🍽️ Feed Diet

Audit your information diet and get a gorgeous report showing what you actually consume.

Trigger

Activate when the user mentions any of:

• - "feed diet"
• "information diet"
• "audit my feeds"
• "what am I reading"
• "analyze my HN"
• "reading habits"
• "content diet"
• "feed report"

Instructions

Audit Mode (default)

1. 1. Determine the data source. Ask the user for one of:

1. 2. Fetch the content. Run the appropriate fetch script:

1. 3. Classify items. Pipe the fetched items through the classifier:

   cat items.jsonl | bash "$SKILL_DIR/scripts/classify.sh" > classified.jsonl
   

1. 4. Generate the report. Run the main entry point:

1. 5. Present the report to the user. The output is Markdown — render it directly.

Digest Mode (weekly curated reading)

When the user wants a filtered reading list based on their goals:

CODEBLOCK3

Quick Reference

Notes for the Agent

• - Be conversational. After presenting the report, offer observations like "Looks like you're heavy on news — want me to suggest some deeper technical feeds?"
• Suggest the digest mode if the user seems interested in filtering their reading.
• The report is the star. Don't summarize it — present it in full. It's designed to be screenshot-worthy.
• If classification seems off, mention that setting an LLM API key improves accuracy.

Discord v2 Delivery Mode (OpenClaw v2026.2.14+)

When the conversation is happening in a Discord channel:

• - Send a compact first summary (top category, diversity score, top 2 recommendations), then ask if the user wants the full report.
• Keep the first response under ~1200 characters and avoid wide category tables in the first message.
• If Discord components are available, include quick actions:

• - If components are not available, provide the same follow-ups as a numbered list.
• Prefer short follow-up chunks (<=15 lines per message) when sharing long reports.

References

• - scripts/feed-diet.sh — Main entry point
• INLINECODE7 — Hacker News story fetcher
• INLINECODE8 — OPML/RSS feed parser
• INLINECODE9 — Batch content classifier (LLM + fallback)
• INLINECODE10 — Shared utilities and formatting

Examples

Example 1: HN Audit

User: "Audit my HN reading diet — my username is tosh"

Agent runs:
CODEBLOCK4

Output: A full Markdown report with category breakdown table, top categories with sample items, surprising finds, and recommendations.

Example 2: Weekly Digest

User: "Give me a digest of what's relevant to my work on compilers and programming languages"

Agent runs:
CODEBLOCK5

Output: A curated reading list of 10-20 items ranked by relevance to the user's goals.

Example 3: RSS Feed Audit

User: "Here's my OPML file, tell me what my feed diet looks like"

Agent runs:
CODEBLOCK6