Token导航 LogoToken导航

Agent Skill · 研究检索

academic-letter-architect(学术字母建筑师)

academic-letter-architect 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

academic-letter-architect 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 38,381。

总安装 1,567周安装 64GitHub Stars 85下载 507核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:academic-letter-architect(学术字母建筑师)
来源仓库:https://github.com/lyndonkl/claude
仓库路径:skills/academic-letter-architect
安装命令:
npx skills add https://github.com/lyndonkl/claude --skill academic-letter-architect
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/lyndonkl/claude --skill academic-letter-architect

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

学术信笺架构师用于撰写符合学术规范的推荐信,强调具体事例与量化成果。适用于申请研究生、奖学金或教职时,需要专业推荐信的场景。能根据候选人特质匹配院校要求,提供结构清晰、语言得体的推荐信模板。需配合具体案例和背景信息使用,建议提前准备候选人的成就清单。安装前请确认是否具备访问外部文档及生成文本内容的权限。

来源仓库内路径:skills/academic-letter-architect

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/lyndonkl/claude --skill academic-letter-archit…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

academic-letter-architect 怎么安装?

在终端执行 npx skills add https://github.com/lyndonkl/claude --skill academic-letter-architect。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

academic-letter-architect 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

academic-letter-architect 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

academic-letter-architect 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

academic-letter-architect 用的人多吗?

公开数据是累计安装 1,567 次,近一周安装 64 次,下载 507 次,GitHub 85 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

academic-letter-architect 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
academic-letter-architect

学术字母建筑师 · 本页

1,56785只读MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Academic Letter Architect

Table of Contents

Related skills (use instead for):

  • Personal statements: career-document-architect
  • Cover letters to journals: scientific-email-polishing
  • Grant proposals: grant-proposal-assistant

Core Principles

1. Show, don't tell: Concrete examples beat adjectives

  • ❌ "She is brilliant"
  • ✅ "She independently developed a novel assay that our lab now uses routinely"

2. Comparisons give context: Readers need reference points

  • ❌ "He is a strong student"
  • ✅ "He is among the top 5% of graduate students I've mentored in 20 years"

3. Enthusiasm is evidence: Tone conveys conviction

  • Lukewarm letters damage candidates
  • Genuine enthusiasm must come through

4. Address what matters: Match content to opportunity

  • Academic job: Research potential, teaching, mentorship
  • Industry job: Practical skills, teamwork, adaptability
  • Award: Specific achievements matching award criteria

Workflow

Copy this checklist and track your progress:

Letter Architect Progress:
- [ ] Step 1: Gather context (candidate, opportunity, relationship)
- [ ] Step 2: Collect evidence (specific examples, achievements)
- [ ] Step 3: Draft opening (credibility, relationship, expectation)
- [ ] Step 4: Build body (evidence paragraphs, comparisons)
- [ ] Step 5: Craft closing (strong endorsement, availability)
- [ ] Step 6: Calibrate tone (enthusiasm level, superlatives)
- [ ] Step 7: Final polish (length, format, signature)

Step 1: Gather Context

Identify: Who is the candidate? What opportunity? Your relationship (advisor, collaborator, instructor)? How long have you known them? In what capacity? See resources/methodology.md for information checklist.

Step 2: Collect Evidence

List 3-5 specific examples demonstrating excellence: Research achievements, intellectual contributions, professional qualities, overcoming challenges. Quantify where possible. See resources/methodology.md for evidence types.

Step 3: Draft Opening

Establish your credibility (position, experience). State relationship to candidate (role, duration, context). Set expectation (strong recommendation signal). See resources/template.md for opening structure.

Step 4: Build Body

Structure evidence into 2-4 paragraphs covering different dimensions (research, intellect, character). Include comparative statements ("top 5%", "best I've seen"). Connect evidence to opportunity requirements. See resources/template.md for paragraph templates.

Step 5: Craft Closing

Provide unambiguous endorsement statement. Offer availability for follow-up. Include professional signature with title/contact. See resources/template.md for closing structure.

Step 6: Calibrate Tone

Ensure enthusiasm matches actual assessment. Check superlative use (too many dilutes impact). Verify letter reads as advocacy, not obligation. See resources/methodology.md for calibration guide.

Step 7: Final Polish

Check length (typically 1-2 pages). Ensure formal formatting. Verify all specific claims are accurate. Validate using resources/evaluators/rubric_academic_letter.json. Minimum standard: Average score ≥ 3.5.

Letter Structure

Opening Paragraph

Purpose: Establish credibility and relationship

Elements:
1. Your identity and position
2. How you know the candidate (role, context)
3. Duration of relationship
4. Capacity of observation (direct supervision, collaboration)
5. Clear statement of recommendation

Example: "I am writing to provide my strongest recommendation for Dr. Jane Smith for the position of Assistant Professor. As the Director of the Structural Biology Center at X University, I have had the privilege of working closely with Jane for the past four years, first as her postdoctoral mentor and subsequently as a research collaborator. During this time, I have observed her exceptional scientific abilities, intellectual creativity, and professional maturity firsthand."

Body Paragraphs

Purpose: Provide evidence-based assessment

Paragraph 1: Research/Technical Excellence

  • Specific project achievements
  • Technical skills demonstrated
  • Independent thinking
  • Problem-solving ability
  • Publications/outputs

Paragraph 2: Intellectual Contributions

  • Creativity and innovation
  • Scientific insight
  • Critical thinking
  • Ability to ask important questions
  • Conceptual contributions

Paragraph 3: Professional Qualities

  • Work ethic and reliability
  • Collaboration and teamwork
  • Communication skills
  • Mentorship of others
  • Leadership potential

Paragraph 4: Comparative Assessment

  • Direct comparison to peers
  • Ranking in your experience
  • Prediction of future success

Closing Paragraph

Purpose: Summarize and endorse

Elements:
1. Overall assessment statement
2. Specific recommendation (enthusiastic, unambiguous)
3. Prediction for future success
4. Offer of availability for follow-up
5. Professional sign-off

Example: "In summary, Jane is an outstanding scientist with exceptional research abilities, intellectual depth, and professional maturity. I give her my highest and most enthusiastic recommendation without reservation. She will make an excellent faculty member and I am confident she will develop an impactful, independent research program. Please do not hesitate to contact me if you require any additional information."

Tone and Language

Enthusiasm Levels

Highest ("absolutely top"):

  • "My strongest possible recommendation"
  • "Without reservation"
  • "The best I have mentored in 20 years"
  • "Truly exceptional"

Strong ("top tier"):

  • "Highly recommend"
  • "Outstanding"
  • "Top 5-10% of students"
  • "Excellent"

Moderate ("good but not stellar"):

  • "I recommend"
  • "Strong"
  • "Above average"
  • "Solid"

Lukewarm (damaging):

  • "I am pleased to recommend"
  • "Adequate"
  • "Met expectations"
  • "Did fine work"

Comparative Statements

Strong comparisons:

  • "Among the top 2-3 students I've trained in my career"
  • "The most creative thinker I've mentored"
  • "Will outperform 95% of candidates you consider"
  • "Best [X] I've seen in [Y] years"

Weak comparisons (avoid):

  • "One of our better students"
  • "Above average"
  • "Compares favorably to peers"

Specificity Examples

Vague (Weak)Specific (Strong)
"Productive researcher""Published 5 first-author papers including 2 in Nature journals"
"Good communicator""Regularly invited to present at lab meetings and gave a talk at the Gordon Conference"
"Works well with others""Mentored 3 undergraduate students, all of whom went to top graduate programs"
"Technically skilled""Independently established our lab's CRISPR screening platform"

Guardrails

Key requirements:

  1. Truthfulness: Only write what you genuinely believe. Dishonest letters harm candidates and your reputation.
  2. Evidence-based: Every claim should have a supporting example. "Smart" means nothing without evidence.
  3. Appropriate comparison: Compare to relevant reference class (other postdocs, not all scientists ever).
  4. Match content to opportunity: Emphasize research for academic jobs, practical skills for industry.
  5. Candidate voice preservation: Reflect the candidate's actual achievements, not fabricated ones.
  6. Cultural awareness: US letters are more superlative than other cultures. Calibrate appropriately.

Common pitfalls:

  • ❌ Lukewarm language: "Adequate", "met expectations" - these hurt
  • ❌ No comparisons: Reader can't calibrate "excellent" without context
  • ❌ Generic adjectives: "Brilliant, creative, hardworking" with no evidence
  • ❌ Too short: Brief letters signal lack of enthusiasm
  • ❌ Wrong focus: Research focus for teaching position
  • ❌ Damning with faint praise: "Did everything asked" sounds minimal

Quick Reference

Key resources:

Letter length guidelines:

  • Graduate school: 1-1.5 pages
  • Faculty position: 1.5-2 pages
  • Award nomination: 1-2 pages (check requirements)
  • Brief reference: 0.5-1 page

Information to gather from candidate:

  • CV/resume
  • Personal statement or cover letter
  • Position/opportunity description
  • Specific points they'd like emphasized
  • Any concerns to address proactively

Time estimates:

  • Strong letter (well-known candidate): 1-2 hours
  • Standard letter (good candidate): 30-60 minutes
  • Brief reference: 15-30 minutes

Inputs required:

  • Candidate information (CV, statement)
  • Opportunity details (position, institution)
  • Your relationship context (duration, capacity)
  • Specific examples of excellence

Outputs produced:

  • Complete recommendation letter
  • (Optional) Commentary on strength calibration

平台分布

Claude Code

26.52%
按下载量换算134

Gemini CLI

24.82%
按下载量换算126

Antigravity

18.92%
按下载量换算96

github-copilot

11.39%
按下载量换算58

OpenCode

7.82%
按下载量换算40

Cursor

3.46%
按下载量换算18

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

继续浏览同类 Skills