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 TashanGKD/tashan-cursor-skills --skill generate-ai-memory-promptgit clone --depth 1 https://github.com/TashanGKD/tashan-cursor-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/tashangkd/tashan-cursor-skills/generate-ai-memory-prompt)<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/generate-ai-memory-prompt"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/generate-ai-memory-prompt/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/tashangkd/tashan-cursor-skills/generate-ai-memory-prompt"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/generate-ai-memory-prompt.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00061 | $0.02121 |
| Opus 5 | $0.00030 | $0.01060 |
| Sonnet 5 | $0.00012 | $0.00424 |
| Haiku 4.5 | $0.00006 | $0.00212 |
Grade A, and why
generate-ai-memory-prompt 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 8d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
生成 AI 记忆提取提示词
触发时机
此 Skill 在以下两种场景被调用:
- 新建科研数字分身:在
collect-basic-info流程开始时,询问用户是否已使用过带记忆功能的 AI(如 ChatGPT、Claude 等),如有则先运行此 Skill - 已有数字分身:用户主动说「从 AI 记忆导入」「根据 AI 记忆丰富画像」「我有 ChatGPT 记忆」等
步骤一:判断画像状态,确定提示词类型
不询问用户使用哪个 AI 工具。提示词对所有 AI 平台(ChatGPT、Claude、Gemini 等)通用。
读取当前画像(若存在),判断哪些维度已有数据、哪些为空白:
| 维度 | 判断标准 |
|---|---|
| 基础身份 | 研究阶段、领域、机构是否已填写 |
| 能力 | 技术能力表格是否有内容;科研流程评分是否有分数 |
| 当前需求 | 三个需求子字段是否有内容 |
| 认知风格(RCSS) | CSI 是否有数值 |
| 学术动机(AMS) | 各维度得分是否有数值 |
| 人格(Mini-IPIP) | 各维度得分是否有数值 |
- 新用户(无画像):所有维度均需提取,生成「全量提示词」
- 已有部分数据:仅针对空白维度生成「补充提示词」,已有数据的维度仍列出以供 AI 做一致性参照
步骤二:生成结构化提示词
根据上一步的判断,从以下模块中选取相关部分,组合成完整提示词。
输出格式要求(必须遵守):
- 先写一句引导语:「请将下方代码块中的提示词复制后,依次粘贴到你所使用的 AI(如 ChatGPT、Claude、Gemini 等)的对话框中发送。」
- 紧接着用 markdown 代码块(```markdown ... ```)包裹完整提示词,使提示词单独成块,方便用户一键复制。
- 代码块下方再附使用说明(步骤三的内容)。
提示词框架(按需组合各模块)
【科研数字分身信息提取请求】
你好!我正在使用一个科研数字分身系统(他山数字分身系统)来记录和分析我的科研状态。
请根据你对我的了解,**依次回答**以下问题。
⚠️ 重要说明:
1. 请仅根据我们真实对话中已出现的信息作答,严禁推测或捏造
2. 如果某项你没有足够的记忆依据,请直接写「记忆不足,无法确认」
3. 所有信息将由我本人核对后才会写入画像,你的回答只作为参考
4. 请尽量保留我在对话中的原话(verbatim),便于核对来源
---
[根据需要插入以下模块]
模块 A:基础身份(若该维度为空白则包含)
【模块 A:基础身份】
请根据你对我的了解,**依次回答**以下问题(每项用1-2句话,不确定则写"记忆不足"):
A1. 我目前处于哪个研究阶段?(博士生 / 博士后 / 青年教师 / PI / 其他)
A2. 我的主要研究领域是什么?(一级学科 + 具体方向)
A3. 我主要采用哪种研究方法?(实验法 / 理论推导 / 计算建模 / 数据驱动 / 质性 / 混合)
A4. 我所在的机构是哪里?导师或团队研究方向是什么?
A5. 我的学术合作圈大概是什么情况?
模块 B:能力(若该维度为空白则包含)
【模块 B:科研能力】
请根据你对我的了解,**依次回答**以下问题:
B1. 我主要使用哪些编程语言或科研工具?熟练程度如何?
B2. 我是否有代表性的学术产出(论文、开源项目、工具包等)?如有请简述。
B3. 在以下6个科研流程环节中,你观察到我哪些比较强、哪些相对薄弱?
- 问题定义
- 文献整合
- 研究方案设计
- 实验/计算执行
- 论文写作
- 项目与时间管理
(请用"较强"/"一般"/"较弱"/"记忆不足"作答)
模块 C:当前需求(若该维度为空白则包含)
【模块 C:当前需求】
请根据你对我最近对话的了解,**依次回答**以下问题:
C1. 我最近花费最多精力的事情是什么?(包括科研以外的事务也可以提)
C2. 我最近提到过哪些困扰、卡点或让我觉得"推不动"的事情?
C3. 我最近是否表达过"最想改变"或"最想突破"某件事?如有,是什么?
⚠️ 当前需求是高度个人化的信息,请格外审慎,仅基于我明确表达过的内容作答。
模块 D:认知风格参照(若 RCSS 为空白则包含)
【模块 D:认知风格参照】
以下是关于科研认知风格的两种类型描述,请根据你对我的了解,
说明你观察到的倾向(不要求精确打分,只需定性描述):
- 横向整合型:喜欢跨领域连接,善于整合不同方法和理论,享受"拼图式"思维
- 垂直深度型:喜欢深挖一个问题,追求单一领域的极致精通,享受"打井式"钻研
D1. 在我们的对话中,我更像哪种类型?
D2. 有没有具体的例子或话语能支持你的判断?
⚠️ 这不是量表测量,只作为参考,最终数据以我自填量表为准。
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.
- 8d ago First seen · 191 lines · 61 tokens per session scan A a0a748bf28f5
generate-ai-memory-prompt is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 61 tokens to every session and 2,121 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
cognitive-consistency-check
A full validation of a structured knowledge system against ten consistency rules, including existing references, declared relationships, document status, and non-contradictory content.
cognitive-extract-principle
A Chinese-language skill for finding recurring patterns across separate notes and turning them into candidate underlying principles.
cognitive-update-knowledge
A controlled workflow for updating a core knowledge document, including impact analysis, backups, consistency checks, and related record updates.
cognitive-self-reflect
A guided self-reflection tool that turns personal observations into written patterns and compares them with earlier reflections over time.
cognitive-attend
A signal detector for finding notable ideas in conversation. It looks for insights, connections between topics, contradictions, reflections, and evidence supporting a principle.
cognitive-background-synthesizer
A background process that looks for connections between recent notes and completed tasks, then writes possible patterns into a system log.