SKILL.md
$2a
Options if needed:
--after-date YYYY-MM-DDfor time-sensitive queries
--include-domains domain1.com,domain2.comto limit to specific sources
--exclude-domains domain.comto filter out noisy sources
--mode advancedfor harder questions (multi-step, agentic search). Defaultbasicis right for almost everything; only escalate when basic results are insufficient
--location us(ISO 3166-1 alpha-2) for geo-targeted results
Parsing results
Do not set max_output_tokens on the command execution — the output is already bounded by --max-results and --excerpt-max-chars-total. Capping output tokens will truncate the JSON and break parsing.
**Prefer reading from the saved -o file**, not stdout. Even bounded output regularly exceeds harness stdout limits and gets truncated. Read /tmp/$FILENAME.json for the authoritative payload. For each result, extract:
- title, url, publish_date
- Useful content from excerpts (skip navigation noise like menus, footers, "Skip to content")
Response format
CRITICAL: Every claim must have an inline citation. Use markdown links like Title pulling only from the JSON output. Never invent or guess URLs.
Synthesize a response that:
- Leads with the key answer/finding
- Includes specific facts, names, numbers, dates
- Cites every fact inline as Source Title — do not leave any claim uncited
- Organizes by theme if multiple topics
End with a Sources section listing every URL referenced:
Sources:
- [Source Title](https://example.com/article) (Feb 2026)
- [Another Source](https://example.com/other) (Jan 2026)This Sources section is mandatory. Do not omit it.
After the Sources section, mention the output file path (/tmp/$FILENAME.json) so the user knows it's available for follow-up questions.
Setup
Requires parallel-cli (installed and authenticated). If parallel-cli --version fails, or if a later command fails with an authentication error, tell the user to see https://docs.parallel.ai/integrations/cli and stop.