Use this skill when the user attaches or references a PDF and asks to read, summarize, extract, compare, translate, inspect, or answer questions about it.

Inputs

Kivio stores each uploaded file as a safe local copy and includes its absolute path in the user message under Kivio 安全副本路径. Pass that safe copy path to run_python via files; Kivio mounts it inside the Pyodide filesystem for the run. Python code must use the mounted virtual paths in KIVIO_INPUT_FILES, not the host absolute path directly.

You can also process any local PDF, not just uploaded safe copies: pass its absolute path (e.g. one discovered via glob/list_dir) directly to run_python via files.

Workflow

Identify the PDF safe copy path from the attachment note.
Use run_python with files=["Kivio 安全副本路径"] and pypdf to inspect or extract text from the PDF when possible.
If extraction fails or returns little text, explain that the PDF may be scanned/image-only and ask for OCR or use the screenshot/Lens flow when appropriate.
Ground answers in extracted content. Do not infer document contents from the filename alone.
For long PDFs, extract page-level text first, then summarize by section/page before answering.

Python Pattern

Use Pyodide-friendly Python. Prefer pypdf for digitally generated PDFs. The files argument mounts attachment safe copies into Pyodide and exposes their virtual paths through KIVIO_INPUT_FILES. If text extraction returns little content, report that the PDF may be scanned/image-only and ask the user whether to use OCR or Lens.

from pathlib import Path
from pypdf import PdfReader

pdf_path = Path(KIVIO_INPUT_FILES[0])
reader = PdfReader(str(pdf_path))
for index, page in enumerate(reader.pages, start=1):
    text = page.extract_text() or ""
    print(f"--- page {index} ---")
    print(text[:4000])

Output

For summaries: include the main points and mention any pages/sections you used when available.
For extraction: preserve original order and tables/lists as much as practical.
For analysis: quote only short snippets and explain conclusions separately.

Más de este repositorio

mismo repositorio

json-canvas

ZMGID/kivio

Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.

2026-07-04304

obsidian-bases

ZMGID/kivio

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

2026-07-04304

obsidian-cli

ZMGID/kivio

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.

2026-07-04304

obsidian-markdown

ZMGID/kivio

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.

2026-07-04304

diagram

ZMGID/kivio

Visualize architectures, flows, sequences, state machines, ER/data models, class structures, decision logic, mind maps, and timelines as rendered diagrams instead of prose. Activate whenever the user discusses or asks to explain a system architecture, module/deployment topology, call/request flow, interaction sequence, state machine or lifecycle, database/entity relationships, class structure, decision tree, or process — especially when they say draw / 画 / 图示 / 可视化 / 用图说明 / 画个流程图/架构图/时序图. Kivio renders mermaid code blocks inline as diagrams and html code blocks in a live preview, so emit those directly without calling any file tool.

2026-06-30304

himalaya

ZMGID/kivio

Read, search, compose, reply, and organize email via the Himalaya CLI (IMAP/SMTP). Activate when the user asks about mail, inbox, sending email, or when an email connector is configured.

2026-06-29304

PDF Skill

Use this skill when the user attaches or references a PDF and asks to read, summarize, extract, compare, translate, inspect, or answer questions about it.

Inputs

You can also process any local PDF, not just uploaded safe copies: pass its absolute path (e.g. one discovered via glob/list_dir) directly to run_python via files.

Workflow

Identify the PDF safe copy path from the attachment note.

Use run_python with files=["Kivio 安全副本路径"] and pypdf to inspect or extract text from the PDF when possible.

If extraction fails or returns little text, explain that the PDF may be scanned/image-only and ask for OCR or use the screenshot/Lens flow when appropriate.

Ground answers in extracted content. Do not infer document contents from the filename alone.

For long PDFs, extract page-level text first, then summarize by section/page before answering.

Python Pattern

from pathlib import Path from pypdf import PdfReader pdf_path = Path(KIVIO_INPUT_FILES[0]) reader = PdfReader(str(pdf_path)) for index, page in enumerate(reader.pages, start=1): text = page.extract_text() or "" print(f"--- page {index} ---") print(text[:4000])

Output

For summaries: include the main points and mention any pages/sections you used when available.

For extraction: preserve original order and tables/lists as much as practical.

For analysis: quote only short snippets and explain conclusions separately.