Agent skill

Research Understanding

by XueruiSu in XueruiSu/Paper-PRISM

A skill your agent uses when Codex needs to interview the user or normalize research notes, experiments, theory, related works, LaTeX, tables, or a draft into a PaperPRISM ResearchAsset.

No licenceAuto-check passedDocuments & Office

Install Research Understanding

skills CLI
$ npx skills add XueruiSu/Paper-PRISM --skill research-understanding -a claude-code

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

GitHub CLI
$ gh skill install XueruiSu/Paper-PRISM research-understanding --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/XueruiSu/Paper-PRISM.git skills-src && mkdir -p .claude/skills && cp -r skills-src/codex_skills/research-understanding .claude/skills/research-understanding && 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
research-understanding
GitHub stars
109
Token cost
~353 tokens
SKILL.md length
154 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
None found

At a glance

A skill your agent uses when Codex needs to interview the user or normalize research notes, experiments, theory, related works, LaTeX, tables, or a draft into a PaperPRISM ResearchAsset.

  • Works in 5 steps: Extract task, method, insight, evidence,… → If the user provides a draft, extract… → Update ResearchAsset.md or provide an… → …
  • Codex needs to interview the user
  • SKILL.md covers Goal, Inputs, Workflow and Rules, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Research Understanding is an agent skill from XueruiSu/Paper-PRISM. Use when Codex needs to interview the user or normalize research notes, experiments, theory, related works, LaTeX, tables, or a draft into a PaperPRISM ResearchAsset.

Its SKILL.md is about 350 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 Literature review and LaTeX. It works with LaTeX.

When your agent uses it

  • Codex needs to interview the user
  • Normalize research notes
  • A draft into a PaperPRISM ResearchAsset

Example prompts

  • “/research-understanding”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Extract task, method, insight, evidence, baselines, related works, theory, limitations, and target venue.
  2. If the user provides a draft, extract assets before rewriting.
  3. Update ResearchAsset.md or provide an equivalent concise working summary.
  4. Identify the top missing inputs that block claims or writing.
  5. Ask at most three high-value questions; otherwise continue with caveats.

What it can do on your machine

Read from SKILL.md and the folder at commit 13e134f. 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

Research Understanding loads about 353 tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 154 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~353

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 154 words (~353 tokens).

name
research-understanding

Read the full SKILL.md on GitHub

Files

Just SKILL.md in codex_skills/research-understanding of XueruiSu/Paper-PRISM.

Open the folder on GitHubat commit 13e134f

Compare with similar skills

Research Understanding 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.

Research Understanding compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Research Understanding this skillXueruiSu/Paper-PRISM109—~353Automated safety check: PassNone
Typst Paperbahayonghang/academic-writing-skills500—~3.6kAutomated safety check: PassNone
Academic Paperbrycewang-stanford/Auto-Empirical-Research-Skills4.6k—~7.3kAutomated safety check: PassCustom licence
Academic Paper Writing PipelineImbad0202/academic-research-skills51k—~16kAutomated safety check: PassCustom licence
Econ Writehanlulong/econ-writing-skill6512 repos~14kAutomated safety check: PassMIT
Paper OrchestraAr9av/PaperOrchestra6791 repos~3.5kAutomated safety check: PassCustom licence

Similar skills

  • Typst Paper

    bahayonghang/academic-writing-skills

    Typst paper assistant for existing .typ manuscripts in English or Chinese.

    500 GitHub stars~3.6k tokensUpdated 13 days ago
    Documents & OfficeAuto-check passed
  • Academic Paper

    brycewang-stanford/Auto-Empirical-Research-Skills

    Academic paper writing skill with 12-agent pipeline. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

    4.6k GitHub stars~7.3k tokensUpdated 5 days ago
    Documents & OfficeAuto-check passed
  • Academic Paper Writing Pipeline

    Imbad0202/academic-research-skills

    Runs a 12-agent pipeline that plans, drafts, cites, reviews and formats academic papers, with modes for revision, rebuttals, abstracts and citation checks.

    51k GitHub stars~16k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Econ Write

    hanlulong/econ-writing-skill

    Expert economics paper writing assistant synthesizing advice from 50+ top guides by Cochrane, McCloskey, Shapiro, Head, Bellemare, Goldin, Glaeser, Kremer, and other leading economists.

    651 GitHub starsUsed in 2 repos~14k tokens
    Research & ScienceAuto-check passed
  • Paper Orchestra

    Ar9av/PaperOrchestra

    Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured research materials (idea, experimental log, LaTeX template, conference guidelines…

    679 GitHub starsUsed in 1 repo~3.5k tokens
    Research & ScienceAuto-check passed
  • Section Writing Agent

    Ar9av/PaperOrchestra

    Step 4 of the PaperOrchestra pipeline (arXiv:2604.05018). An agent skill from Ar9av/PaperOrchestra.

    679 GitHub starsUsed in 1 repo~3.3k tokens
    Research & ScienceAuto-check passed

More from XueruiSu/Paper-PRISM

All 11 skills in this repo
  • Logical Template Builder

    XueruiSu/Paper-PRISM

    A skill your agent uses when Codex needs to convert selected exemplar trajectories into a sentence-level PaperPRISM ClozeBlueprint before paper writing, or revise an existing…

    109 GitHub stars~743 tokensUpdated 3 mo ago
    Auto-check passed
  • Paper Writer

    XueruiSu/Paper-PRISM

    A skill your agent uses when Codex needs to write, rewrite, or extend PaperPRISM paper prose or LaTeX while respecting claims, evidence, and WritingPlan constraints.

    109 GitHub stars~512 tokensUpdated 3 mo ago
    Auto-check passed
  • Paperprism Orchestrator

    XueruiSu/Paper-PRISM

    A skill your agent uses when the user wants to turn a research idea, experiment results, related works, or draft into a paper through the Codex-native PaperPRISM workflow.

    109 GitHub stars~1.2k tokensUpdated 3 mo ago
    Auto-check passed
  • Review Simulator

    XueruiSu/Paper-PRISM

    A skill your agent uses when Codex needs to simulate reviewer feedback, explain reviewer risks, and turn critique into a PaperPRISM revision plan.

    109 GitHub stars~423 tokensUpdated 3 mo ago
    Auto-check passed
  • Trajectory Selector

    XueruiSu/Paper-PRISM

    A skill your agent uses when Codex must select, compare, or adapt exemplar sentence-type trajectories from PaperPRISM's trajectory library before creating a ClozeBlueprint or writing a paper.

    109 GitHub stars~723 tokensUpdated 3 mo ago
    Auto-check passed
  • Archetype Identifier

    XueruiSu/Paper-PRISM

    A skill your agent uses when Codex needs to explain, validate, or revise PaperPRISM research archetype and paper framing choices.

    109 GitHub stars~413 tokensUpdated 3 mo ago
    Auto-check passed

Works with

Questions about Research Understanding

What does Research Understanding do?

A skill your agent uses when Codex needs to interview the user or normalize research notes, experiments, theory, related works, LaTeX, tables, or a draft into a PaperPRISM ResearchAsset. Research Understanding is an agent skill from XueruiSu/Paper-PRISM. Use when Codex needs to interview the user or normalize research notes, experiments, theory, related works, LaTeX, tables, or a draft into a PaperPRISM ResearchAsset.

When should I use Research Understanding?

Research Understanding fits situations like: Codex needs to interview the user; normalize research notes; A draft into a PaperPRISM ResearchAsset.

How do I install Research Understanding in Claude Code?

Run `npx skills add XueruiSu/Paper-PRISM --skill research-understanding -a claude-code`. Or copy the skill folder (codex_skills/research-understanding in XueruiSu/Paper-PRISM) into .claude/skills/research-understanding in your project. Claude Code loads it when a task matches its description.

How do I install Research Understanding in Codex?

Run `npx skills add XueruiSu/Paper-PRISM --skill research-understanding -a codex`. Or copy the skill folder (codex_skills/research-understanding in XueruiSu/Paper-PRISM) into .agents/skills/research-understanding in your project. Codex loads it when a task matches its description.

Can I use Research Understanding 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 XueruiSu/Paper-PRISM --skill research-understanding -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research-understanding, .gemini/skills/research-understanding, .github/skills/research-understanding and .opencode/skills/research-understanding in your project.

What does Research Understanding need to run?

SKILL.md names no scripts, command-line tools or credentials: Research Understanding is instructions for the agent only. Our summary lists: Python 3.

Does Research Understanding 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 Research Understanding 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 Research Understanding use?

No licence was found for Research Understanding or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Research Understanding use?

About 353 tokens (SKILL.md is roughly 1.4k 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 Research Understanding?

Skills that share tags, products or a category with Research Understanding: Typst Paper (bahayonghang/academic-writing-skills, 500 stars), Academic Paper (brycewang-stanford/Auto-Empirical-Research-Skills, 4.6k stars), Academic Paper Writing Pipeline (Imbad0202/academic-research-skills, 51k stars) and Econ Write (hanlulong/econ-writing-skill, 651 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Research Understanding?

XueruiSu (a GitHub user) maintains it in XueruiSu/Paper-PRISM, which has 109 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on July 11, 2026.

Source: XueruiSu/Paper-PRISM on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.