# Seed

Add a source file to the processing queue.

- Repository: https://github.com/agenticnotetaking/arscontexta (3518 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-02-24
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add agenticnotetaking/arscontexta --skill seed -g -a claude-code -y`
Codex: `npx skills add agenticnotetaking/arscontexta --skill seed -g -a codex -y`
Cursor: `npx skills add agenticnotetaking/arscontexta --skill seed -g -a cursor -y`
Gemini CLI: `npx skills add agenticnotetaking/arscontexta --skill seed -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add agenticnotetaking/arscontexta`

## Description

Add a source file to the processing queue. Checks for duplicates, creates archive folder, moves source from inbox, creates extract task, and updates queue. Triggers on "/seed", "/seed [file]", "queue this for processing".

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

## EXECUTE NOW

**Target: $ARGUMENTS**

The target MUST be a file path. If no target provided, list {DOMAIN:inbox}/ contents and ask which to seed.

### Step 0: Read Vocabulary

Read `ops/derivation-manifest.md` (or fall back to `ops/derivation.md`) for domain vocabulary mapping. All output must use domain-native terms. If neither file exists, use universal terms.

**START NOW.** Seed the source file into the processing queue.

---

## Step 1: Validate Source

Confirm the target file exists. If it does not, check common locations:
- `{DOMAIN:inbox}/{filename}`
- Subdirectories of {DOMAIN:inbox}/

If the file cannot be found, report error and stop:
```
ERROR: Source file not found: {path}
Checked: {locations checked}
```

Read the file to understand:
- **Content type**: what kind of material is this? (research article, documentation, transcript, etc.)
- **Size**: line count (affects chunking decisions in /reduce)
- **Format**: markdown, plain text, structured data

## Step 2: Duplicate Detection

Check if this source has already been processed. Two levels of detection:

### 2a. Filename Match

Search the queue file and archive folders for matching source names:

```bash
SOURCE_NAME=$(basename "$FILE" .md | tr ' ' '-' | tr '[:upper:]' '[:lower:]')

# Check queue for existing entry
# Search in ops/queue.yaml, ops/queue/queue.yaml, or ops/queue/queue.json
grep -l "$SOURCE_NAME" ops/queue*.yaml ops/queue/*.yaml ops/queue/*.json 2>/dev/null

# Check archive folders
ls -d ops/queue/archive/*-${SOURCE_NAME}* 2>/dev/null
```

### 2b. Content Similarity (if semantic search available)

If semantic search is available (qmd MCP tools or CLI), check for content overlap:

```
mcp__qmd__search query="claims from {source filename}" limit=5
```

Or via keyword search in the {DOMAIN:notes}/ directory:
```bash
grep -rl "{key terms from source title}" {DOMAIN:notes}/ 2>/dev/null | head -5
```

### 2c. Report Duplicates

The rest: https://github.com/agenticnotetaking/arscontexta/blob/HEAD/skill-sources/seed/SKILL.md