From syndicate-pipeline
Fetch RSS feeds from the last N days into syndicate's snapshot.db. Writes to DB.
How this skill is triggered — by the user, by Claude, or both
Slash command
/syndicate-pipeline:syndicate-ingest-rss [--days 2] [--no-fetch]When to use
When the user explicitly asks to refresh / fetch / ingest RSS feeds into syndicate. Examples: "pull RSS", "refresh syndicate rss", "ingest the last 3 days of RSS".
[--days 2] [--no-fetch]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are running RSS ingestion. This **writes to the DB** — only run when the user explicitly asked.
You are running RSS ingestion. This writes to the DB — only run when the user explicitly asked.
Default lookback is 1 day. Parse $ARGUMENTS for --days N (default 1) and
the boolean --no-fetch flag (default off — only re-parses already-cached
HTML instead of hitting the network):
cd "${SYNDICATE_REPO:-$(pwd)}" && uv run python -m pipeline.cli ingest-rss --days ${days:-1} ${no_fetch:+--no-fetch}
Output envelope:
{"ok": true, "result": {"fetched": N, "saved": N, "skipped": N, "failed": N, "errors": []}, "log_path": "logs/<date>.txt"}
One line:
✓ rss · fetched=X saved=Y skipped=Z failed=W
If failed > 0 or specific feeds appear in result.errors, list them.
A single feed returning 502 / 404 is non-fatal — syndicate's RSS pipeline
treats per-feed failures as failed += 1 and continues. Surface the
failing feed name so the user can decide whether to remove it from
config/rss_sources.json.
npx claudepluginhub aadarshvelu/syndicate --plugin syndicate-pipelineCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.