SKILLS & AGENTS/Skill 与 Agent·CLAUDE-SKILL

rune

Rune-kit/rune

Less skills. Deeper connections. A lean, interconnected skill ecosystem for Claude Code.

打开仓库Open repository

怎么装：Install: npx @rune-kit/rune setup

02 / 现在的位置02 / Why now

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

03 OCT 202603 OCT 2026

增长GROWTH

+0.0%+0.0%

88 → 88 stars · 2 个快照88 → 88 stars · 2 snapshots

状态STATUS

持续活跃Active

03 / 它能帮你做什么03 / What it helps you do

它能帮你做成什么What it helps you do

04 / 安装04 / Install

怎么装How to install

NPX

$

README 里给出的安装方式。The installation method given in the README.

NPX

$

README 里给出的安装方式。The installation method given in the README.

两种装法选一个即可 —— 上面那条给命令行用户，下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.

05 / 限制与风险05 / Limits and risk

限制与风险Limits and risk

风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.

限制LIMITS

需检查Needs review

01需要 API KeyREQUIRES API KEY: 是Yes
02需要本地环境NEEDS LOCAL RUNTIME: 是Yes
03需要 DockerNEEDS DOCKER: 未在文档中发现Not found in the docs
04难度DIFFICULTY: 需要本地环境Needs a local runtime

PROVENANCE · 这些结论的依据是什么Where these conclusions come from

来源 URLSource URL: https://github.com/Rune-kit/rune
原始数据哈希Raw data hash: f8921b904f54aa1213a5059c17286dec
解析时间Parsed at: 2026-10-03T23:24:45.046Z
最后一次验证Last verified: 2026-10-04T08:53:33.891Z
增长测量时间Growth measured: 2026-10-03T23:24:59.911Z
发现查询Discovery queries: focus:design:code:ui-ux, focus:motion:code:framer-motion
分类来源Category source: rules
焦点Focus: design · motion (5)

静态扫描STATIC SCAN

01控制浏览器Controls a browserskills/browser-pilot/SKILL.md

Browser automation for testing and verification using MCP Playwright tools. Navigates to URLs, captures accessibility snapshots and screensh

02读取 API KeyReads an API keyskills/browser-pilot/SKILL.md

2. **Restrict JavaScript execution to read-only inspection.** Never execute JS that modifies state, submits forms, or accesses credentials (

03控制浏览器Controls a browserskills/doc-processor/SKILL.md

| PDF | Yes | Yes (via the runtime's document/PDF reader) | jsPDF, Puppeteer (HTML→PDF) | reportlab, weasyprint |

04读取 API KeyReads an API keyskills/mcp-builder/SKILL.md

| Hardcoded API keys in generated code | CRITICAL | Constraint 3: always use env vars + .env.example |

05执行 Shell 命令Runs shell commandsskills/perf/SKILL.md

Finding: `SYNC_IN_ASYNC — [file:line] — [readFileSync|execSync|etc] in async function — blocks event loop`

06执行 Shell 命令Runs shell commandsskills/sentinel-env/SKILL.md

- `Grep` for `subprocess.run(`, `child_process.exec(`, `Deno.Command(` → project invokes external CLI

这里只做静态扫描：读 README、SKILL.md 和依赖清单，不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.

完整解析证据 JSONFull parse evidence JSON

{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "tree: .claude-plugin/"
    },
    {
      "agent": "codex",
      "evidence": "readme: …ntigravity</strong> · <strong>OpenAI Codex</strong> · <strong>OpenCode</…"
    },
    {
      "agent": "cursor",
      "evidence": "readme: …across the fleet: **cursor** `.cursor/rules/*.mdc` → `.cursor/skills/` (C…"
    },
    {
      "agent": "windsurf",
      "evidence": "readme: …ong>Cursor</strong> · <strong>Windsurf</strong> · <strong>Google Ant…"
    },
    {
      "agent": "gemini-cli",
      "evidence": "readme: …opilot CLI</strong> · <strong>Gemini CLI</strong> · <strong>Qoder</str…"
    },
    {
      "agent": "opencode",
      "evidence": "readme: …enAI Codex</strong> · <strong>OpenCode</strong> · <strong>Aider</str…"
    },
    {
      "agent": "copilot",
      "evidence": "readme: …rong>Aider</strong> · <strong>GitHub Copilot CLI</strong> · <strong>Gemini…"
    },
    {
      "agent": "cline",
      "evidence": "skills/council/SKILL.md: …, Codex, Gemini, Antigravity, Cline, Amp, OpenCode, Qwen, Grok, A…"
    }
  ],
  "apiKey": "CP references now go through `XLABS_MCP_TOKEN` — plaintext bearer values are forbidde",
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 0,
      "dev-tools": 2,
      "indie-web": 1,
      "skill-agent": 3,
      "productivity": 3
    },
    "primary": "skill-agent",
    "secondary": "claude-skill"
  },
  "localRuntime": "ep 5.5 Motion Performance** — GPU-property, Framer-Motion-shorthand, and",
  "skillMdTotal": 67,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 0,
    "agent": 0,
    "media": 0,
    "design": 0,
    "browser": 0,
    "devtool": 3,
    "security": 1,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "60 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "skills/ directory with 174 markdown files",
      "weight": 0.75
    },
    {
      "signal": "README describes a Claude / Agent Skill",
      "weight": 0.7
    },
    {
      "signal": "Claude Code plugin manifest",
      "weight": 0.7
    },
    {
      "signal": "description mentions AI",
      "weight": 0.2
    }
  ],
  "scannedSources": [
    "readme",
    "skills/adversary/SKILL.md",
    "skills/asset-creator/SKILL.md",
    "skills/audit/SKILL.md",
    "skills/autopsy/SKILL.md",
    "skills/ba/SKILL.md",
    "skills/brainstorm/SKILL.md",
    "skills/browser-pilot/SKILL.md",
    "skills/completion-gate/SKILL.md",
    "skills/constraint-check/SKILL.md",
    "skills/context-engine/SKILL.md",
    "skills/context-pack/SKILL.md",
    "skills/converge/SKILL.md",
    "skills/cook/SKILL.md",
    "skills/council/SKILL.md",
    "skills/db/SKILL.md",
    "skills/debug/SKILL.md",
    "skills/dependency-doctor/SKILL.md",
    "skills/deploy/SKILL.md",
    "skills/design/SKILL.md",
    "skills/diagram/SKILL.md",
    "skills/doc-processor/SKILL.md",
    "skills/docs-seeker/SKILL.md",
    "skills/docs/SKILL.md",
    "skills/fix/SKILL.md",
    "skills/git/SKILL.md",
    "skills/graft/SKILL.md",
    "skills/hallucination-guard/SKILL.md",
    "skills/improve-architecture/SKILL.md",
    "skills/incident/SKILL.md",
    "skills/integrity-check/SKILL.md",
    "skills/journal/SKILL.md",
    "skills/launch/SKILL.md",
    "skills/logic-guardian/SKILL.md",
    "skills/marketing/SKILL.md",
    "skills/mcp-builder/SKILL.md",
    "skills/neural-memory/SKILL.md",
    "skills/onboard/SKILL.md",
    "skills/perf/SKILL.md",
    "skills/plan/SKILL.md",
    "skills/preflight/SKILL.md",
    "skills/problem-solver/SKILL.md",
    "skills/quarantine/SKILL.md",
    "skills/rescue/SKILL.md",
    "skills/research/SKILL.md",
    "skills/retro/SKILL.md",
    "skills/review-intake/SKILL.md",
    "skills/review/SKILL.md",
    "skills/safeguard/SKILL.md",
    "skills/sast/SKILL.md",
    "skills/scaffold/SKILL.md",
    "skills/scope-guard/SKILL.md",
    "skills/scout/SKILL.md",
    "skills/sentinel-env/SKILL.md",
    "skills/sentinel/SKILL.md",
    "skills/sequential-thinking/SKILL.md",
    "skills/session-bridge/SKILL.md",
    "skills/skill-forge/SKILL.md",
    "skills/skill-router/SKILL.md",
    "skills/slides/SKILL.md",
    "skills/surgeon/SKILL.md"
  ],
  "skillMdFetched": 60
}