Agent skill

Document Assist

by xujingchen1996 in 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.

MITAuto-check passedBusiness, Finance & HR

Install Document Assist

skills CLI
$ npx skills add xujingchen1996/research-app-toolkit --skill document-assist -a claude-code

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

GitHub CLI
$ gh skill install xujingchen1996/research-app-toolkit document-assist --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/document-assist .claude/skills/document-assist && 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
document-assist
GitHub stars
134
Token cost
~821 tokens
SKILL.md length
393 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 draft or revise an SOP, personal statement, motivation letter, research proposal, recommendation-letter draft, or similar application document.

  • Works in 4 steps: Extract reusable background from… → Provide a short outline first. → Then output the full first draft. → …
  • The user asks to draft
  • SKILL.md covers Preconditions, Language Rules, Optional Linkage: Life Science… and Identify the Document Type, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Document Assist is an agent skill from xujingchen1996/research-app-toolkit. Use when the user asks to draft or revise an SOP, personal statement, motivation letter, research proposal, recommendation-letter draft, or similar application document. Based on the shared application profile and user materials, generate research application documents.

Its SKILL.md is about 820 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 Business, Finance & HR, covering Operations and SOPs. 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 draft
  • Personal statement
  • Motivation letter
  • Research proposal

Example prompts

  • “/document-assist”

Workflow steps

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

  1. Extract reusable background from memory.md.
  2. Provide a short outline first.
  3. Then output the full first draft.
  4. If the user has hard constraints, such as word count, prompt title, or paragraph count, strictly narrow the output to those limits.

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

Document Assist loads about 821 tokens when it runs. Until then it costs about 72 tokens; SKILL.md has 393 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~821

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). 393 words, ~821 tokens.

Download SKILL.mdSave it as .claude/skills/document-assist/SKILL.md (or your agent's skills folder).
name
document-assist
description
Use when the user asks to draft or revise an SOP, personal statement, motivation letter, research proposal, recommendation-letter draft, or similar application document. Based on the shared application profile and user materials, generate research application documents.

Application Document Assistance

Preconditions

  • Read ../../memory.md first.
  • If the application profile is missing, first suggest that the user run cv-analyze, or fill in the necessary background directly in this round before continuing.

Language Rules

  • Support three output modes: zh, en, and bilingual.
  • If the user explicitly specifies the document language, prioritize the current request.
  • Otherwise read preferred_language from memory.md.
  • If it is still unclear, prioritize the official commonly used language of the target program.
  • If the user requests bilingual output, default to one main draft language version plus one shortened counterpart version or outline, rather than repeating the entire document paragraph by paragraph.

Optional Linkage: Life Science Research

  • If the user's application direction clearly falls under life sciences / biomedical research, and the document needs real research background support, life-science-research can be linked first before drafting.
  • This is especially suitable for the following document tasks:
    • research-proposal
    • cases where research fit needs to be written clearly
    • cases that require future directions, problem significance, or dataset / pathway / target context
  • The linkage result can be used to:
    • supplement research background
    • refine a more specific research question
    • organize literature / dataset / target / disease context
    • avoid documents that stay at the level of vague interest statements
  • If the current task is only language polishing, word-count reduction, tone adjustment, or structure adjustment, and the user has already provided complete content, do not trigger that linkage.
Show full SKILL.md (166 more words)Show less

Identify the Document Type

If the user does not specify it, default to sop. Supported types:

  • sop
  • motivation
  • research-proposal
  • recommendation-draft

Material Collection

For document tasks, do not start writing immediately; first fill in the minimum required materials:

  • target program and school
  • target professor / lab group, if any
  • experiences that must be included
  • application motivation
  • short-term / long-term goals after graduation
  • word-count or formatting requirements

Workflow

  1. Extract reusable background from memory.md.
  2. Provide a short outline first.
  3. Then output the full first draft.
  4. If the user has hard constraints, such as word count, prompt title, or paragraph count, strictly narrow the output to those limits.

Document Rules

  • Do not fabricate experiences, papers, awards, or motivations.
  • Prioritize a style that is real, specific, and verifiable.
  • A research-proposal must clearly define the research question, method, expected contribution, and risks.
  • A recommendation-draft must be written from the recommender's perspective.

Output Requirements

  • By default include:
    • an outline
    • a full draft
    • 2 to 4 points that can be further strengthened

© 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/document-assist of xujingchen1996/research-app-toolkit.

Open the folder on GitHubat commit d84dbc0

Compare with similar skills

Document Assist 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.

Document Assist compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Document Assist this skillxujingchen1996/research-app-toolkit134—~821Automated safety check: PassMIT
Cc Sdd New Agentgotalab/cc-sdd3.7k—~1.1kAutomated safety check: PassMIT
DBS Business Toolkit Entrydontbesilent2025/dbskill11k—~2kAutomated safety check: PassCustom licence
Agent Sop Authorstrands-agents/agent-sop1.2k—~3.5kAutomated safety check: PassApache-2.0
Diffusion Narrative Denouncingcanwhite/Krebs1k—~831Automated safety check: PassMIT
Polanyi Perspective0xenzyme/polanyi-skill137—~1.3kAutomated safety check: PassMIT

Similar skills

  • Cc Sdd New Agent

    gotalab/cc-sdd

    Add or extend coding-agent support in cc-sdd by executing the SOP in docs/cc-sdd/sop-new-agent.md end-to-end.

    3.7k GitHub stars~1.1k tokensUpdated 16 days ago
    Business, Finance & HRAuto-check passed
  • DBS Business Toolkit Entry

    dontbesilent2025/dbskill

    Chinese-language entry skill for the dontbesilent business toolkit: onboards new users, orchestrates tasks across sub-skills, runs numbered prompts and lists hidden ones.

    11k GitHub stars~2k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • Agent Sop Author

    strands-agents/agent-sop

    Create (or update) and validate Agent SOPs (Standard Operating Procedures) - markdown-based workflows that guide AI agents through complex, multi-step tasks with RFC 2119 constraints.

    1.2k GitHub stars~3.5k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed
  • 基于"扩散模型叙事去噪流"的小说写作 SOP。将 AI 视为去杂质机器,通过锁定全局信号、预测叙事噪声、精准去噪、随机修正四个步骤,解决 AI 翻译腔、逻辑断层和故事平淡的问题。

    1k GitHub stars~831 tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • Polanyi Perspective

    0xenzyme/polanyi-skill

    Michael Polanyi 的思维框架。用 Polanyi 视角分析隐性知识、技能习得、经验传承、师徒制、 知识管理、学习方法、AI/工具替代边界、科学共同体与后批判哲学问题。

    137 GitHub stars~1.3k tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed

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
  • 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 Ppt

    xujingchen1996/research-app-toolkit

    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.

    134 GitHub stars~1.8k 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 Document Assist

What does Document Assist do?

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. Document Assist is an agent skill from xujingchen1996/research-app-toolkit. Use when the user asks to draft or revise an SOP, personal statement, motivation letter, research proposal, recommendation-letter draft, or similar application document.

When should I use Document Assist?

Document Assist fits situations like: the user asks to draft; personal statement; motivation letter; research proposal.

How do I install Document Assist in Claude Code?

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

How do I install Document Assist in Codex?

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

Can I use Document Assist 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 document-assist -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/document-assist, .gemini/skills/document-assist, .github/skills/document-assist and .opencode/skills/document-assist in your project.

What does Document Assist need to run?

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

Does Document Assist 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 Document Assist 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 Document Assist use?

Document Assist 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 Document Assist use?

About 821 tokens (SKILL.md is roughly 3.3k 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 Document Assist?

Skills that share tags, products or a category with Document Assist: Cc Sdd New Agent (gotalab/cc-sdd, 3.7k stars), DBS Business Toolkit Entry (dontbesilent2025/dbskill, 11k stars), Agent Sop Author (strands-agents/agent-sop, 1.2k stars) and Diffusion Narrative Denouncing (canwhite/Krebs, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Document Assist?

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.