Skip to content
Agentmart
Submit a tool

export-documents

Prepare and export lixSearch answers as polished PDF documents.

Skill by pollinations

IndexedCC0-1.0★ 24
Write a review

Chalk Labs

Need help deploying export-documents?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/pollinations-export-documents

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Prepare and export lixSearch answers as polished PDF documents. Use only when a user explicitly asks to create, save, download, or export content as a PDF.

Use cases: documents, writing

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/export-documents

What's inside

Skill name
export-documents
Description
Prepare and export lixSearch answers as polished PDF documents. Use only when a user explicitly asks to create, save, download, or export content as a PDF.
License
CC0-1.0
Instructions
35 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Export Documents

Export completed content without repeating research.

## Workflow

1. Accept the canonical finalized Markdown and an optional title. If research is requested in the same turn, wait until sources are fetched and the final synthesis is complete. Never substitute raw research-thread output or status summaries for that synthesis. For a referential follow-up such as "make that a PDF", export the last substantive grounded assistant answer verbatim; do not regenerate or broaden it.
2. Ensure content is non-empty and remove internal task messages.
3. Reject tool syntax, draft preambles, future-work promises, and documents that do not satisfy an explicit requested count or range.
4. Choose a concise subject-based PDF title. Derive the filename as a lowercase hyphenated slug of that title; never derive either from conversational filler, clarification field labels, or the internal resolved-request envelope.
5. Preserve headings, lists, links, citations, and code blocks.
6. Call `export_to_pdf` exactly once. Never call it once per source or once per reasoning turn.
7. Return the download URL unchanged.

## Guardrails

- Depend on synthesis when content is not finalized.
- Never export search snippets, memory excerpts, placeholders, source-count status messages, prior PDF confirmations, errors, or a draft that has not passed synthesis.
- In a continuation, preserve the earlier answer and its citations. Do not replace it with generic background knowledge.
- A successful export must return its stable download URL; after success, stop exporting.
- Do not invent citations or expand source content.
- Do not export without explicit user intent.
- Never export a clarification question or any task whose required fields remain unresolved. Pending clarification is a hard runtime block, not a suggestion.
- Preserve the text response if export fails.

## Runtime contract

    agent: document
    tools: [export_to_pdf]
    timeout_seconds: 20
    max_concurrency: 1
    depends_on: [synthesize-answer]
    output: document_bundle

From pollinations/search.elixpo, CC0-1.0.

More from pollinations/search.elixpo

Signals

Stars
24
Forks
6
Open issues
8
Last commit (this folder)
Sep 16, 2026 (1 month ago)
Last release
Mar 27, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
CC0-1.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from pollinations

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get export-documents running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying export-documents?

CallGet help
Cite this page

export-documents skill. Agent Mart. https://agentmart.dev/skills/pollinations-export-documents (last updated 2026-10-24)