From 4521e97e6e824c5ad0ac6355219434a8aa8669c5 Mon Sep 17 00:00:00 2001 From: Richard Oliver Bray Date: Fri, 24 Jul 2026 12:13:25 +0100 Subject: [PATCH 1/3] docs(skills): document --highlights/--no-highlights in firecrawl-search CLI 1.19.27 added these flags for the new relevance-model search excerpts, but the skill doc never mentioned them. --- skills/firecrawl-search/SKILL.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/skills/firecrawl-search/SKILL.md b/skills/firecrawl-search/SKILL.md index 87b426cf92..16e7cd1152 100644 --- a/skills/firecrawl-search/SKILL.md +++ b/skills/firecrawl-search/SKILL.md @@ -42,11 +42,13 @@ firecrawl search "your query" --sources news --tbs qdr:d -o .firecrawl/news.json | `--country ` | Country code for search | | `--scrape` | Also scrape full page content for each result | | `--scrape-formats` | Formats when scraping (default: markdown) | +| `--highlights` / `--no-highlights` | Query-relevant excerpts vs. original snippets | | `-o, --output ` | Output file path | | `--json` | Output as JSON | ## Tips +- **`--highlights` is on by default.** Firecrawl's relevance model scores every paragraph/list/table on the page against your query and returns only the excerpts that answer it, instead of full-page noise. Use `--no-highlights` to get the original snippets. This is a server-side upgrade (works with or without the flag), but the flag lets you control it explicitly. - **`--scrape` fetches full content** — don't re-scrape URLs from search results. This saves credits and avoids redundant fetches. - Always write results to `.firecrawl/` with `-o` to avoid context window bloat. - Use `jq` to extract URLs or titles: `jq -r '.data.web[].url' .firecrawl/search.json` From 0c944c2385d87415fd9f8bf4154438c895f084a5 Mon Sep 17 00:00:00 2001 From: Richard Oliver Bray Date: Thu, 6 Aug 2026 11:38:01 +0100 Subject: [PATCH 2/3] docs(skills): trim highlights tip to match surrounding style --- skills/firecrawl-search/SKILL.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/skills/firecrawl-search/SKILL.md b/skills/firecrawl-search/SKILL.md index 84d8d398f3..641ca45ca9 100644 --- a/skills/firecrawl-search/SKILL.md +++ b/skills/firecrawl-search/SKILL.md @@ -75,7 +75,7 @@ Each result holds `id`, `type` (`issue`, `pull_request`, `readme`, `doc`), ## Tips -- **`--highlights` is on by default.** Firecrawl's relevance model scores every paragraph/list/table on the page against your query and returns only the excerpts that answer it, instead of full-page noise. Use `--no-highlights` to get the original snippets. This is a server-side upgrade (works with or without the flag), but the flag lets you control it explicitly. +- **`--highlights` is on by default:** results are query-relevant excerpts, not full-page snippets. Use `--no-highlights` for the original snippets. - **`--scrape` fetches full content** — don't re-scrape URLs from search results. This saves credits and avoids redundant fetches. - Always write results to `.firecrawl/` with `-o` to avoid context window bloat. - Use `jq` to extract URLs or titles: `jq -r '.data.web[].url' .firecrawl/search.json` From f718a45a93903591a163a9f6af03b2f54634d757 Mon Sep 17 00:00:00 2001 From: Richard Oliver Bray Date: Thu, 6 Aug 2026 11:39:46 +0100 Subject: [PATCH 3/3] docs(skills): tighten highlights tip wording --- skills/firecrawl-search/SKILL.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/skills/firecrawl-search/SKILL.md b/skills/firecrawl-search/SKILL.md index 641ca45ca9..894ba9c061 100644 --- a/skills/firecrawl-search/SKILL.md +++ b/skills/firecrawl-search/SKILL.md @@ -75,7 +75,7 @@ Each result holds `id`, `type` (`issue`, `pull_request`, `readme`, `doc`), ## Tips -- **`--highlights` is on by default:** results are query-relevant excerpts, not full-page snippets. Use `--no-highlights` for the original snippets. +- **`--highlights` on by default:** results are query-relevant excerpts, not full-page snippets. Use `--no-highlights` for the original snippets. - **`--scrape` fetches full content** — don't re-scrape URLs from search results. This saves credits and avoids redundant fetches. - Always write results to `.firecrawl/` with `-o` to avoid context window bloat. - Use `jq` to extract URLs or titles: `jq -r '.data.web[].url' .firecrawl/search.json`