What is skill-package-validator?

A pre-publication checker for Agent Skills packages, which are folders containing instructions and optional scripts or assets for an AI agent.

It checks the folder structure, SKILL.md YAML header, manifest files, and referenced resources, then produces a Markdown pass-or-fail report for release review or CI checks.

It catches missing files, invalid metadata, broken internal paths, and mismatched package details before SkillHub rejects the upload.

skill-package-validator — Skill for Claude Code and Codex by BiglionX

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add BiglionX/SkillHub --skill skill-package-validator

Clone the repo

git clone --depth 1 https://github.com/BiglionX/SkillHub

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/biglionx/skillhub/skill-package-validator/github.svg)](https://agentmods.dev/skills/biglionx/skillhub/skill-package-validator)

Your own site

<a href="https://agentmods.dev/skills/biglionx/skillhub/skill-package-validator"><img src="https://agentmods.dev/badge/skills/biglionx/skillhub/skill-package-validator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/biglionx/skillhub/skill-package-validator"><img src="https://agentmods.dev/badge/skills/biglionx/skillhub/skill-package-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 757 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00057	$0.00757
Opus 5.5	$0.00023	$0.00303
Sonnet 5.5	$0.00011	$0.00151
Haiku 4.5	$0.00006	$0.00076

Measured 2mo ago against content hash 7a9aa16c40e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skill-package-validator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/skill-package-validator/SKILL.md · 67 lines

What it actually says

技能包校验 (skill-package-validator)

本技能指导 Agent 对技能包做发布前静态校验。技能包是 SkillHub 分发的 Agent Skills 标准包，最小结构：

my-skill/
├── SKILL.md            # 必须：frontmatter + 技能指令正文
├── scripts/            # 可选：辅助脚本
├── assets/             # 可选：资源文件
└── package.json        # 可选：manifest（或 skill.json）

何时使用

审核/发布前校验技能包
复查 skillhub publish 的 --dry-run 结果
排查上传被拒的包

校验清单（按序执行）

1. 目录结构

SKILL.md 存在（缺失 → 直接拒绝）
无 node_modules/、.git/ 混入
scripts/、assets/ 若存在，内容有实际用途（非空）

2. SKILL.md frontmatter（YAML）

YAML 语法合法（用 gray-matter/js-yaml 解析）
必填键：name（非空、slug 友好）、description（非空、简洁）
推荐键：version（x.y.z 语义化）、allowed-tools、license、author
正文有实际指令（非空、非占位符 lorem ipsum）
引用的工具/文件路径在包内存在

3. Manifest（package.json / skill.json）

JSON 合法
name 非空、version 匹配 /^\d+\.\d+\.\d+$/
与 SKILL.md frontmatter 的 name/version 一致（不一致 → 警告）

4. 资源引用

正文/脚本引用的相对路径（如 scripts/foo.py、assets/logo.png）实际存在
无对外部绝对路径的强依赖（若必须，记录到报告）

输出

生成结构化校验报告（markdown）：

# 校验报告: <skill-name>@<version>
- 结构: PASS/FAIL
- frontmatter: PASS/FAIL (错误列表)
- manifest: PASS/FAIL (错误列表)
- 资源: PASS/FAIL (警告列表)
- 结论: 通过 / 拒绝 (原因)

任一 FAIL → 拒绝发布；仅警告 → 可发布但记录。

实现参考

web 端解析器：apps/web/lib/skills/skill-md-parser.ts（gray-matter + zod）
CLI 端校验器：apps/cli/src/utils/validator.ts（zod schema）
本地试跑：pnpm --filter @skillhub/cli 后 node apps/cli/dist/index.js publish <dir> --dry-run

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 67 lines · 57 tokens per session scan A 7a9aa16c40e4

Subscribe to this mod's changes

skill-package-validator is a skill published in the GitHub repository BiglionX/SkillHub (38 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 57 tokens to every session and 757 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Building agents

skill-package-validator next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skill-package-validatorBiglionX/SkillHub	Skill	38	1mo ago	Apache-2.0	A	57	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code