Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Comp Cumcm Disclosure

ASecurity

CUMCM AI 工具使用申报双件套入口:生成/校验《AI工具使用详情》PDF 与正文 AI 使用声明,核对口径一致。触发词:AI 申报、AI工具使用详情、AI 使用声明、disclosure、人工智能工具使用规定、申报四节。

10 stars
0 votes
0 copies
0 views
Added 9/24/2026
ai-agentspythonbash

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add FOURTEEN1416/academic-agent-toolkit --skill comp-cumcm-disclosure --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Comp Cumcm Disclosure?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Comp Cumcm Disclosure
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fourteen1416-comp-cumcm-disclosure/badge)](https://www.skillsdirectory.com/skills/fourteen1416-comp-cumcm-disclosure)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: comp-cumcm-disclosure
description: "CUMCM AI 工具使用申报双件套入口:生成/校验《AI工具使用详情》PDF 与正文 AI 使用声明,核对口径一致。触发词:AI 申报、AI工具使用详情、AI 使用声明、disclosure、人工智能工具使用规定、申报四节。"
---

# CUMCM AI 工具使用申报(comp-cumcm-disclosure)

**定位**:本条是**入口与门禁**,不是生成器。生成逻辑与全部细则以既有真源为准:

| 真源 | 路径 | 作用 |
|---|---|---|
| 执行脚本 | `skills/_utils/build_ai_disclosure.py`(镜像 `skills/shared-scripts/build_ai_disclosure.py`) | 确定性生成声明 + 详情 PDF + `--check-only` 反查 |
| 规则全文 | `skills/_utils/ai_disclosure_rules.md` | 八条不可变边界 + 执行方式 + 正文声明格式(**唯一真源,本技能不复制其内容**) |

> 依《全国大学生数学建模竞赛人工智能工具使用规定(2026 年试行)》执行。

**适用范围**:本双件套机制(确定性脚本 + manifest + 正文声明 + 详情 PDF)
**两族竞赛链通用**——华为杯链的 S14 共用 `comp-final-audit`,其 AI 申报反查闸对
`comp_huawei` 同样按本节 token 执行。但**规则文本的出处是 CUMCM 2026 试行规定**:
华为杯当届若另发 AI 工具使用规定,申报措辞与细则以当届规程为准(provider 白名单与
五类用途闸由脚本统一把守,两族一致),⛔ 勿把国赛规定措辞当作华为杯官方原文引用。

## 何时用

- 需要在论文正文放 AI 使用声明、并产出独立支撑材料 `AI工具使用详情.pdf`。
- 主稿/章节/代码/图表/参考文献发生变化后,需要**重跑同步**(旧详情不能沿用)。
- `comp-final-audit` 的 AI 申报反查闸(fatal 级)报错时,回到本技能排查。

## 唯一执行方式(照抄,勿手改产物)

```bash
# 前置:AGENTS.md 必须含 MH_AI_DISCLOSURE=used 或 =none;=invalid 时立即停止并请用户重新确认

AI_TOOL=skills/_utils/build_ai_disclosure.py
[ -f "$AI_TOOL" ] || AI_TOOL=skills/shared-scripts/build_ai_disclosure.py

# 生成(LaTeX 工程;Word/Markdown 工程把 --paper-source 换成 paper/main.md)
python "$AI_TOOL" --manifest .mh/ai_disclosure.json \
  --paper-source paper/main.tex --output "AI工具使用详情.pdf"

# 收尾阻断检查(未通过不得把写作步骤标为完成)
python "$AI_TOOL" --manifest .mh/ai_disclosure.json \
  --paper-source paper/main.tex --output "AI工具使用详情.pdf" --check-only
```

## manifest 最小样例(`.mh/ai_disclosure.json`)

```json
{
  "schema_version": 3,
  "mode": "used",
  "confirmed_truthful": true,
  "records": [
    { "provider_id": "hunyuan", "model": "hunyuan-turbo",
      "used_on": "2026-09-11", "purposes": ["语言润色", "参考文献格式整理"] }
  ]
}
```

- `provider_id` 只允许白名单国产工具(脚本内 `PROVIDERS`:deepseek / qwen / zhipu / kimi / hunyuan /
  doubao / ernie / spark …),`model` 必须与该 provider 匹配且不得出现境外工具名。
- `purposes` 只允许五类辅助环节:**语言润色、代码调试、排版检查、参考文献格式整理、术语翻译与校对**。
- `mode=used` 时 `records` 1–5 条且 `confirmed_truthful` 必须为 `true`。
- `mode=none` 时正文写"本参赛队在竞赛过程中未使用任何AI工具。",且不得残留旧的详情 PDF。

## 硬约束(违反即合规事故)

1. ⛔ **不得让语言模型自由编写详情**——必须调用确定性脚本;工具/型号/日期/用途只来自用户确认。
2. ⛔ **正文与详情分离**——声明在参考文献**之前**(不编号 `\section*{AI 工具使用声明}`,`\newpage` 独立成页),
   详情 PDF 放工作区根,**不入论文附录**。
3. ⛔ **不把 AI 工具列入参考文献**(2026 规定只要求正文声明 + 独立支撑材料)。
4. ⛔ **不得宣称逐轮对话实录**——第三节只写提问范围与边界("限于/不含/不涉及")。
5. ⛔ **工作区变化必须触发同步**——`--check-only` 指纹比对不通过就重跑生成。

## 与 comp-final-audit 的接口

反查闸必查 5 个结构 token(详情 PDF 须全部命中):
`AI工具使用详情` / `所用AI工具名称` / `具体使用目的和环节` / `主要提示方式与使用过程` / `采纳、人工修改和核验情况`,
外加论文题名一致性检查(防顶替)。

## 执行与产出

| 产出 | 类型 | 说明 |
|---|---|---|
| `AI工具使用详情.pdf` | 支撑材料 | 四节结构;由脚本按工作区指纹自适应,同一工作区重复生成逐字一致 |
| `paper/main.tex` 声明段 | 正文产物 | 脚本插入/校验,禁止手工改写 |
| `--check-only` 退出码 | 门禁信号 | 非 0 即未与当前工作区同步,阻断交付 |

Attribution

FOURTEEN1416FOURTEEN1416
View sourceSee grades on GitHubMore from FOURTEEN1416 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →