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.
npx agentmods add skills/biglionx/skillhub/skill-package-validatornpx skills add BiglionX/SkillHub --skill skill-package-validatorgit clone --depth 1 https://github.com/BiglionX/SkillHubWrote 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.
[](https://agentmods.dev/skills/biglionx/skillhub/skill-package-validator)<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="Measured on agentmods" height="20"></a>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 | $0.00057 | $0.00757 |
| Opus 5 | $0.00028 | $0.00378 |
| Sonnet 5 | $0.00011 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
skill-package-validator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
技能包校验 (skill-package-validator)
本技能指导 Agent 对技能包做发布前静态校验。技能包是 SkillHub 分发的 Agent Skills 标准包，最小结构：
my-skill/
├── SKILL.md # 必须：frontmatter + 技能指令正文
├── scripts/ # 可选：辅助脚本
├── assets/ # 可选：资源文件
└── package.json # 可选：manifest（或 skill.json）
何时使用
- 审核/发布前校验技能包
- 复查
skillhub publish的--dry-run结果 - 排查上传被拒的包
校验清单（按序执行）
1. 目录结构
-
SKILL.md存在（缺失 → 直接拒绝） - 无
node_modules/、.git/混入 -
scripts/、assets/若存在，内容有实际用途（非空）
2. SKILL.md frontmatter（YAML）
- YAML 语法合法（用
gray-matter/js-yaml解析） - 必填键：
name（非空、slug 友好）、description（非空、简洁） - 推荐键：
version（x.y.z语义化）、allowed-tools、license、author - 正文有实际指令（非空、非占位符 lorem ipsum）
- 引用的工具/文件路径在包内存在
3. Manifest（package.json / skill.json）
- JSON 合法
-
name非空、version匹配/^\d+\.\d+\.\d+$/ - 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
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.
- 4d ago First seen · 67 lines · 57 tokens per session scan A 7a9aa16c40e4
skill-package-validator is a skill published in the GitHub repository BiglionX/SkillHub (34 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 757 once invoked, about $0.0003 per session on Opus 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…