SKILLS & AGENTS/Skill 与 Agent·CLAUDE-SKILL

skillspec

modiqo/skillspec

SkillSpec makes agent skills followable, testable, and provable with Doctor risk reports, guided imports, structured contracts, and alignment proof.

打开仓库Open repository 官网Homepage

怎么装：Install: curl -fsSL https://skillspec.sh/install.sh | sh

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%

724 → 724 stars · 2 个快照724 → 724 stars · 2 snapshots

讨论DISCUSSION

1 SOURCES1 SOURCES

1 条外部提及1 external mentions

状态STATUS

持续活跃Active

它能帮你做成什么What it helps you do

04 / 安装04 / Install

怎么装How to install

CURL-PIPE

$

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

CARGO

$

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

存在风险Risk found

01需要 API KeyREQUIRES API KEY: 未在文档中发现Not found in the docs
02需要本地环境NEEDS LOCAL RUNTIME: 未在文档中发现Not found in the docs
03需要 DockerNEEDS DOCKER: 未在文档中发现Not found in the docs
04难度DIFFICULTY: 一键安装One-click install

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

来源 URLSource URL: https://github.com/modiqo/skillspec
原始数据哈希Raw data hash: 433e7a913a61d208e40d10bcecc98497
解析时间Parsed at: 2026-10-03T23:15:16.499Z
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:token:code:token-usage
分类来源Category source: rules
焦点Focus: token (3)

静态扫描STATIC SCAN

01执行远程脚本Runs a remote scriptreadme

curl -fsSL https://skillspec.sh/install.sh | sh

02执行远程脚本Runs a remote scriptdocs/examples/why-skillspec-demo/skillspec_backed/SKILL.md
```
curl -fsSL https://skillspec.sh/install.sh | sh
```
03控制浏览器Controls a browser.claude/skills/rote-shell/source/SKILL.md
```
Do not satisfy browser intent with `rote exec`, raw Playwright, native web
```

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/"
    },
    {
      "agent": "codex",
      "evidence": "examples/generic-skill-creator/SKILL.md: …lidating, and forward-testing Codex skills without colliding with the ca…"
    }
  ],
  "apiKey": null,
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 3,
      "dev-tools": 1,
      "indie-web": 0,
      "skill-agent": 6,
      "productivity": 0
    },
    "primary": "skill-agent",
    "secondary": "claude-skill"
  },
  "localRuntime": null,
  "skillMdTotal": 24,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 0,
    "agent": 1,
    "media": 0,
    "design": 0,
    "browser": 0,
    "devtool": 1,
    "security": 0,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "24 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "skills/ directory with 10 markdown files",
      "weight": 0.75
    },
    {
      "signal": "README describes a Claude / Agent Skill",
      "weight": 0.7
    },
    {
      "signal": "Claude Code plugin manifest",
      "weight": 0.7
    },
    {
      "signal": "name contains 'skill'",
      "weight": 0.4
    },
    {
      "signal": "description mentions AI",
      "weight": 0.2
    }
  ],
  "scannedSources": [
    "readme",
    ".claude/skills/code-review/SKILL.md",
    ".claude/skills/code-review/source/SKILL.md",
    ".claude/skills/commit-convention/SKILL.md",
    ".claude/skills/commit-convention/source/SKILL.md",
    ".claude/skills/research-codebase/SKILL.md",
    ".claude/skills/research-codebase/source/SKILL.md",
    ".claude/skills/rote-browse/SKILL.md",
    ".claude/skills/rote-shell/SKILL.md",
    ".claude/skills/rote-shell/source/SKILL.md",
    "docs/examples/why-skillspec-demo/prose_only/SKILL.md",
    "docs/examples/why-skillspec-demo/skillspec_backed/SKILL.md",
    "examples/durable-executor/SKILL.md",
    "examples/generic-skill-creator/SKILL.md",
    "examples/imports/SKILL.md",
    "examples/local-csv-report/SKILL.md",
    "examples/mcp-builder/SKILL.md",
    "examples/pdf-processing/SKILL.md",
    "examples/pdf/SKILL.md",
    "examples/repo-readiness/SKILL.md",
    "examples/rote-browse/SKILL.md",
    "examples/rote-computer/SKILL.md",
    "examples/skill-router/SKILL.md",
    "plugins/skillspec/skills/skillspec/SKILL.md",
    "skills/skillspec/SKILL.md"
  ],
  "skillMdFetched": 24
}

skillspec

它现在处在什么位置Where it stands right now

相关讨论RELATED DISCUSSIONS

它能帮你做成什么What it helps you do

怎么装How to install

限制与风险Limits and risk