Agent skill

Hwb Paper Aigc Auditor

by xieyouxixi in xieyouxixi/hwb-math-modeling-skills

Audit a HUAWEI Cup paper for AI-generation traces, template-like modeling, model stacking and fake improvement, producing a risk band, per-section evidence, model-authenticity classification and…

No licenceAuto-check passed

Install Hwb Paper Aigc Auditor

skills CLI
$ npx skills add xieyouxixi/hwb-math-modeling-skills --skill hwb-paper-aigc-auditor -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install xieyouxixi/hwb-math-modeling-skills hwb-paper-aigc-auditor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/xieyouxixi/hwb-math-modeling-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/'skills/论文自查类/hwb-paper-aigc-auditor' .claude/skills/hwb-paper-aigc-auditor && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
hwb-paper-aigc-auditor
GitHub stars
197
Token cost
~713 tokens
SKILL.md length
97 words
Files
15 (incl. references)
Skills in repo
16
Repo updated
First seen
Licence
None found

At a glance

Audit a HUAWEI Cup paper for AI-generation traces, template-like modeling, model stacking and fake improvement, producing a risk band, per-section evidence, model-authenticity classification and…

  • SKILL.md covers Required references, 输入, 审计三层 and 模型真实性分类, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Hwb Paper Aigc Auditor is an agent skill from xieyouxixi/hwb-math-modeling-skills. Audit a HUAWEI Cup paper for AI-generation traces, template-like modeling, model stacking and fake improvement, producing a risk band, per-section evidence, model-authenticity classification and humanisation suggestions. Use at the final stage to locate sections that read as machine-generated so the team can rewrite them in its own voice and disclose AI use truthfully.

Its SKILL.md is about 710 tokens, which your agent loads only when the skill is triggered. The skill folder holds 17 other files, including reference files (for example `HWB数模论文AI痕迹审计完整Prompt.md`, `INTEGRATION_SUMMARY.md` and `QUICK_CHECK_CARD.md`).

The repository describes itself as: 华为杯研究生数学建模竞赛全套AI-skills.

Example prompts

  • “/hwb-paper-aigc-auditor”

What it can do on your machine

Read from SKILL.md and the folder at commit afcf23a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Hwb Paper Aigc Auditor loads about 713 tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 99 tokens; SKILL.md has 97 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~99
When it runs · the whole SKILL.md, loaded when a task matches
~713
With references · SKILL.md plus every file in references/, read only if the agent opens them
~10k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 97 words (~713 tokens).

name
hwb-paper-aigc-auditor
agent_created
true

Read the full SKILL.md on GitHub

Files

SKILL.md and 14 other files (references) in skills/论文自查类/hwb-paper-aigc-auditor of xieyouxixi/hwb-math-modeling-skills.

  • SKILL.md
  • HWB数模论文AI痕迹审计完整Prompt.md
  • INTEGRATION_SUMMARY.md
  • QUICK_CHECK_CARD.md
  • README.md
  • agents/openai.yaml
  • references/audit-framework.md
  • references/detector-integration.md
  • references/humanizer-keywords.txt
  • references/layer1-enhanced-detection.md
  • references/models-zh.md
  • references/nature-detector-integration.md
  • references/patterns-zh.md
  • templates/HWB数模论文AI痕迹审计报告模板.html
  • templates/HWB数模论文AI痕迹自查指南.html

Open the folder on GitHubat commit afcf23a

Compare with similar skills

Hwb Paper Aigc Auditor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Hwb Paper Aigc Auditor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Hwb Paper Aigc Auditor this skillxieyouxixi/hwb-math-modeling-skills197—~713Automated safety check: PassNone
Observe Traceruvnet/ruflo74k—~522Automated safety check: NotesMIT
Tracezereight/gitlab-mcp2k1 repos~412Automated safety check: PassMIT
Distributed Tracingwshobson/agents40k12 repos~527Automated safety check: PassMIT
Arize Tracegithub/awesome-copilot40k1 repos~5.9kAutomated safety check: NotesMIT
Evidence-Driven TraceYeachan-Heo/oh-my-claudecode40k—~2.6kAutomated safety check: PassMIT

Similar skills

  • Observe Trace

    ruvnet/ruflo

    Trace agent execution by collecting spans and building a trace tree for a task

    74k GitHub stars~522 tokensUpdated yesterday
    Auto-check: notes
  • Trace

    zereight/gitlab-mcp

    Evidence-driven tracing with competing hypotheses in parallel.

    2k GitHub starsUsed in 1 repo~412 tokens
    DevelopmentAuto-check passed
  • Distributed Tracing

    wshobson/agents

    Implement distributed tracing with Jaeger and Tempo to track requests across microservices and identify performance bottlenecks.

    40k GitHub starsUsed in 12 repos~527 tokens
    DevOps & CloudAuto-check passed
  • Arize Trace

    github/awesome-copilot

    Official

    Downloads, exports, and inspects existing Arize traces and spans to understand what an LLM app is doing or debug runtime issues.

    40k GitHub starsUsed in 1 repo~5.9k tokens
    DevelopmentAuto-check: notes
  • Evidence-Driven Trace

    Yeachan-Heo/oh-my-claudecode

    Explains why something happened by generating competing hypotheses, gathering evidence in parallel, ranking explanations and proposing the next discriminating probe.

    40k GitHub stars~2.6k tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Trace

    jeremylongshore/tons-of-skills-marketplace

    A skill your agent uses when encountering bugs, test failures, runtime errors, broken builds, or "this doesn't work" reports.

    2.8k GitHub stars~5k tokensUpdated yesterday
    DevelopmentAuto-check passed

More from xieyouxixi/hwb-math-modeling-skills

All 16 skills in this repo
  • Hwb Cpgmcm Award Standing

    xieyouxixi/hwb-math-modeling-skills

    Query a graduate training unit's Huawei Cup (CPGMCM) award profile, estimate the award band from the contest's total team count and a team's rank or paper score, and assess a student's preparation…

    197 GitHub stars~936 tokensUpdated 24 days ago
    Auto-check passed
  • Hwb Model Dictionary

    xieyouxixi/hwb-math-modeling-skills

    Judge whether a candidate model actually fits a HUAWEI Cup problem, its data and its intended use, returning a model archive with requirements, assumptions, strengths, limitations, failure…

    197 GitHub stars~511 tokensUpdated 24 days ago
    Auto-check passed
  • Hwb Paper Format Checker

    xieyouxixi/hwb-math-modeling-skills

    Run a strict whole-paper format, structure, anonymity and file-hygiene audit for a HUAWEI Cup paper: official template compliance, cover page, abstract page limit, page allocation, headings…

    197 GitHub stars~645 tokensUpdated 24 days ago
    Auto-check passed
  • Hwb Abstract Checker

    xieyouxixi/hwb-math-modeling-skills

    Check the title, abstract and keywords of a HUAWEI Cup paper for independence, information density, the five required abstract elements and two-page limit compliance.

    197 GitHub stars~514 tokensUpdated 24 days ago
    Auto-check passed
  • Hwb AI Usage Disclosure

    xieyouxixi/hwb-math-modeling-skills

    Generate or review an AI-tool usage statement and detailed usage disclosure for a HUAWEI Cup paper, matching the contest's explicit policy that AI products may be used only as auxiliary tools with…

    197 GitHub stars~588 tokensUpdated 24 days ago
    Auto-check passed
  • Hwb Model Assumption Checker

    xieyouxixi/hwb-math-modeling-skills

    Diagnose whether each modeling assumption in a HUAWEI Cup paper is necessary, realistic, consistent with the data, and actually used later in the paper.

    197 GitHub stars~469 tokensUpdated 24 days ago
    Auto-check passed

Questions about Hwb Paper Aigc Auditor

What does Hwb Paper Aigc Auditor do?

Audit a HUAWEI Cup paper for AI-generation traces, template-like modeling, model stacking and fake improvement, producing a risk band, per-section evidence, model-authenticity classification and…. Hwb Paper Aigc Auditor is an agent skill from xieyouxixi/hwb-math-modeling-skills. Audit a HUAWEI Cup paper for AI-generation traces, template-like modeling, model stacking and fake improvement, producing a risk band, per-section evidence, model-authenticity classification and humanisation suggestions.

How do I install Hwb Paper Aigc Auditor in Claude Code?

Run `npx skills add xieyouxixi/hwb-math-modeling-skills --skill hwb-paper-aigc-auditor -a claude-code`. Or copy the skill folder (skills/论文自查类/hwb-paper-aigc-auditor in xieyouxixi/hwb-math-modeling-skills) into .claude/skills/hwb-paper-aigc-auditor in your project. Claude Code loads it when a task matches its description.

How do I install Hwb Paper Aigc Auditor in Codex?

Run `npx skills add xieyouxixi/hwb-math-modeling-skills --skill hwb-paper-aigc-auditor -a codex`. Or copy the skill folder (skills/论文自查类/hwb-paper-aigc-auditor in xieyouxixi/hwb-math-modeling-skills) into .agents/skills/hwb-paper-aigc-auditor in your project. Codex loads it when a task matches its description.

Can I use Hwb Paper Aigc Auditor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xieyouxixi/hwb-math-modeling-skills --skill hwb-paper-aigc-auditor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/hwb-paper-aigc-auditor, .gemini/skills/hwb-paper-aigc-auditor, .github/skills/hwb-paper-aigc-auditor and .opencode/skills/hwb-paper-aigc-auditor in your project.

What does Hwb Paper Aigc Auditor need to run?

SKILL.md names no scripts, command-line tools or credentials: Hwb Paper Aigc Auditor is instructions for the agent only.

Does Hwb Paper Aigc Auditor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Hwb Paper Aigc Auditor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Hwb Paper Aigc Auditor use?

No licence was found for Hwb Paper Aigc Auditor or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Hwb Paper Aigc Auditor use?

About 713 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.4k tokens, read only when the agent opens those files.

What are the alternatives to Hwb Paper Aigc Auditor?

Skills that share tags, products or a category with Hwb Paper Aigc Auditor: Observe Trace (ruvnet/ruflo, 74k stars), Trace (zereight/gitlab-mcp, 2k stars), Distributed Tracing (wshobson/agents, 40k stars) and Arize Trace (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Hwb Paper Aigc Auditor?

xieyouxixi (a GitHub user) maintains it in xieyouxixi/hwb-math-modeling-skills, which has 197 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on September 16, 2026.

Source: xieyouxixi/hwb-math-modeling-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.