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/full-stack-skills/agent-skills/skill-trace-evaluationnpx skills add full-stack-skills/agent-skills --skill skill-trace-evaluationgit 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-evaluation)<a href="https://agentmods.dev/skills/full-stack-skills/agent-skills/skill-trace-evaluation"><img src="https://agentmods.dev/badge/skills/full-stack-skills/agent-skills/skill-trace-evaluation.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 | $0.00069 | $0.06576 |
| Opus 5 | $0.00034 | $0.03288 |
| Sonnet 5 | $0.00014 | $0.01315 |
| Haiku 4.5 | $0.00007 | $0.00658 |
Grade A, and why
skill-trace-evaluation 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 467 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill TRACE 质量评测
评估模型:脚本计算确定性基分 + AI 阅读内容后语义校准(±0.3)→ 最终分。 详细评分标准见 references/scoring-criteria.md,校准规则见 references/calibration-guide.md。
⚡ 新手 30 秒入门
干什么? 对任意 Agent Skill 做 TRACE 五维度质量评分,输出带子项分的评估报告。
什么时候触发?
- 刚写完一个新 Skill,想知道质量怎么样 → 直接用
- 用户要求 "检查 Skill 质量"、"TRACE 评测"、"技能打分"
- 提供了 Skill 目录路径 + "评估"/"评测"/"打分" 关键词
触发示例:
✅ "用 TRACE 评测 /path/to/skill"
✅ "TRACE 评测 ddd-architecture-awesome"
✅ "对 skill-trace-evaluation 做五维度评估"
✅ "生成 TRACE 报告 + HTML 雷达图"
✅ "严格评测 jimeng-prompt-text2image" (全部子项需 5.0)
✅ "快速检查这个 Skill 有哪些扣分项" (仅输出扣分项)
✅ "只检查 T 维度" (单维度聚焦)
✅ "我修改了 FAQ,重新评测一下规范性"
✅ "输出 TRACE 五维画像 + 基线对比"
✅ "技能评估报告 + 官方合规检查"
一句话流程: 运行脚本拿基分 → 阅读 SKILL.md → 对照评分细则校准 → 产出报告。
执行时机
以下场景适合触发 TRACE 评测:
- 新 Skill 完成编写:刚写完 SKILL.md,想知道质量基线
- Skill 重大修改后:修改了功能说明、FAQ、边界条件、触发词等核心内容
- 用户明确要求:"检查 Skill 质量"、"TRACE 评测"、"技能打分"
- 第三方评审:平台审核员或社区用户对 Skill 做质量评估
能力边界说明
✅ 擅长处理
- 评估任意 Agent Skill,输出 20 子项评分
- 定位具体扣分原因,每个分数附证据
- 生成标准化报告(dimension-level 中文评语 + 子项分表 + 改进建议)
- 验证修改是否有效:修改后重新评测,对比前后分数变化
- 对比两个版本差异:判断新版本比旧版本在哪些子项有实质提升
- 支持标准/严格/快速/单维度四种模式
⚠️ 需要素材
- 完整评估需要 Skill 目录路径(含 SKILL.md),只凭名称无法评测
- R1/E1/E3 评分需要 AI 自己阅读正文判断语义质量——脚本只提供结构基分
❌ 超出范围(附替代方案)
- 帮你写 Skill 内容 → 用
skill-awesome(规范知识)或skill-trace-checker(发布前自检) - 评测非 Skill 类文档 → 找对应工具
- 自动发布 Skill → 手动完成
评估流程
Step 1 ──── Step 2 ──── Step 3 ──── Step 4
收集基分 阅读技能 逐项校准 产出报告
────────────────────────────────────────────
trace_ev- AI 直接 基分 ±0.3 Markdown
aluate.py 阅读正文 附调整理由 + 可选 HTML
Step 1:收集基分
python3 scripts/trace_evaluate.py --skill-dir <path> --format json
输出含 base_scores:每子项 base(1.0-5.0)、formula(计算公式)、evidence(证据字段)。
Step 2:阅读技能
必须自己阅读 SKILL.md 正文 + 扫描 references/、examples/ 目录。脚本提供结构数据,AI 判断内容质量。
AI 阅读时的检查思路示例:
【T 维】
安全 → 查有无密钥/secrets/脚本,正文有无安全声明
国内 → 查全文中文化程度、示例是否基于国内平台
边界 → 查有无独立边界章节、三分类是否每类≥3例
隐私 → 查有无数据隐私说明(FAQ 或专项章节)
【R 维】
异常 → 查 Gotchas 是否包含"交互式引导模板"(先假设版本→列缺失项)
功能 → 查 workflow 步骤是否覆盖所有声明功能
稳定 → 查有无 validate-plan-execute 循环或等效约束
降级 → 查边界章节中超范围后是否给替代方案
【A 维】
边界定义 → 查三分类是否有场景化判断逻辑("什么时候该用/不该用/模糊怎么判")
触发 → 查 description 信息量,是关键词堆砌还是场景化路由
受众 → 查有无显式说明适用用户类型
定制 → 查有无风格/参数传递机制
【C 维】
文档 → 查 examples 数量是否达标(prompt≥10/cli≥4/doc≥5)
披露 → 查 body 行数 + references 文件数,是否三层结构
结构 → 查 name 规范 + refs 子目录≥2
反模式/FAQ → 查 Gotchas 数量是否≥5 + FAQ 是否≥6且非充数
【E 维】
准确 → 查有无"禁止胡编"规则或等效约束
完整 → 查 examples 数量是否达阈值(prompt≥25/cli≥4/doc≥5)
增值 → 查 refs 子目录≥2 + 是否有评估框架/决策树等深度领域知识
开箱 → 查有无快速开始章节 + ≥3 个可复制开场白
What ships with it
10 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.
- examples/trace-report.generated.html 17 KB
- examples/trace-report.generated.md 5.7 KB
- LICENSE.txt 12 B
- references/calibration-guide.md 4.3 KB
- references/scoring-criteria.md 12 KB
- references/trace-anti-patterns.md 5.7 KB
- references/trace-faq-deep.md 5.7 KB
- references/trace-sample-reports.md 12 KB
- references/trace-skill-checklist.md 2.5 KB
- scripts/trace_evaluate.py 20 KB runs code
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.
- 5d ago First seen · 467 lines · 69 tokens per session scan A 0dba90e5aa04
skill-trace-evaluation 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 69 tokens to every session and 6,576 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…