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/ali66611/glskill/gl-thesis-topicnpx skills add Ali66611/glskill --skill gl-thesis-topicgit clone --depth 1 https://github.com/Ali66611/glskillWrote 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/ali66611/glskill/gl-thesis-topic)<a href="https://agentmods.dev/skills/ali66611/glskill/gl-thesis-topic"><img src="https://agentmods.dev/badge/skills/ali66611/glskill/gl-thesis-topic.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 | $0.00152 | $0.02042 |
| Opus 5 | $0.00076 | $0.01021 |
| Sonnet 5 | $0.00030 | $0.00408 |
| Haiku 4.5 | $0.00015 | $0.00204 |
Grade A, and why
gl-thesis-topic 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GL 论文定题 Skill
核心目标
不要以“生成更多题目”为目标。先筛掉不能写的题目,再留下能落地的题目。
把论文选题当作一组判断,而不是标题润色:判断学历标准、专业匹配、变量衡量、数据可得、方法难度、现实逻辑和完成能力。
始终遵循:
先场景,后方向;
先证据,后标题;
先数据可得,再谈创新。
硬规则
- 区分学历标准:本科重点是规范完成;硕士重点是边际贡献、识别可信和盲审安全;期刊选题还受目标期刊、作者积累、数据质量和审稿偏好影响,不在本 Skill 中完整展开。
- 方向不是题目,热词不是变量:不得把“数字经济”“新质生产力”“绿色金融”“人工智能”“数据资产入表”等方向词直接当作完整题目或默认可测变量。题目至少要明确 X、Y、研究对象、数据来源和方法路线。
- 执行掐头去尾:去掉文献拥挤、组合直接、撞题风险高的“大肉题”;去掉概念拼接、因果链过远、变量不可测、数据难拿的“脑洞题”;只保留有热点、有文献、有变量、有数据、有微创新且普通学生能完成的中间层题目。
- 宏观热词不得凭感觉降维:先核验 CNKI 经管领域硕博论文是否已将热词变量化,并检查衡量方式、指标体系和数据来源。若已有可靠变量化证据,可保留为 X 或 Y;若没有,再拆解内涵并寻找可衡量切口。不得用哲学、马克思主义、思想政治或纯政策阐释类论文作为核心变量衡量依据。
- 主动核验:能查就实际查,不把本可完成的检索甩给用户。不能访问 CNKI、数据库或学术检索工具时,明确写明:
待核验:当前环境无法完成该项检索,因此该判断不能作为最终定题依据。 - 不得编造:不得编造文献、题名、作者、检索结果、数据库字段、变量口径、数据权限或统计结果。搜索摘要只能作为发现线索,正式判断要尽量回到论文详情、数据库说明或一手来源。政策年份、数据库字段、有效样本数量和已有文献结论等可核查事实,未经当前检索不得写成已确认事实。
- 按固定优先级推荐:
可行性 > 相关性 > 创新性。不得为了“新”牺牲数据可得、专业匹配或方法可执行性。
核心判断是:
普通学生最好的题目,不是最前沿,也不是最复杂,而是新一点、热一点、还能做出来。
执行流程
Step 1:判断用户场景
先识别以下信息:
- 学历:本科或硕士。
- 专业:会计、财务管理、金融、工商管理、经济学、国际贸易、公共管理等。
- 用途:毕业论文、课程论文、开题报告或研究方案。
- 方法能力:是否会 Stata、面板数据及 DID、IV、PSM 等方法。
- 数据条件:是否能使用 CSMAR、Wind、CNRDS、EPS、CNOpenData、统计年鉴等。
- 时间限制:是否需要快速完成。
信息不足时最多询问 5 个关键问题。若可以合理默认,先给初步判断,并把不确定项标记为“待核验”。
Step 2:按学历分流
- 本科任务:读取 references/undergraduate-standard.md。
- 硕士任务:读取 references/master-standard.md。
- 期刊任务:说明本 Skill 只能做初步方向判断;若用户给出目标期刊和发表要求,可据此补充边界分析,但不得假装完成完整投稿策划。
Step 3:寻找方向
读取 references/direction-sources.md,根据用户材料从国社科项目、期刊选题或专题征稿、数据库新变量以及用户直接给出的方向中提取候选切口。
Step 4:生成候选题
通常生成 5—10 个候选题;若用户只要求判断一个既有题目,则围绕该题给出保留、收窄、替换或放弃的判断。
每个候选题必须同时给出:
- X 与 Y。
- 研究对象和数据层级。
- 数据来源初判。
- 方法路线初判。
- 适合本科还是硕士。
- 主要风险。
- 核验状态。
不得只给标题。
Step 5:主动核验
读取并执行 references/verification-protocol.md。至少检查 CNKI 撞题、马甲词、宏观热词变量化、变量衡量、数据可得性、专业相关性、现实逻辑和掐头去尾结果。
把核验状态统一标为:
已核验:已查看足以支持判断的一手或权威来源。部分核验:完成部分检索,但仍有关键证据缺口。待核验:当前无法完成检索或没有可靠证据。
What ships with it
6 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.
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 · 128 lines · 152 tokens per session scan A 80733c6d43c4
gl-thesis-topic is a skill published in the GitHub repository Ali66611/glskill (6 stars, last pushed 1mo ago), licensed MIT. It adds 152 tokens to every session and 2,042 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 2026-08-31.
Other skills, from other repositories
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.
data-management-plan
Draft a funder-compliant Data Management Plan (NSF DMP, NIH DMS Policy 2023, ERC, Horizon Europe) by composing the confidential-data and environment-capture primitives. Sections cover data description, formats/metadata, storage/backup, access/sharing, preservation/archiving, and roles. Use when user says "data…
seven-pass-review
Mechanize Pattern 15 — the seven-pass adversarial review protocol for academic manuscripts. Spawns 7 forked subagents in parallel (abstract, intro, methods, results, robustness, prose, citations), then synthesizes a prioritized revision checklist. Use for submission-ready or R&R-stage papers where single-pass review…
slide-excellence
Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for…
triage-inbox
Triage academic email and calendar (Gmail / Google Calendar via the session's MCP) into a prioritized digest plus a referee-obligations tracker — classifying referee requests, R&R and editor correspondence, co-author threads, seminar and conference invites, and grant/admin deadlines, and proposing a human-gated action…