A skill your agent uses when the user asks to prepare a PhD interview deck, professor meeting slides, research presentation PPT, slide-by-slide speaking notes, or interview visuals.

MITAuto-check passedDocuments & Office

Install Interview Ppt

skills CLI
$ npx skills add xujingchen1996/research-app-toolkit --skill interview-ppt -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install xujingchen1996/research-app-toolkit interview-ppt --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/xujingchen1996/research-app-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/codex/skills/interview-ppt .claude/skills/interview-ppt && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
interview-ppt
GitHub stars
134
Token cost
~1.8k tokens
SKILL.md length
970 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user asks to prepare a PhD interview deck, professor meeting slides, research presentation PPT, slide-by-slide speaking notes, or interview visuals.

  • Works in 5 steps: Build the Overall Deck Strategy First → Rebuild Project Material Into Meeting… → Generate Slide Content → …
  • The user asks to prepare a PhD interview deck
  • SKILL.md covers Preconditions, Language Rules, Optional Linkage: Life Science… and Determine the Deck Mode First, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Interview Ppt is an agent skill from xujingchen1996/research-app-toolkit. Use when the user asks to prepare a PhD interview deck, professor meeting slides, research presentation PPT, slide-by-slide speaking notes, or interview visuals. Structure CV, project files, and supervisor fit into an interview-ready academic deck, and generate visuals when explicitly requested.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Documents & Office, covering Slides and decks. The repository describes itself as: Research Application Toolkit - Claude Code plugin for PhD, MRes, MPhil applications. The licence is MIT.

When your agent uses it

  • The user asks to prepare a PhD interview deck
  • Professor meeting slides
  • Research presentation PPT
  • Slide-by-slide speaking notes

Example prompts

  • “/interview-ppt”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Build the Overall Deck Strategy First
  2. Rebuild Project Material Into Meeting Logic
  3. Generate Slide Content
  4. Generate Speaking Notes
  5. Generate Visual Suggestions

What it can do on your machine

Read from SKILL.md and the folder at commit d84dbc0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Interview Ppt loads about 1.8k tokens when it runs. Until then it costs about 78 tokens; SKILL.md has 970 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from xujingchen1996/research-app-toolkit at commit d84dbc0, republished under its MIT licence (© xujingchen1996). 970 words, ~1,842 tokens.

Download SKILL.mdSave it as .claude/skills/interview-ppt/SKILL.md (or your agent's skills folder).
name
interview-ppt
description
Use when the user asks to prepare a PhD interview deck, professor meeting slides, research presentation PPT, slide-by-slide speaking notes, or interview visuals. Structure CV, project files, and supervisor fit into an interview-ready academic deck, and generate visuals when explicitly requested.

Interview PPT Organization

Preconditions

  • Read ../../memory.md first.
  • If cv_profile_analyzed is not complete, but the user has already provided enough materials in the current conversation, continue directly and do not block forcibly.
  • If project documents, the target professor, or the target scenario are missing, prioritize filling in the minimum necessary information.

Language Rules

  • Support three output modes: zh, en, and bilingual.
  • If the user explicitly requests English slide content or English speaking notes, prioritize the current request.
  • If not explicitly stated, read preferred_language from memory.md.
  • If the output is bilingual, default to keeping slide content in the main presentation language and do not repeat the entire deck bilingually.

Optional Linkage: Life Science Research

  • If the user is preparing an interview or professor-meeting PPT in a life sciences / biomedical direction and needs stronger scientific grounding, life-science-research can be linked first.
  • This is especially suitable for pages such as:
    • Research Fit
    • Why This Lab / Why This Professor
    • Future Directions
    • Problem Significance
  • The linkage result can help strengthen:
    • target / gene / disease / pathway background
    • current public evidence and research gaps
    • dataset / omics / clinical evidence context
    • the transition from existing projects to future research directions
  • If the user only wants general expression optimization, layout simplification, or slide-by-slide speaking notes and already has complete slide text, do not trigger that linkage.

Determine the Deck Mode First

Determine and narrow the deck type according to the scenario:

  • meeting: outreach, first meeting, professor communication
  • formal-interview: PhD interview, scholarship interview, panel interview
  • project-presentation: focused explanation of 1 to 2 projects

If the user does not specify it, default to formal-interview.

Visual Generation Mode

Before organizing the deck, first determine visual mode. The priority order is:

  1. explicit switches in the current request
  2. explicit natural-language requests in the current request
  3. the default fallback

Supported explicit switches:

  • visuals:on
  • visuals:off
  • with-visuals
  • no-visuals

Rules:

  • If the user explicitly says things like "also generate the visuals", "make the figures too", or "create images for every slide", set it to on.
  • If the user explicitly disables image generation, treat it as off even if visuals are mentioned elsewhere in the context.
  • If there is no explicit switch and no clear request, default to off.
  • When visual mode is on, if the current host provides image generation / image-gen capability, generate visuals directly; if the current host does not have that capability, fall back to image prompts and layout suggestions.
  • Prioritize reusing the user's existing images, screenshots, charts, or project materials, rather than regenerating unconditionally.
  • Unless the user explicitly asks for visuals on every slide, by default generate visuals only for the 1 to 3 highest-value slides.

Workflow

1. Build the Overall Deck Strategy First

Prioritize confirming:

  • target professor / program
  • interview language
  • the strongest 2 to 4 project or experience blocks
  • whether the user only wants slide content, or also wants speaking notes / visuals
  • whether the current visual mode is on or off

When outputting, prioritize a high-information-density, low-redundancy academic meeting structure rather than CV-style slide flipping.

Common page order:

  • Who I Am
  • Awards / Skills
  • Research & Project Experience
  • Teaching / Industry Experience
  • Research Fit
  • Potential PhD Directions
  • Closing / Q&A
2. Rebuild Project Material Into Meeting Logic

Do not mechanically reuse the original project-document structure of background / aim / data / summary.

Prioritize restructuring into forms that fit a meeting better, for example:

  • Objective / Process / Outcome
  • Problem / Method / Result
  • Goal / Key Design / What I Learned

If the user wants it to be easier to present orally, prioritize:

  • 2 objectives per project
  • 1 slide per objective
  • each slide should clearly explain what was done, how it was done, and what results were achieved
Show full SKILL.md (378 more words)Show less
3. Generate Slide Content

For each page, output by default:

  • slide title
  • English bullets that can be directly pasted into the PPT
  • add one layout suggestion when necessary

Style requirements:

  • academic
  • concise
  • easy to deliver orally
4. Generate Speaking Notes

If the user wants a spoken script, default to short English speaking notes:

  • about 20 to 40 seconds per slide
  • simple sentences
  • suitable for professor meetings
  • avoid over-decoration
5. Generate Visual Suggestions

When a page needs visuals and visual mode is off, prioritize providing:

  • a suitable figure type
  • an image generation prompt
  • a simple flowchart / structure diagram suggestion

When visual mode is on:

  • if the host supports image generation, generate images directly
  • if the host does not support it, output reusable image prompts and page placement suggestions
  • by default, prioritize project explanation pages, system structure pages, process pages, and research-fit transition pages

For project pages, prioritize:

  • flowcharts
  • module relationship diagrams
  • technical highlight diagrams
  • scenario concept diagrams

Research Fit Page

If the user requests a page matching the professor's research direction:

  1. first extract the professor's research themes
  2. then extract the natural connection points in the user's background
  3. avoid vague praise
  4. make the transition from "past experience -> future research direction" feel natural

Future Directions Page

If the user requests future research interests:

  • do not provide only a keyword list
  • prioritize outputting 2 to 3 mini-proposals

Each direction should include as much as possible:

  • direction title
  • short problem definition
  • possible methods

If the user wants it shorter, compress it into:

  • one line for the direction
  • one line for methods

Output Priority

Output high-value content in the following order:

  1. overall deck outline
  2. final slide text
  3. speaking notes
  4. generated images when visual mode is on, otherwise visual suggestions

If the user already has an existing PPT, prioritize revising only the specified pages rather than rebuilding the whole deck.

Constraints

  • Do not turn the PPT into long document paragraphs.
  • Do not directly flatten the CV into bullets.
  • Do not fabricate papers, methods, results, datasets, or professor interests.
  • When the professor's current research direction is involved, prioritize verifying the latest public information.
  • The whole deck should lean toward meeting presentation rather than thesis-defense style.
  • Do not generate decorative images unrelated to the explanatory logic just for appearance.

© xujingchen1996, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in codex/skills/interview-ppt of xujingchen1996/research-app-toolkit.

Open the folder on GitHubat commit d84dbc0

Compare with similar skills

Interview Ppt next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Interview Ppt compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Interview Ppt this skillxujingchen1996/research-app-toolkit134—~1.8kAutomated safety check: PassMIT
Academic PresentationsGabberflast/academic-pptx-skill1.1k1 repos~1.9kAutomated safety check: PassProprietary
Lineage SkillJuneYaooo/lineage-skill451—~3.3kAutomated safety check: NotesApache-2.0
Devils Advocatepedrohcgs/claude-code-my-workflow1.6k2 repos~641Automated safety check: PassMIT
Academic Paper to PPTXYuan1z0825/nature-skills46k—~1.1kAutomated safety check: PassApache-2.0
OpenMAIC Deck Style CloneTHU-MAIC/OpenMAIC40k—~4.9kAutomated safety check: PassMIT

Similar skills

  • Academic Presentations

    Gabberflast/academic-pptx-skill

    Plans and structures academic decks for conference talks, seminars, thesis defenses and grant briefings, with argument-first slides, and leaves file creation to the PPTX skill.

    1.1k GitHub starsUsed in 1 repo~1.9k tokens
    Documents & OfficeAuto-check passed
  • Lineage Skill

    JuneYaooo/lineage-skill

    Turn courses, books, video, audio, PDFs, slides, transcripts, OCR, notes, and long-form materials into source-grounded learning Skills that teach unseen concepts progressively with reliable terminal…

    451 GitHub stars~3.3k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check: notes
  • Devils Advocate

    pedrohcgs/claude-code-my-workflow

    Adversarial 5-7 question challenge to a deck's pedagogical choices — ordering, prerequisites, cognitive load, motivation.

    1.6k GitHub starsUsed in 2 repos~641 tokens
    Documents & OfficeAuto-check passed
  • Academic Paper to PPTX

    Yuan1z0825/nature-skills

    Creates or revises a Chinese-language academic PPTX deck from a scientific paper or reading notes, reusing the paper's figures and adding speaker notes.

    46k GitHub stars~1.1k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • OpenMAIC Deck Style Clone

    THU-MAIC/OpenMAIC

    Produces a new course in the look of an imported deck by copying the layout that fits each page and rewriting that copy's content element by element.

    40k GitHub stars~4.9k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Respond To Eval

    pedrohcgs/claude-code-my-workflow

    Turn student course evaluations (free-text + numeric) into an actionable teaching-improvement plan — the teaching analogue of /respond-to-referees.

    1.6k GitHub stars~2.6k tokensUpdated 10 days ago
    Documents & OfficeAuto-check: notes

More from xujingchen1996/research-app-toolkit

All 9 skills in this repo
  • Cold Email

    xujingchen1996/research-app-toolkit

    A skill your agent uses when the user asks to write a cold email, draft an outreach email, follow up with a professor, or prepare other supervisor-facing application emails.

    134 GitHub stars~694 tokensUpdated 2 mo ago
    Auto-check passed
  • Cv Analyze

    xujingchen1996/research-app-toolkit

    A skill your agent uses when the user asks to analyze a CV or resume, extract an applicant profile, review a resume, or parse a CV.

    134 GitHub stars~690 tokensUpdated 2 mo ago
    Auto-check passed
  • Cv Polish

    xujingchen1996/research-app-toolkit

    A skill your agent uses when the user asks to polish a CV or resume, improve a CV, tailor a resume, or optimize a CV.

    134 GitHub stars~710 tokensUpdated 2 mo ago
    Auto-check passed
  • Document Assist

    xujingchen1996/research-app-toolkit

    A skill your agent uses when the user asks to draft or revise an SOP, personal statement, motivation letter, research proposal, recommendation-letter draft, or similar application document.

    134 GitHub stars~821 tokensUpdated 2 mo ago
    Auto-check passed
  • Gap Analysis

    xujingchen1996/research-app-toolkit

    A skill your agent uses when the user asks to analyze research gaps, find research gaps, generate research ideas, or analyze papers for gaps.

    134 GitHub stars~932 tokensUpdated 2 mo ago
    Auto-check passed
  • Interview Prep

    xujingchen1996/research-app-toolkit

    A skill your agent uses when the user asks to prepare for an interview, run a mock interview, practice interview questions, or get ready for a graduate application interview.

    134 GitHub stars~600 tokensUpdated 2 mo ago
    Auto-check passed

Questions about Interview Ppt

What does Interview Ppt do?

A skill your agent uses when the user asks to prepare a PhD interview deck, professor meeting slides, research presentation PPT, slide-by-slide speaking notes, or interview visuals. Interview Ppt is an agent skill from xujingchen1996/research-app-toolkit. Use when the user asks to prepare a PhD interview deck, professor meeting slides, research presentation PPT, slide-by-slide speaking notes, or interview visuals.

When should I use Interview Ppt?

Interview Ppt fits situations like: the user asks to prepare a PhD interview deck; professor meeting slides; research presentation PPT; slide-by-slide speaking notes.

How do I install Interview Ppt in Claude Code?

Run `npx skills add xujingchen1996/research-app-toolkit --skill interview-ppt -a claude-code`. Or copy the skill folder (codex/skills/interview-ppt in xujingchen1996/research-app-toolkit) into .claude/skills/interview-ppt in your project. Claude Code loads it when a task matches its description.

How do I install Interview Ppt in Codex?

Run `npx skills add xujingchen1996/research-app-toolkit --skill interview-ppt -a codex`. Or copy the skill folder (codex/skills/interview-ppt in xujingchen1996/research-app-toolkit) into .agents/skills/interview-ppt in your project. Codex loads it when a task matches its description.

Can I use Interview Ppt in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add xujingchen1996/research-app-toolkit --skill interview-ppt -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/interview-ppt, .gemini/skills/interview-ppt, .github/skills/interview-ppt and .opencode/skills/interview-ppt in your project.

What does Interview Ppt need to run?

SKILL.md names no scripts, command-line tools or credentials: Interview Ppt is instructions for the agent only.

Does Interview Ppt access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Interview Ppt safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Interview Ppt use?

Interview Ppt is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Interview Ppt use?

About 1.8k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Interview Ppt?

Skills that share tags, products or a category with Interview Ppt: Academic Presentations (Gabberflast/academic-pptx-skill, 1.1k stars), Lineage Skill (JuneYaooo/lineage-skill, 451 stars), Devils Advocate (pedrohcgs/claude-code-my-workflow, 1.6k stars) and Academic Paper to PPTX (Yuan1z0825/nature-skills, 46k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Interview Ppt?

xujingchen1996 (a GitHub user) maintains it in xujingchen1996/research-app-toolkit, which has 134 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on July 18, 2026.

Source: xujingchen1996/research-app-toolkit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.