FreePublished on GitHub

llm-intern-skill

Use when polishing, diagnosing, tailoring, or exporting resumes for LLM, RAG, Agent, Agentic RL, post-training, pretraining, AIGC, search/ranking, multimodal, AI backend, or LLM algorithm internships from raw resume text, a materials folder, and/or a target job description. Audits evidence, maps JD fit, enforces truth boundaries, writes polished and targeted resumes, generates interviewer-style grilling questions, answer cards, evidence-upgrade plans, and optional open-source project recommendations without fabricating experience.

The English summary is being prepared. Showing the original description.

wanyichen06/LLMInternSkill

See how to install

Files included (118)

SKILL.md5.0 KB
.gitattributes117 B
.gitignore585 B
agents/openai.yaml310 B
docs/e1b5c6a672b04d5a9f8a3c7e2d1a0b49.txt33 B
docs/frontier-training-jd-notes.md4.0 KB
docs/index.html9.9 KB
docs/robots.txt87 B
docs/sitemap.xml219 B
evals/manual-eval-suite.md5.3 KB
examples/agent-rag-input.md1.3 KB
examples/agent-rag-output.md2.7 KB
examples/doubao-seed-final-pack.md6.0 KB
examples/doubao-seed-materials-input.md1.9 KB
examples/doubao-seed-search-ranking-jd.md3.0 KB
examples/lora-weak-metrics.md2.0 KB
examples/posttraining-agentic-rl-case.md2.4 KB
examples/project-scout-minimind.md3.2 KB
examples/project-scout-search-rerank.md2.7 KB
examples/prompt-only-downgrade.md1.8 KB
examples/resume-polish-before-after.md4.1 KB
examples/seed-resume-latex/README.md971 B
examples/seed-resume-latex/seed-topseed-resume.pdf95.5 KB
LICENSE1.0 KB
README_EN.md13.0 KB
README.md11.8 KB
references/README.md526 B
skill-references/answer-cards.md1.1 KB
skill-references/evidence-contract.md1.3 KB
skill-references/interview-grilling.md946 B
skill-references/jd-analysis.md1.8 KB
skill-references/materials-audit.md1.3 KB
skill-references/project-scout.md1.6 KB
skill-references/resume-polish.md3.0 KB
skill-references/resume-tailoring.md1.4 KB
skill-references/roles/role-agent.md1.8 KB
skill-references/roles/role-agentic-rl.md3.0 KB
skill-references/roles/role-aigc.md1.4 KB
skill-references/roles/role-backend-ai.md1.3 KB
skill-references/roles/role-llm-algorithm.md2.3 KB
skill-references/roles/role-llm-app.md1.6 KB
skill-references/roles/role-multimodal.md1.3 KB
skill-references/roles/role-posttraining.md2.8 KB
skill-references/roles/role-pretraining.md2.8 KB
skill-references/roles/role-rag.md1.9 KB
skill-references/roles/role-search-ranking.md3.0 KB
skill-references/truth-boundary.md988 B
skill-references/upgrade-plan.md853 B
templates/final-pack.md1.7 KB
templates/intake.md1.5 KB
templates/materials-folder.md1.3 KB
templates/project-search-criteria.md1.2 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/.gitignore700 B
templates/resume-latex/bill-ryan-elegant-zh_CN/avatar.jpg1.6 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/fontawesome.sty2.8 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/fontawesomesymbols-generic.tex32.5 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/fontawesomesymbols-pdftex.tex45.3 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/fontawesomesymbols-xeluatex.tex44.7 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/fonts/fontawesome-webfont.ttf138.7 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/fonts/fontawesome/opentype/FontAwesome.otf129.5 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/fonts/Main/Fontin-SmallCaps.otf28.6 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/fonts/Main/texgyretermes-bold.otf148.1 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/fonts/Main/texgyretermes-bolditalic.otf155.8 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/fonts/Main/texgyretermes-italic.otf153.0 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/fonts/Main/texgyretermes-regular.otf150.6 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/IEEEtran.bst57.8 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/latexmkrc727 B
templates/resume-latex/bill-ryan-elegant-zh_CN/LICENSE1.0 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/linespacing_fix.sty928 B
templates/resume-latex/bill-ryan-elegant-zh_CN/Makefile376 B
templates/resume-latex/bill-ryan-elegant-zh_CN/mycite.bib844 B
templates/resume-latex/bill-ryan-elegant-zh_CN/NotoSansSC_external.sty1.0 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/NotoSerifCJKsc_external.sty1.1 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/README.md9.4 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/resume_photo.tex2.9 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/resume-en_US-zh_CN.png572.8 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/resume-zh_CN.tex3.0 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/resume.cls3.2 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/resume.tex2.5 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/scripts/fontawesome_preamble.sty1.4 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/scripts/fontawesome_tail.sty46 B
templates/resume-latex/bill-ryan-elegant-zh_CN/scripts/fs_sty.py1.7 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/scripts/fs_sty.sh756 B
templates/resume-latex/bill-ryan-elegant-zh_CN/seed-topseed-resume.tex3.6 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/SOURCE.md791 B
templates/resume-latex/bill-ryan-elegant-zh_CN/zh_CN-Adobefonts_external.sty1.1 KB
templates/resume-latex/bill-ryan-elegant-zh_CN/zh_CN-Adobefonts_internal.sty1.1 KB
templates/resume-latex/bill-ryan-elegant/.gitignore662 B
templates/resume-latex/bill-ryan-elegant/avatar.jpg1.6 KB
templates/resume-latex/bill-ryan-elegant/fontawesome.sty2.8 KB
templates/resume-latex/bill-ryan-elegant/fontawesomesymbols-generic.tex32.5 KB
templates/resume-latex/bill-ryan-elegant/fontawesomesymbols-pdftex.tex45.3 KB
templates/resume-latex/bill-ryan-elegant/fontawesomesymbols-xeluatex.tex44.7 KB
templates/resume-latex/bill-ryan-elegant/fonts/fontawesome-webfont.ttf138.7 KB
templates/resume-latex/bill-ryan-elegant/fonts/fontawesome/opentype/FontAwesome.otf129.5 KB
templates/resume-latex/bill-ryan-elegant/fonts/Main/Fontin-SmallCaps.otf28.6 KB
templates/resume-latex/bill-ryan-elegant/fonts/Main/texgyretermes-bold.otf148.1 KB
templates/resume-latex/bill-ryan-elegant/fonts/Main/texgyretermes-bolditalic.otf155.8 KB
templates/resume-latex/bill-ryan-elegant/fonts/Main/texgyretermes-italic.otf153.0 KB
templates/resume-latex/bill-ryan-elegant/fonts/Main/texgyretermes-regular.otf150.6 KB
templates/resume-latex/bill-ryan-elegant/IEEEtran.bst57.8 KB
templates/resume-latex/bill-ryan-elegant/latexmkrc727 B
templates/resume-latex/bill-ryan-elegant/LICENSE1.0 KB
templates/resume-latex/bill-ryan-elegant/Makefile376 B
templates/resume-latex/bill-ryan-elegant/mycite.bib844 B
templates/resume-latex/bill-ryan-elegant/README.md2.5 KB
templates/resume-latex/bill-ryan-elegant/resume_photo.tex2.9 KB
templates/resume-latex/bill-ryan-elegant/resume.cls3.2 KB
templates/resume-latex/bill-ryan-elegant/resume.tex2.5 KB
templates/resume-latex/bill-ryan-elegant/scripts/fontawesome_preamble.sty1.4 KB
templates/resume-latex/bill-ryan-elegant/scripts/fontawesome_tail.sty46 B
templates/resume-latex/bill-ryan-elegant/scripts/fs_sty.py1.7 KB
templates/resume-latex/bill-ryan-elegant/scripts/fs_sty.sh756 B
templates/resume-latex/bill-ryan-elegant/SOURCE.md540 B
templates/resume-latex/bill-ryan-elegant/zh_CN-Adobefonts_external.sty1.1 KB
templates/resume-latex/bill-ryan-elegant/zh_CN-Adobefonts_internal.sty1.1 KB
templates/resume-latex/README.md713 B
templates/resume-polish-report.md767 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

LLMInternSkill

Use this Skill when the user wants resume polish, resume diagnosis, JD tailoring, project packaging, interview preparation, or final resume export for LLM-related internship applications.

Core rule:

Do not fabricate. Diagnose first, polish second.

Inputs

Preferred input folder:

materials/
├── target_jd.txt
├── resume.md / resume.pdf
├── projects/
├── code/
├── notes/
├── papers/
├── awards/
└── other/

If the user only provides a JD and no materials, ask the intake questions from templates/intake.md.

If the user only asks for resume polish, run a lightweight version:

raw resume line -> claim extraction -> evidence/risk check -> polished wording -> interview risk

Main Workflow

Decide the mode
- Resume polish only: use skill-references/resume-polish.md.
- JD tailoring: use skill-references/jd-analysis.md and skill-references/resume-tailoring.md.
- Full materials folder: run the complete workflow below.
- Interview prep only: use skill-references/interview-grilling.md and skill-references/answer-cards.md.
- Project Scout only: use skill-references/project-scout.md.
Read the target JD when present
- Use skill-references/jd-analysis.md.
- Detect role type: RAG, Agent, Agentic RL, post-training, pretraining, LLM app, LLM algorithm, search/ranking, AIGC, multimodal, backend AI, infra, or mixed.
- Load the matching role file under skill-references/roles/ when relevant.
Audit the materials folder when present
- Use skill-references/materials-audit.md.
- Extract projects, claims, evidence, missing evidence, and unclear ownership.
Set truth boundaries
- Use skill-references/truth-boundary.md.
- Classify content as 可以写, 谨慎写, 补证据后写, 不能写, or 无法判断.
Build the evidence contract
- Use skill-references/evidence-contract.md.
- Every strong claim needs evidence, risk, safe wording, and interview proof.
Generate polished / targeted resume
- Use skill-references/resume-polish.md for line-level polish.
- Use skill-references/resume-tailoring.md.
- Produce conservative, standard, and stronger-after-evidence bullets.
- Generate a targeted full resume draft when enough information exists.
- If the user wants a PDF-ready resume, use templates/resume-latex/bill-ryan-elegant-zh_CN/resume-zh_CN.tex as the LaTeX base.
Generate interview grilling
- Use skill-references/interview-grilling.md.
- Ask interviewer-style questions based on JD gaps and resume claims.
Generate answer cards
- Use skill-references/answer-cards.md.
- For high-risk questions, produce dangerous / passable / strong answers.
Create upgrade plan
- Use skill-references/upgrade-plan.md.
- Split into half-day, 1-day, 3-day, and 1-week evidence upgrades.
Optional Project Scout

Use skill-references/project-scout.md when the user's evidence is weak or they ask for projects to learn.
Recommend projects only as learning/reproduction/modification opportunities, not as fake experience.

Assemble final pack

Use templates/final-pack.md.

Output Files

When writing files, prefer this structure:

output/
├── 01_jd_analysis.md
├── 02_materials_audit.md
├── 03_truth_boundary.md
├── 04_evidence_contract.md
├── 05_resume_polish.md
├── 06_targeted_resume.md
├── 07_interview_grilling.md
├── 08_answer_cards.md
├── 09_upgrade_plan.md
├── 10_project_scout.md
└── 11_final_pack.md

If the user wants only an answer in chat, still follow the same section order.

Fit Verdict

Always give one:

strong fit
weak fit
risky fit
not recommended

Explain the verdict with:

JD must-haves.
User evidence.
Gaps.
Highest interview risk.
Fastest useful upgrade.

Non-Negotiables

Never invent internships, production status, metrics, user scale, model training, ranking gains, or ownership.
Do not write "主导" when evidence only supports "参与".
Do not write "上线" when evidence only supports demo, local run, or internal trial.
Do not write open-source learning as work experience unless the user actually reproduced, modified, and documented it.
If materials are insufficient, ask questions or produce a conservative report instead of polished fiction.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Report a problem with this skill

Install

Install with a command

npx skills add https://github.com/wanyichen06/LLMInternSkill --skill llm-intern-skill

Paste it into your terminal and run it (requires Node.js). You can choose which agents to install it for, such as Claude Code or Codex.

Ask your agent

Please install the following Agent Skill.
https://github.com/wanyichen06/LLMInternSkill

First review SKILL.md and the bundled files and confirm there is nothing suspicious (such as sending data externally or reading credentials). Then place it in ~/.claude/skills/llm-intern-skill/ for Claude Code, or ~/.agents/skills/llm-intern-skill/ for Codex.

Send this text to Claude Code or Codex as is. It checks the contents before installing.

View source on GitHub

Repository: wanyichen06/LLMInternSkill
Stars: 327
Forks: 15
Category: Data & AI
License: MIT
Original language: Chinese
Last updated: Aug 4, 2026

A skill is a set of instructions and scripts for an agent. cccskills does not guarantee that skills are safe. Review the contents before you install.