用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill typst-latex-compiler命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.
正在显示 SKILL.md
基于 SOC 职业分类
| name | Typst & LaTeX Compiler |
| description | Compile Typst and LaTeX documents to PDF via API. Send source code, get back a PDF. |
| metadata | {"clawdbot":{"config":{"requiredEnv":[],"stateDirs":[]}}} |
Compile Typst (.typ) and LaTeX (.tex) documents to PDF using the TypeTex compilation API.
Base URL: https://studio-intrinsic--typetex-compile-app.modal.run
POST /public/compile/typst
Content-Type: application/json
Request Body:
{
"content": "#set page(paper: \"a4\")\n\n= Hello World\n\nThis is a Typst document.",
"main_filename": "main.typ",
"auxiliary_files": {}
}
Response (Success):
{
"success": true,
"pdf_base64": "JVBERi0xLjQK..."
}
Response (Failure):
{
"success": false,
"error": "error: file not found: missing.typ"
}
POST /public/compile/latex
Content-Type: application/json
Request Body:
{
"content": "\\documentclass{article}\n\\begin{document}\nHello World\n\\end{document}",
"main_filename": "main.tex",
"auxiliary_files": {}
}
Response (Success):
{
"success": true,
"pdf_base64": "JVBERi0xLjQK..."
}
Response (Failure):
{
"success": false,
"error": "! LaTeX Error: Missing \\begin{document}.",
"log_output": "This is pdfTeX..."
}
GET /public/compile/health
Returns {"status": "ok", "service": "public-compile"} if the service is running.
import requests
import base64
response = requests.post(
"https://studio-intrinsic--typetex-compile-app.modal.run/public/compile/typst",
json={
"content": """
#set page(paper: "a4", margin: 2cm)
#set text(font: "New Computer Modern", size: 11pt)
= My Document
This is a paragraph with *bold* and _italic_ text.
== Section 1
- Item 1
- Item 2
- Item 3
""",
"main_filename": "main.typ"
}
)
result = response.json()
if result["success"]:
pdf_bytes = base64.b64decode(result["pdf_base64"])
with open("output.pdf", "wb") as f:
f.write(pdf_bytes)
print("PDF saved to output.pdf")
else:
print(f"Compilation failed: {result['error']}")
import requests
import base64
response = requests.post(
"https://studio-intrinsic--typetex-compile-app.modal.run/public/compile/latex",
json={
"content": r"""
\documentclass[11pt]{article}
\usepackage[margin=1in]{geometry}
\usepackage{amsmath}
\title{My Document}
\author{Author Name}
\begin{document}
\maketitle
\section{Introduction}
This is a LaTeX document with math: $E = mc^2$
\end{document}
""",
"main_filename": "main.tex"
}
)
result = response.json()
if result["success"]:
pdf_bytes = base64.b64decode(result["pdf_base64"])
with open("output.pdf", "wb") as f:
f.write(pdf_bytes)
else:
print(f"Compilation failed: {result['error']}")
if result.get("log_output"):
print(f"Log: {result['log_output']}")
import requests
import base64
response = requests.post(
"https://studio-intrinsic--typetex-compile-app.modal.run/public/compile/typst",
json={
"content": """
#import "template.typ": *
#show: project.with(title: "My Report")
= Introduction
#include "chapter1.typ"
""",
"main_filename": "main.typ",
"auxiliary_files": {
"template.typ": """
#let project(title: none, body) = {
set page(paper: "a4")
set text(font: "New Computer Modern")
align(center)[
#text(size: 24pt, weight: "bold")[#title]
]
body
}
""",
"chapter1.typ": """
== Chapter 1
This is the first chapter.
"""
}
}
)
result = response.json()
if result["success"]:
pdf_bytes = base64.b64decode(result["pdf_base64"])
with open("report.pdf", "wb") as f:
f.write(pdf_bytes)
For binary files like images, base64-encode them:
import requests
import base64
# Read and encode an image
with open("figure.png", "rb") as f:
image_base64 = base64.b64encode(f.read()).decode("utf-8")
response = requests.post(
"https://studio-intrinsic--typetex-compile-app.modal.run/public/compile/typst",
json={
"content": """
#set page(paper: "a4")
= Document with Image
#figure(
image("figure.png", width: 80%),
caption: [A sample figure]
)
""",
"main_filename": "main.typ",
"auxiliary_files": {
"figure.png": image_base64
}
}
)
# Typst compilation
curl -X POST https://studio-intrinsic--typetex-compile-app.modal.run/public/compile/typst \
-H "Content-Type: application/json" \
-d '{
"content": "#set page(paper: \"a4\")\n\n= Hello World\n\nThis is Typst.",
"main_filename": "main.typ"
}' | jq -r '.pdf_base64' | base64 -d > output.pdf
# LaTeX compilation
curl -X POST https://studio-intrinsic--typetex-compile-app.modal.run/public/compile/latex \
-H "Content-Type: application/json" \
-d '{
"content": "\\documentclass{article}\n\\begin{document}\nHello World\n\\end{document}",
"main_filename": "main.tex"
}' | jq -r '.pdf_base64' | base64 -d > output.pdf
When compilation fails, the response includes:
success: falseerror: Human-readable error messagelog_output (LaTeX only): Full compilation log for debuggingCommon errors:
auxiliary_filessuccess before accessing pdf_base64auxiliary_files for multi-file projects