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 Claycui828/ASu-resume-skills --skill asu-resume-audit-skillgit clone --depth 1 https://github.com/Claycui828/ASu-resume-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/claycui828/asu-resume-skills/asu-resume-audit-skill)<a href="https://agentmods.dev/skills/claycui828/asu-resume-skills/asu-resume-audit-skill"><img src="https://agentmods.dev/badge/skills/claycui828/asu-resume-skills/asu-resume-audit-skill/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.
<a href="https://agentmods.dev/skills/claycui828/asu-resume-skills/asu-resume-audit-skill"><img src="https://agentmods.dev/badge/skills/claycui828/asu-resume-skills/asu-resume-audit-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00167 | $0.03273 |
| Opus 5 | $0.00084 | $0.01636 |
| Sonnet 5 | $0.00033 | $0.00655 |
| Haiku 4.5 | $0.00017 | $0.00327 |
Grade A, and why
asu-resume-audit-skill 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 13d 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 — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ASU 简历真实性审计 Skill
把简历视为一组可以独立检验的主张。目标不是判断一个人“好”或“坏”,而是确定现有证据支持什么、直接反驳什么,以及哪些内容仍然无法核验。
必须交付的结果
除非用户明确缩小范围,否则生成以下内容:
report-data.json:标准化主张、来源、结论、包装模式、时间线和限制。- 自包含
report.html:不引用外部样式、脚本、字体或图片。 - 与同一数据模型一致的
report.pdf。 - 一段简短的对话总结:优先说明最强的支持证据、直接矛盾和未解决缺口。
完成 JSON 后,用 scripts/render_report.py 生成 HTML/PDF;交付前用 scripts/validate_report.py 校验。
证据与伤害边界
简历审计涉及可识别个人,错误结论可能造成真实的名誉伤害,因此始终遵守以下规则:
- 只使用公开且与任务直接相关的信息。不得搜集住址、电话、家庭成员、账号凭证、私人消息或无关个人信息。
- 截图、指控文章、匿名评论和候选人自有主页只能证明“有人这样说过”,不能自动成为独立证据。
- 使用
公开证据仅支持 contributor,尚未支持 core author等精确表述,避免使用骗子、害虫或欺诈者等人格标签。 - 只有可靠证据与主张直接冲突时才标记
contradicted;否则使用unsupported、partially_corroborated或unverifiable。 - 主动提 issue、贡献前端/文档、与维护者建立关系或因此获得正式社区身份,本身不是不当行为。要核验的是简历是否准确描述正式角色、技术深度和个人贡献。
- 不得用学校排名或“双非”身份推断诚信。“双非”是非正式标签,不是造假证据。应核验院校、项目、学籍与学位授予方。
- 性别、外貌、性格、税务或动机推断通常与简历真实性无关;除非权威证据证明其直接关联某条简历主张,否则排除。
- 对当事人有利的重要证据必须与不利证据同等展示。
给结论状态前先阅读 references/evidence-methodology.md。核验开源或教育主张前,阅读相应专项参考。
工作流程
1. 确定范围并保存来源集合
列出用户提供的全部材料:
- 简历 PDF 或截图;
- 文章和社交媒体帖子;
- 代码仓库及个人主页链接;
- 网页存档;
- 用户提供的就业、学校、奖项或付费社群背景。
条件允许时完整阅读链接和文档,以原始分辨率检查图片。页面被安全策略或登录限制阻挡时,说明限制;可使用用户提供的正文或其他公开来源,但不得绕过访问控制。
立即为每个来源分配编号(S-001、S-002……),并标记来源类型:
official_record:官方记录;repository_record:代码仓库记录;candidate_self_statement:候选人自述;user_provided_document:用户提供材料;media_or_commentary:媒体或评论文章;anonymous_or_unverified:匿名或未经核验来源。
2. 把简历拆成原子主张
不要把整段经历作为一条主张。将角色、范围、结果和因果关系分开检验。
例如:
“作为核心作者主导项目从 1.0 到 2.0,性能提升 25%。”
应拆为:
- 候选人正式或事实上属于核心作者。
- 候选人领导了 1.0 到 2.0 的迁移。
- 性能指标确实提升了 25%。
- 该提升由候选人的工作造成或得到其实质贡献。
每条主张记录:
- 简历原文;
- 标准化主张;
- 主张类别;
- 时间范围;
- 组织或项目;
- 隐含角色与责任范围;
- 核验所需证据。
数据格式见 references/report-schema.md。
3. 先做确定性的内部一致性检查
联网研究前,先让简历与自身对账:
- 重算转化率、增长率和比例;
- 比较简历、主页、offer 和帖子中的日期;
- 标记重叠的全职或实习时间;
- 比较不同平台使用的角色级别;
- 找出没有明确比较范围的“最年轻、第一、核心”等最高级;
- 区分项目整体指标与个人影响指标;
- 检查是否在没有基线或对照组时宣称因果关系。
算术矛盾不依赖外部解释,通常可以给出高置信度。
当材料能够明确给出分子、分母和展示百分比时,在对应的结构化 Claim 中写入:
"metric": {
"numerator": 200,
"denominator": 2000,
"displayed_percent": 10
}
What ships with it
11 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.
- agents/openai.yaml 338 B
- assets/report_template.html 18 KB
- evals/evals.json 1.5 KB
- references/asu-case-study.md 5.2 KB
- references/education-branding-audit.md 2.1 KB
- references/evidence-methodology.md 3.2 KB
- references/inflation-patterns.md 3.2 KB
- references/open-source-audit.md 3.5 KB
- references/report-schema.md 4.5 KB
- scripts/render_report.py 18 KB runs code
- scripts/validate_report.py 7.3 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.
- 13d ago First seen · 267 lines · 167 tokens per session scan A 78e841695f57
asu-resume-audit-skill is a skill published in the GitHub repository Claycui828/ASu-resume-skills (286 stars, last pushed 20d ago), licensed MIT. It adds 167 tokens to every session and 3,273 once invoked, about $0.0008 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
brainstorming
A brainstorming workflow for turning an idea into an agreed design before implementation. It requires exploring the project, asking clarifying questions, comparing options, documenting the design, and getting user approval.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-commit-conventions
A Chinese-language guide to Conventional Commits, a format for writing consistent Git commit messages, plus related changelog, commit-checking, and commit-helper configuration.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
chinese-code-review
A Chinese-language code-review communication guide with templates and severity levels for review comments.