counts
metrics: file counts, component count estimate, accessibility signals (alt rate, button label rate, semantic tag use)
rules: derived defaults (grid size, type ratio, max variants per token, allowed colors). Edit by hand if needed.

Run it

node ~/.claude/skills/dragoon/skills/scan/scripts/scan.js [root]

Flags:

--out <path> write to a custom path
--json print manifest to stdout
--dry-run compute but don't write
--quiet no terminal output beyond errors
--help full usage

Notes

Pure regex scanning. No AST parser dependency. No network calls.
Skips node_modules, dist, build, .git automatically (gitignore-aware).
Caps at 5,000 files per scan and 2MB per file. Larger codebases get a representative sample.
Re-run /scan after major design changes to keep rules current.