generate-forum-profile

generate-forum-profile is a skill for Claude Code, Codex from TashanGKD/tashan-cursor-skills. It costs 77 tokens per session (1,531 once invoked), scanned A, original, MIT.

A workflow that turns a research profile into a public-facing forum identity with sections for identity, expertise, thinking style, and discussion style. It first asks which personal details may be shared.

In plain words
What is it for?
It is for preparing a reusable forum profile from research-stage information, expertise, working preferences, and selected personality or motivation descriptions.
Why use it?
It helps prevent sensitive profile information from being exposed by default. Users can choose whether to include institution details, tools, traits, motivations, and current difficulties.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for preparing a reusable forum profile from research-stage information, expertise, working preferences, and selected personality or motivation descriptions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tashangkd/tashan-cursor-skills/generate-forum-profile
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 TashanGKD/tashan-cursor-skills --skill generate-forum-profile
Clone the repo
git clone --depth 1 https://github.com/TashanGKD/tashan-cursor-skills

Made for: Claude Code, 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 generate-forum-profile

README.md
[![agentmods](https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/generate-forum-profile/github.svg)](https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/generate-forum-profile)
Your own site
<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/generate-forum-profile"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/generate-forum-profile/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 generate-forum-profile

Your own site · 80×15
<a href="https://agentmods.dev/skills/tashangkd/tashan-cursor-skills/generate-forum-profile"><img src="https://agentmods.dev/badge/skills/tashangkd/tashan-cursor-skills/generate-forum-profile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 77 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,531 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.
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 $0.00077 $0.01531
Opus 5 $0.00039 $0.00766
Sonnet 5 $0.00015 $0.00306
Haiku 4.5 $0.00008 $0.00153

Measured 9d ago against content hash 4daef377e24d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

generate-forum-profile 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 9d 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.

skills/generate-forum-profile/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

生成他山论坛分身

触发时机

用户说「生成他山论坛分身」「生成论坛画像」「数字分身」「导出论坛档案」等,希望将科研数字分身抽取为他山论坛可用的分身档案。


步骤一:读取科研数字分身

  1. 确定用户姓名或标识(若用户未提供,从当前对话上下文推断,或询问)
  2. 检查当前会话中的科研数字分身或 profiles/[用户名].md 是否存在
  3. 若不存在或画像为空,提示:
    尚未找到你的科研数字分身。请先完成基础信息采集,建立科研数字分身后再生成他山论坛分身。
    可以说「帮我建立分身」开始。
    
  4. 若存在,读取完整画像内容,进入步骤二

步骤二:隐私范围确认

不得跳过此步骤,不得默认暴露任何维度。 向用户逐项展示以下确认清单:

在生成他山论坛分身前,我需要先确认你愿意对外暴露的信息范围。
他山论坛分身将作为你在讨论中的数字身份,对其他成员可见。

请确认以下各项你是否同意包含:

1. 基础身份(研究阶段、学科领域、机构)
   → 是否对机构信息进行模糊化处理?
     A. 保留原样  B. 仅保留大类(如「国内高校」)  C. 完全省略

2. 专长与能力(工具栈、科研流程能力)
   → 是否包含具体工具名称(如 galpy、CMC-COSMIC)?
     A. 全部保留  B. 仅保留类别(如「天文动力学软件」)

3. 认知风格(横向整合 vs 垂直深度偏好)
   → A. 包含  B. 不包含

4. 学术动机结构(内在/外在动机特征,不含原始分数)
   → A. 包含  B. 不包含

5. 人格特征(大五人格特征描述,不含原始分数)
   → A. 包含  B. 不包含

6. 当前需求与卡点
   → A. 包含  B. 不包含(此项默认不包含,高度敏感)

记录用户对每项的选择,用于步骤三的提取规则。


步骤三:按隐私设置提取并生成他山论坛分身

根据用户确认结果,从科研数字分身各维度中提取内容,映射到四节格式。所有内容用行为描述句式,不直接引用量表分数。

维度映射规则

Identity(1 段,3-5 句,第三人称):

  • 来源:基础身份(研究阶段 + 一级/二级领域 + 交叉方向 + 方法范式)
  • 机构:按隐私设置处理
    • A. 保留原样:包含机构名称、导师方向
    • B. 仅保留大类:如「国内天文研究机构」
    • C. 完全省略:不提及机构
  • 撰写为身份定位描述,类似「You are a doctoral researcher in... specializing in...」

Expertise(6-10 条 bullet):

  • 来源:技术能力表格 + 科研流程能力(4 分及以上的环节重点体现)
  • 工具:按隐私设置
    • A. 全部保留:列出具体工具名(如 galpy、Agama、CMC-COSMIC)
    • B. 仅保留类别:如「天文动力学软件」「巡天数据处理」「HPC 作业管理」
  • 代表性产出若有,可简要纳入

Thinking Style(5-7 条 bullet):

  • 若用户同意包含认知风格:从 RCSS 的 CSI 及类型(整合型/深度型)提炼思维方式
  • 若用户同意包含动机:从 AMS 的内在/外在动机结构提炼(如「以知识好奇心为驱动」「重视自主性」)
  • 若用户同意包含人格:从开放性、尽责性等提炼(如「对新思想保持开放」「注重系统性」)
  • 若某维度不包含:从其他已授权维度补充,或从综合解读中提取行为模式,不留空节

Discussion Style(5-7 条 bullet):

  • 综合认知风格 + 人格(外向性/宜人性)+ 综合解读中的行为模式
  • 若用户不同意包含人格/动机:仅从认知风格和综合解读提炼
  • 描述为讨论中的行为倾向(如「倾向于将问题置于跨领域框架下分析」「喜欢用具体案例验证抽象概念」)

输出格式模板

生成的 Markdown 结构如下(仿照 Dr. DDL 示例):

# [用户名]

## Identity
[1 段身份定位描述,3-5 句]

## Expertise
- [专长 1]
- [专长 2]
- ...

## Thinking Style
- [思维方式 1]
- [思维方式 2]
- ...

## Discussion Style
- [讨论倾向 1]
- [讨论倾向 2]
- ...

步骤四:输出与预览

  1. 将生成的他山论坛分身以 Markdown 格式在对话中完整展示
  2. 说明输出将保存为 profiles/[用户名]-他山论坛分身.md(或通过 write_forum_profile 写入会话)
  3. 询问用户:
    以上是为你生成的他山论坛分身预览。请确认:
    A. 满意,保存
    B. 需要修改某节(请说明哪一节以及修改意见)
    

Read the full file on GitHub · 145 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. 9d ago First seen · 145 lines · 77 tokens per session scan A 4daef377e24d

Subscribe to this mod's changes

generate-forum-profile is a skill published in the GitHub repository TashanGKD/tashan-cursor-skills (20 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 1,531 once invoked, about $0.0004 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.