asu-resume-audit-skill

asu-resume-audit-skill is a skill for Codex from Claycui828/ASu-resume-skills. It costs 167 tokens per session (3,273 once invoked), scanned A, original, MIT.

An evidence-based workflow for checking whether claims in a résumé are supported by public records, documents, code repositories, or other provided sources. It produces a structured report in HTML and PDF.

In plain words
What is it for?
Use it to review education, employment, open-source roles, project contributions, metrics, and public disputes while recording the evidence and its limitations.
Why use it?
It separates confirmed facts, contradictions, unsupported claims, and unresolved information instead of treating every résumé statement as true or false. It also sets limits to reduce privacy and reputational harm.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to review education, employment, open-source roles, project contributions, metrics, and public disputes while recording the evidence and its limitations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/claycui828/asu-resume-skills/asu-resume-audit-skill
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 Claycui828/ASu-resume-skills --skill asu-resume-audit-skill
Clone the repo
git clone --depth 1 https://github.com/Claycui828/ASu-resume-skills

Made for: 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.

agentmods badge for asu-resume-audit-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/claycui828/asu-resume-skills/asu-resume-audit-skill/github.svg)](https://agentmods.dev/skills/claycui828/asu-resume-skills/asu-resume-audit-skill)
Your own site
<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.

agentmods 80×15 button for asu-resume-audit-skill

Your own site · 80×15
<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>
Per session 167 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,273 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.

ModelPer sessionOnce 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

Measured 13d ago against content hash 78e841695f57, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/render_report.py, scripts/validate_report.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/asu-resume-audit-skill/SKILL.md · 267 lines

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:

  1. report-data.json:标准化主张、来源、结论、包装模式、时间线和限制。
  2. 自包含 report.html:不引用外部样式、脚本、字体或图片。
  3. 与同一数据模型一致的 report.pdf
  4. 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 unsupportedpartially_corroboratedunverifiable
  • 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-001S-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:

  1. 候选人正式或事实上属于核心作者。
  2. 候选人领导了 1.0 到 2.0 的迁移。
  3. 性能指标确实提升了 25%。
  4. 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
}

Read the full file on GitHub · 267 lines

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.

  1. 13d ago First seen · 267 lines · 167 tokens per session scan A 78e841695f57

Subscribe to this mod's changes

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.