agentleFS
VortiagoVortiago/mcp-outline/skills/outline/SKILL.md

outline

Skill158 starsChanged 11 months agoMITView on GitHub

Conventions and efficient workflows for Outline knowledge bases via mcp-outline tools. Use when creating, editing, restructuring, or diagramming Outline documents — covers Outline markdown quirks (mermaidjs code fences), document and collection structure, string-match editing, staged rewrites, batch operations, and search status filters.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Default to edit_document: each old_string must match exactly once (add surrounding context to disambiguate).

    line 50
  2. Distinctive:

    Use what's listed; if an editing tool is absent, say so.

    line 80

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Working with Outline

Markdown

  • Mermaid diagrams need ```mermaidjs fences, NOT ```mermaid — the wrong fence silently renders as a plain code block.
  • Otherwise standard markdown. Use ATX headings (#–######); they power the TOC and section tools.

Structure

  • Collections contain documents; documents nest via parent_document_id. Browse: list_collections, get_collection_structure.
  • Lifecycle: draft → published → archived → trash (30-day recovery via restore_document; delete_document(permanent=True) is unrecoverable).
  • create_document(template=True) / update_document(template=True) adds to the "New from template" picker.
  • Titles are not unique; resolve to IDs with get_document_id_from_title or search_documents. Check get_document_backlinks before restructuring or deleting.

Search defaults to published only

Drafts and archived docs are invisible to search_documents and list_recently_updated_documents unless widened: status_filter=["draft", "published", "archived"].

Reading large documents

  1. get_document_toc — headings with 0-based line numbers.
  2. read_document_section(heading=...) — case-insensitive substring; accepts headings as the TOC prints them (e.g. "## Background").
  3. search_document_content(query=...) — grep within the document: matching lines with line numbers and context. Use it to locate text for edit_document old_strings or read_document offsets.
  4. read_document(offset=N, limit=M) — TOC/grep line numbers are valid offsets.

Full read_document only for small documents.

Editing

  • Default to edit_document: each old_string must match exactly once (add surrounding context to disambiguate); edits apply sequentially, all-or-nothing. Batch all edits for one document into a single call.
  • update_document only for full replacement, title changes, or append=True (sends just the chunk).

Staged rewrites

edit_document(id, edits=[...], save=False)   # stage, repeat as needed
edit_document(id, edits=[...], save=True)    # final batch + push all
edit_document(id, edits=[], save=True)       # or: flush only

One API write total. Staged changes are server-memory only — flush before ending; a restart discards them. Read tools show staged text with an "unsaved changes" notice; export_document bypasses staging and returns the last saved content.

Many documents

Use batch_create_documents, batch_update_documents, batch_move_documents, batch_archive_documents, batch_delete_documents (10–50 per call; per-document results) instead of loops.

Missing tools

Deployments may be read-only, delete-disabled, or scope-filtered. Use what's listed; if an editing tool is absent, say so.

Exploration

For broad search-and-summarize, delegate to the outline-explorer agent (bundled with this plugin).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.