docs: improve agent discoverability (README, AGENTS.md, llms.txt)

[PeterHollens]

Summary

Sharpens SuperDoc's positioning for AI agents evaluating DOCX editing tools. Four low-risk, additive changes:

• README.md — Rewritten tagline ("document engine for AI agents and teams that need real DOCX and PDF deliverables"), added best-for/not-for filter, start-here routing table, expanded agent section with integration paths and use cases. All existing sections preserved.
• packages/superdoc/AGENTS.md — Restructured for agent evaluation: positioning, best-for/not-for, all integration paths (MCP, SDK, CLI, API, browser), capability overview, knowledge corrections. Ships with npm package.
• apps/docs/llms.txt — New concise context file for AI crawlers. Positioning, quick start, accurate tool counts (12 MCP tools, 9 grouped SDK tools, 360+ underlying operations), links.
• apps/docs/llms-full.txt — Comprehensive context with architecture, code examples, full operation list, configuration reference, and knowledge corrections.

Context

AI agents increasingly discover and evaluate tools by reading READMEs, llms.txt, and AGENTS.md files. These changes make it easier for an agent to conclude "SuperDoc is the right tool for real DOCX workflows" without reading multiple doc pages.

Based on competitive analysis of Nutrient, CKEditor, Syncfusion, Apryse, OnlyOffice, and Microsoft Word MCP — SuperDoc has the strongest combination of OOXML-native editing, tracked changes, agent tooling, and self-hosted deployment. The gap is discoverability, not capability.

Test plan

• Verify README renders correctly on GitHub
• Verify AGENTS.md content is accurate against current MCP/SDK capabilities
• Verify llms.txt links resolve
• Review best-for/not-for positioning for accuracy
• Confirm tool counts match current public docs (12 MCP tools, 9 SDK tools, 360+ operations)

🤖 Generated with Claude Code

[caio-pizzol]

@PeterHollens appreciate the effort here — adding llms.txt / llms-full.txt is something we've been wanting to do (SD-2319). a few things to address before merging.

headline: we're keeping "Modern document editing and tooling" for now. AI agents are a big focus for us but the headline needs to cover all SuperDoc use cases, not just agent workflows.

AGENTS.md: the current version has working code examples, a config table, and a "common tasks" cheat sheet — exactly what an AI agent needs when it finds this file in node_modules/. this rewrite replaces all of that with marketing-style content. i'd keep the current file as-is.

llms.txt files: great addition. the content needs a tone pass though — check brand.md for our voice guidelines. some of it reads more like a landing page than a technical reference. a couple factual fixes needed too (inline comments).

README.md: the "Best for / Not for" lists and new sections shift the tone from developer docs to product marketing. our brand leans toward "show, don't sell" — the current README structure works better.

suggested path: keep the llms files (with fixes + tone pass), drop the AGENTS.md and README changes, and use brand.md as the style guide.

[caio-pizzol]

we're keeping "Modern document editing and tooling" for now. AI agents are a big focus for us but the headline needs to cover all SuperDoc use cases, not just agent workflows.

[caio-pizzol]

the "Best for / Not for" lists shift the README from developer docs toward product marketing. our brand leans toward "show, don't sell" — the current structure (quick start first, features second) fits better.

[caio-pizzol]

the current AGENTS.md has code examples, a config table, and a common tasks cheat sheet — that's what agents actually need when they find this in node_modules/. this rewrite replaces all of it with positioning content. i'd keep the current version.

[caio-pizzol]

lines 46 and 48 point to the same URL. one should be removed or point somewhere different.

[caio-pizzol]

"360+ operations" — actual count is 344. should say "340+". same in llms.txt and AGENTS.md.