Typst Paper

What it does

When your agent uses it

• The user wants to compile
• Improve a Typst paper
• Including format checks
• Bibliography validation for BibTeX

Example prompts

• “three-line table”
• “check abstract”
• “reformat for another journal”
• “/typst-paper”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): Read, Glob, Grep, Bash(uv *), Bash(typst *)

Workflow steps

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

1. 1Parse $ARGUMENTS and select the active module.
2. 2Read only the reference file needed for that module.
3. 3Run the module script with uv run python ....
4. 4Return Typst-ready comments and next actions.
5. 5For bibliography requests, decide BibTeX vs Hayagriva first, then run bibliography.

What it can do on your machine

Read from SKILL.md and the folder at commit 9fa87d8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Glob
  • Grep
  • Bash(uv *)
  • Bash(typst *)

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/, which the agent can run.

  Shell commands in SKILL.md call:

  • uv

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

• Network

  No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

  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

Typst Paper loads about 1.9k tokens when it runs, and up to ~40k if it reads all its reference files. Until then it costs about 237 tokens; SKILL.md has 692 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~237

When it runs · the whole SKILL.md, loaded when a task matches

~1.9k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~40k

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

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); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 692 words (~1,919 tokens).

name

typst-paper

allowed-tools

Read, Glob, Grep, Bash(uv *), Bash(typst *)

metadata.category

academic-writing

metadata.tags

typst, paper, chinese, english, ieee, acm, springer, neurips, compilation, grammar, bibliography, hayagriva, pseudocode, algorithmic, lovelace

argument-hint

[main.typ] [--section SECTION] [--module MODULE]

Read the full SKILL.md on GitHub

Files

SKILL.md and 61 other files (scripts, references) in skills/35-bahayonghang-academic-writing-skills/skills/typst-paper of brycewang-stanford/Auto-Empirical-Research-Skills.

• SKILL.md
• agents/openai.yaml
• evals/evals.json
• examples/bibliography-and-title.md
• examples/compile-and-format.md
• examples/expression-and-translation.md
• references/ABSTRACT_STRUCTURE.md
• references/BEST_PRACTICES.md
• references/CITATION_STYLES.md
• references/CITATION_VERIFICATION.md
• references/COMMON_ERRORS.md
• references/DEAI_GUIDE.md
• references/JOURNAL_ABBREVIATIONS.md
• references/JOURNAL_ADAPTATION_WORKFLOW.md
• references/NUMBER_UNIT_GUIDE.md
• references/REVIEWER_PERSPECTIVE.md
• references/STYLE_GUIDE.md
• … and 45 more

Open the folder on GitHubat commit 9fa87d8