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 skills add full-stack-skills/agent-skills --skill skill-trace-checkergit clone --depth 1 https://github.com/full-stack-skills/agent-skillsWrote 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/full-stack-skills/agent-skills/skill-trace-checker)<a href="https://agentmods.dev/skills/full-stack-skills/agent-skills/skill-trace-checker"><img src="https://agentmods.dev/badge/skills/full-stack-skills/agent-skills/skill-trace-checker.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 5.1 | $0.00104 | $0.03517 |
| Opus 5 | $0.00052 | $0.01758 |
| Sonnet 5 | $0.00021 | $0.00703 |
| Haiku 4.5 | $0.00010 | $0.00352 |
Grade A, and why
skill-trace-checker 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 7d 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.
This is a copy
78% identical to luban — 594 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill TRACE 质量评测流程
强制规则：每次创建或修改 Skill 后，必须完成本 TRACE 自检，全部子项达到满分标准才算任务完成。 不允许在评分未达标时交付 Skill，也不允许只生成好看的报告而不真正改进 Skill 内容。
⚡ 新手 30 秒入门
这个 Skill 是干什么的？ 帮你检查自己写的 Skill 质量够不够好，哪里不足、怎么改。
什么时候触发？
- 刚写完一个新 Skill，想知道要不要改 → 直接用
- 修改了已有 Skill 的核心内容 → 用
- 用户要求"检查 Skill 质量" → 用
直接复制这些触发示例就能开始：
✅ "帮我检查刚写的 opc-skill 是否符合 TRACE 标准"
✅ "对这个 SKILL.md 做全量 TRACE 自检"
✅ "检查一下 skill-trace-checker 本身的质量有没有问题"
✅ "我修改了招聘 Skill 的 FAQ，重新评测一下"
✅ "这个 Skill 的反模式章节写得够好吗？帮我打分"
一句话流程： 读取 Skill 文件 → 对照20个检查项逐项打分 → 找出 < 5.0 的子项 → 修改 → 重打分 → 全部 5.0 才结束。
能力边界说明
✅ 擅长处理
- 检查新创建的 Skill：读取 SKILL.md 及 references/ 文件，逐维度打分，输出结构化评分表
- 定位具体扣分原因：每个低于 5.0 的子项都给出"是什么问题、在哪个文件、怎么改"的精确指引
- 验证修改是否有效：修改后重新打分，确认实质性改进而非只改措辞
- 批量检查多个文件：同时对 SKILL.md + references/ 下多份文件综合评判
- 对比两个版本差异：判断新版本是否比旧版本在某个子项上有实质提升
- 生成标准评分表：输出统一格式的 TRACE 评分表，方便记录和追踪
⚠️ 需要素材才能做
- 完整自检：需要提供 SKILL.md 文件路径或完整内容；只凭 Skill 名称无法评测
- 针对性建议：需要描述 Skill 的使用场景（面向什么用户、解决什么问题），否则只能给通用建议
- 多版本对比：需要提供两个版本的文件内容，才能判断改进幅度
❌ 超出范围（附替代方案）
- 帮你写 Skill 内容：本 Skill 只评分，不帮你生成 Skill 内容 → 用 skill-creator 来创建 Skill
- 评测非 Skill 类文档：如 README、产品文档、代码质量 → 找对应的代码审查工具或文档评审 Skill
- 执行 Skill 的功能：只负责质量评测，不代替被检查的 Skill 执行实际任务
- 自动发布或安装 Skill：评测通过后的发布操作需手动完成
执行时机
以下任一情况发生后，立即执行本检查流程：
- 完成新 Skill 的 SKILL.md 编写
- 对已有 Skill 进行重大内容修改（新增模块、修改行为规范、调整 FAQ 等）
- 用户明确要求"检查 Skill 质量"或"TRACE 评测"
TRACE 五维度评分标准
对每个子项按 1.0～5.0 打分，未达 5.0 则必须立即修改 Skill 内容直到满分。
T · Trust 可信任度（目标：5.0）
| 子项 | 满分标准 | 检查方法 |
|---|---|---|
| 国内适配性 | 全中文界面；支持口语化中文输入；示例基于国内真实场景（微信/淘宝/小红书等） | 检查所有示例和说明是否为中文，触发词是否包含中文关键词 |
| 安全性 | 无 P0/P1 安全风险；不引导用户操作他人账号；不处理真实敏感数据 | 检查系统提示词中是否有"禁止行为"章节，是否有隐私保护说明 |
| 边界透明度 | 能做/需素材/超范围三类清晰区分，且每类有具体例子 | SKILL.md 中是否有独立的"能力边界说明"章节 |
| 数据隐私规范 | FAQ 或专项章节明确说明敏感数据处理原则，提供脱敏操作指导 | 检查是否有隐私/数据安全相关说明 |
扣分常见原因：
- 示例全是英文场景
- 没有隐私使用说明
- 边界描述模糊（只说"有些场景不支持"）
R · Reliability 可靠性（目标：5.0）
| 子项 | 满分标准 | 检查方法 |
|---|---|---|
| 异常处理 | 所有错误提示为用户语言而非技术报错；格式为"缺少[具体项]+如何补充" | 检查系统提示词中是否有精确错误提示规范，是否明确禁止笼统提示 |
| 功能完善性 | 主要使用场景全覆盖，无明显功能盲区；每个功能有输出格式说明 | 数一下功能点，对比典型用户需求是否有遗漏 |
| 运行稳定性 | 输入模糊时有明确的降级策略（先给假设版本再问），不挂起也不给空回复 | 系统提示词中是否有"遇到信息不足时"的处理规则 |
| 降级兜底 | 超出范围时给出替代工具引导，多任务时按优先级排序 | 能力边界章节是否说明了超范围后的处理方式 |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 256 lines · 104 tokens per session scan A 35804af3b42a
skill-trace-checker is a skill published in the GitHub repository full-stack-skills/agent-skills (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 104 tokens to every session and 3,517 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 78% identical to luban, differing in 594 lines, and is treated as a copy.
Other skills, from other repositories
skill-creator
A guide for creating or improving an agent skill: a SKILL.md file that gives an AI a repeatable workflow for a specific task. It covers the skill’s name, search keywords, instructions, failure handling, and examples where needed.
xiaohongshu-ops
A browser-based operations assistant for Xiaohongshu, a Chinese social-media and shopping platform. It uses a logged-in Chrome browser to analyse accounts and content and manage publishing workflows.
api-skill-builder
A skill generator that finds the web API behind data shown on a website and packages it into a reusable data-fetching skill. An API is a structured way for software to request data from another service.
platform-data-explorer
A platform-exploration skill that examines a website or online service to find useful browser actions and data-extraction tasks that could become skills.
typo3-conformance
Use when checking which TYPO3 versions an extension says it supports, when composer.json and extemconf.php disagree, when a version bump must reach every file that states it, when reviewing a TYPO3 extension for what needs attention, or when auditing coding standards, TER readiness, deprecations and modernization to…
card-xiaohongshu
Xiaohongshu-style knowledge cards, arranged as a swipeable multi-card carousel.