Skip to content
Agentmart
Submit a tool

document-pair

Ecosystem document-pair construction.

Skill by Literate AI maintainers <literate-ai-maintainers@users.noreply.github.com>

IndexedApache-2.0★ 28
Write a review

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/jordanhubbard-document-pair

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

Ecosystem document-pair construction. Use for Literate AI workflow tasks.

Use cases: documents, productivity

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. Checked Oct 25, 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/document-pair

What's inside

Skill name
document-pair
Description
Ecosystem document-pair construction. Use for Literate AI workflow tasks.
License
Apache-2.0
Metadata
author: Literate AI maintainers <literate-ai-maintainers@users.noreply.github.com>
Instructions
37 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Ecosystem document-pair construction

Generate the build source that realizes a document pair for exactly one selected
`documentation.ecosystem` target, from the consuming Component's specification and the
ecosystem binding fragment contributed by the selected Flavor.

Emit a deterministic build program that constructs every declared member as native
editable objects, plus the capability manifest described by the document-pair interface.
Read the member set, surface geometry, access audience, permission, and link-sharing
state from the consuming specification; read format, collaboration surface, access
vocabulary, and the concrete formatting mapping from the ecosystem binding fragment.
Never infer either from the other.

Realize only local artifacts. Set every member's `published_location` to null and leave
publication to a separately authorized step. Record the resolved access record for each
member without contacting the service that would enforce it.

For every realized presentation member, author non-empty per-page notes carrying that
page's supporting authority and its recorded limits, keep every element's bounding box
inside the declared surface geometry, and keep text-bearing frames from overlapping.
Geometry-escape does not detect painted overflow or colliding titles. Put body copy in
the owning shape's text frame as real paragraphs; a newline character inside one
paragraph is not a line break after Google Slides import. For every realized narrative
member, use the ecosystem's built-in heading styles without skipping a level.

Generate the acceptance evidence the document-pair acceptance contract consumes: a
per-page geometry scan against the declared surface, a text-bearing-frame overlap scan,
a notes-coverage count, a heading hierarchy walk, a placeholder scan, and a credential
scan over the manifest and every retained artifact. Emit these as machine-readable
results, not prose. They are lifecycle metadata; do not read them back from the build
program at runtime.

Treat the authoring package as an input to be preserved, never rewritten: the narrative
specification, factual ledger, generation prompts, owned assets, regeneration entry
point, deliverable links, and QA record are authored material. Only the build source is
generated.

From jordanhubbard/literate-ai, Apache-2.0.

More from jordanhubbard/literate-ai

Signals

Stars
28
Forks
10
Open issues
26
Last commit (this folder)
Sep 30, 2026 (29 days ago)
Last release
Oct 12, 2026 (17 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Literate AI maintainers <literate-ai-maintainers@users.noreply.github.com>

Cite this page

document-pair skill. Agent Mart. https://agentmart.dev/skills/jordanhubbard-document-pair (last updated 2026-10-24)