SlipBot Instapaper Importer

Import reading notes from Instapaper exports into the slipbox. Use when user pastes an Instapaper highlight export with article title and notes. Parses title/URL from header, extracts user's own notes (plain text lines), skips original highlights (> lines), then runs slipbot for each.

Security Scan

Instructions are internally consistent: an instruction-only skill that parses pasted Instapaper exports and delegates creation of notes to an existing slipbot workflow, and it doesn't request extra credentials, installs, or system access.

Purpose & Capability

Name/description match the instructions: the SKILL.md describes parsing Instapaper export text and creating slipbox entries by calling slipbot. The skill does not request unrelated credentials, binaries, or config paths. The only implicit requirement is that a slipbot integration/skill is available to handle the note creation.

Instruction Scope

Runtime instructions are narrowly scoped to parsing the pasted export, counting notes, asking for confirmation, and invoking slipbot for each note. No instructions read arbitrary files, access environment variables, or send data to unknown external endpoints. It does extract titles and URLs from the paste (including instapaper-private:// links) and passes those as source metadata to slipbot.

Install Mechanism

Instruction-only skill with no install spec and no code files. Nothing is written to disk or downloaded during install.

Credentials

Requires no environment variables, credentials, or config paths. The data it handles comes from the user's pasted content; no secret access is requested.

Persistence & Privilege

always is false and the skill does not request elevated privileges. It delegates creation of persistent notes to slipbot; installations that allow autonomous model invocation could cause agents to run this skill without an interactive user, but the SKILL.md includes an explicit confirmation step. Consider whether your agent's autonomy settings and slipbot's permissions match your risk tolerance.

Assessment

This skill appears to do exactly what it says: parse a pasted Instapaper export and call slipbot to create notes. Before installing, confirm that (1) you have or trust the slipbot integration the skill will call (it will hand slips to that tool to create files/entries), (2) you are comfortable with the agent's autonomy settings (an autonomous agent could run the import, though the SKILL.md includes a confirmation step), and (3) you understand that the parser will include any URLs (including instapaper-private:// links) from the paste as metadata. If you want extra safety, keep autonomous invocation off or verify slipbot's behavior/permissions first.

Instapaper Import

Parse Instapaper highlight exports and create slipbox entries for user's notes.

Input Format

# [[Article Title](url)]
> Original highlight from article (SKIP)
User's note about the highlight (IMPORT)
> Another highlight (SKIP)
Another user note (IMPORT)

Key distinction:

• > lines = Original article highlights → Skip these
• Plain text lines = User's own ideas/takeaways → Import these as notes

Parsing Rules

Header Line

1. Extract title from: # [[Title](url)]
2. URL may be instapaper-private://... (private) or regular URL
3. Source type: article
4. Author: null (Instapaper doesn't include author)

Content Lines

1. Lines starting with > = original highlights → skip
2. Plain text lines after > lines = user notes → import
3. Empty lines → skip
4. Each user note becomes a separate slipbox entry

Workflow

1. Parse header → extract article title and URL
2. Extract user notes → collect plain text lines (not starting with >)
3. Precheck → show user: article title, note count, ask for confirmation
4. On confirmation → for each note, invoke slipbot:
   • Type: note (- prefix)
   • Source: ~ article, {title}
   • Let slipbot handle: filename, tags, links, graph update
5. Report → count of notes created

Example

Input:

# [[How to Learn Faster](https://example.com/article)]
> Get feedback more often
To learn faster we need faster feedback loops.
> Latent learning occurs without reinforcement
Testing yourself proactively speeds up learning.

Extracted notes:

1. "To learn faster we need faster feedback loops."
2. "Testing yourself proactively speeds up learning."

Slipbot calls:

- To learn faster we need faster feedback loops. ~ article, How to Learn Faster
- Testing yourself proactively speeds up learning. ~ article, How to Learn Faster

Edge Cases

• No user notes (only > lines): Report "no notes to import"
• Multi-line user notes: Treat each paragraph as separate note
• Title with special chars: Preserve as-is for source metadata