Skill

interfluence: Ingest Writing Samples

Add writing samples to the interfluence corpus. Use when the user says "ingest", "add writing sample", "analyze my writing from", "add my blog post", or provides a URL/path to their writing.

From interfluence

Install

Run in your terminal

npx claudepluginhub mistakeknot/interagency-marketplace --plugin interfluence

Tool Access

This skill is limited to using the following tools:

mcp_interfluence_corpus_addmcp_interfluence_corpus_add_textmcp_interfluence_corpus_listReadWebFetchGlob

Skill Content

Similar Skills

ui-ux-pro-max

Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.

ui-ux-pro-max

57.6k

context7-mcp

Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.

context7-plugin

51.4k

context7-mcp

Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.

context7

50.8k

Stats

Stars4

Forks0

Last CommitMar 10, 2026

Actions

View Source View Plugin View on GitHub View README

Process

Determine the source type:

File path: Read the file directly and use corpus_add with the file path
Directory: Glob for text/markdown files and ingest each one using corpus_add
URL: Use WebFetch to extract the text content, then use corpus_add_text with source "url"

For URLs (especially Substack, blogs, Notion exports):

Fetch the page and extract the main article text
Strip navigation, footers, comments, and other non-article content
Preserve the author's formatting: paragraph breaks, headers, lists, emphasis
Set the title from the page title or first heading

After ingestion:

Show the user what was added (title, word count, sample ID)
If this is the first sample, suggest running /interfluence:voice-analyze to generate a voice profile
If a voice profile already exists, suggest re-running analysis to incorporate the new sample

interfluence: Ingest Writing Samples

You are ingesting writing samples into the interfluence corpus for voice analysis.

Process

Determine the source type:
- File path: Read the file directly and use corpus_add with the file path
- Directory: Glob for text/markdown files and ingest each one using corpus_add
- URL: Use WebFetch to extract the text content, then use corpus_add_text with source "url"
For URLs (especially Substack, blogs, Notion exports):
- Fetch the page and extract the main article text
- Strip navigation, footers, comments, and other non-article content
- Preserve the author's formatting: paragraph breaks, headers, lists, emphasis
- Set the title from the page title or first heading
After ingestion:
- Show the user what was added (title, word count, sample ID)
- If this is the first sample, suggest running /interfluence:voice-analyze to generate a voice profile
- If a voice profile already exists, suggest re-running analysis to incorporate the new sample

Important

The projectDir parameter should be the current working directory
Always preserve the author's original text faithfully — do not clean up, edit, or summarize
For directories, confirm with the user before ingesting many files