firecrawl-search

Name: firecrawl-search
Author: firecrawl

byfirecrawl· 131 skills

Installs

77k

Stars

539

Forks

How to install firecrawl-search?

firecrawl/cli/firecrawl-search

$npx -y skills add firecrawl/cli --skill firecrawl-search

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Use this skill

Run `npx skills use "https://github.com/firecrawl/cli" --skill "firecrawl/cli/firecrawl-search"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the whole pack

Use the skills in "https://github.com/firecrawl/cli" that are relevant to the current task. Run `npx skills add "https://github.com/firecrawl/cli"` and select the relevant skills, then follow their instructions.

Files · 1

View on GitHub

SKILL.md

1	# firecrawl search
2
3	Web search with optional content scraping. Returns search results as JSON, optionally with full page content.
4
5	## When to use
6
7	- You don't have a specific URL yet
8	- You need to find pages, answer questions, or discover sources
9	- First step in the [workflow escalation pattern](firecrawl-cli): search → scrape → map → crawl → interact
10
11	## Quick start
12
13	```bash
14	# Basic search
15	firecrawl search "your query" -o .firecrawl/result.json --json
16
17	# Search and scrape full page content from results
18	firecrawl search "your query" --scrape -o .firecrawl/scraped.json --json
19
20	# News from the past day
21	firecrawl search "your query" --sources news --tbs qdr:d -o .firecrawl/news.json --json
22	```
23
24	## Options
25
26	\| Option \| Description \|
27	\| ------------------------------------ \| --------------------------------------------- \|
28	\| `--limit <n>` \| Max number of results \|
29	\| `--sources <web,images,news>` \| Source types to search \|
30	\| `--categories <github,research,pdf>` \| Filter by category \|
31	\| `--tbs <qdr:h\\|d\\|w\\|m\\|y>` \| Time-based search filter \|
32	\| `--location` \| Location for search results \|
33	\| `--country <code>` \| Country code for search \|
34	\| `--scrape` \| Also scrape full page content for each result \|
35	\| `--scrape-formats` \| Formats when scraping (default: markdown) \|
36	\| `-o, --output <path>` \| Output file path \|
37	\| `--json` \| Output as JSON \|
38
39	## Tips
40
41	- `--scrape` fetches full content — don't re-scrape URLs from search results. This saves credits and avoids redundant fetches.
42	- Always write results to `.firecrawl/` with `-o` to avoid context window bloat.
43	- Use `jq` to extract URLs or titles: `jq -r '.data.web[].url' .firecrawl/search.json`
44	- Naming convention: `.firecrawl/search-{query}.json` or `.firecrawl/search-{query}-scraped.json`
45
46	## Send feedback after every search (refunds 1 credit)
47
48	Search costs 2 credits. After you've actually used the results (or decided they were useless), send structured feedback with `firecrawl search-feedback <id>`. The first feedback per search refunds 1 credit and helps us improve search quality. Do this once per search, in the background, after you finish processing the results — it does not block your main task.
49
50	Opt out: if `FIRECRAWL_NO_SEARCH_FEEDBACK=1` (or `FIRECRAWL_DISABLE_SEARCH_FEEDBACK=1`) is set, the CLI silently skips the call and never sends anything. Respect that — do not try to work around it. (Team admins can also disable this server-side; the API will return `feedbackErrorCode: "TEAM_OPTED_OUT"` and the CLI will exit 0 silently.)
51
52	Rules to know before you call this:
53
54	- Time window: must be sent within ~2 minutes of the search. Late feedback is rejected.
55	- `--missing-content` is the most important field. It's a list of _specific pieces_ of content you expected but did not find. One topic per entry — do not pack multiple topics into one string. These aggregate across teams and tell us what to index next.
56	- Substantive content required (zero-effort feedback is rejected with HTTP 400):
57	- `good` → must include at least one `--valuable-sources` entry.
58	- `partial` → must include `--valuable-sources` or `--missing-content`.
59	- `bad` → must include `--missing-content` or `--query-suggestions`.
60	- Daily refund cap (per team, per UTC day, default 100 credits). Once your team has been refunded 100 credits today, further submissions still record feedback but no longer refund credits. The response includes `creditsRefundedToday` / `dailyRefundCap` / `dailyCapReached`. When `dailyCapReached: true`, stop calling `search-feedback` for the rest of the UTC day — it won't refund anything and you're wasting bandwidth.
61	- Idempotent: re-submitting for the same search id returns success but no extra refund.
62	- `--silent &` is the right pattern — exit code 0 even on failure, so a rejected/expired call never crashes your pipeline.
63
64	Read the search response's `id`:
65
66	```bash
67	SEARCH_ID=$(jq -r '.id' .firecrawl/search-react-hooks.json)
68	```
69
70	Then send feedback. Pick the rating that matches what actually happened:
71
72	```bash
73	# Results were useful, with notes on what was still missing
74	firecrawl search-feedback "$SEARCH_ID" \
75	--rating good \
76	--valuable-sources '[{"url":"https://react.dev/reference/react/hooks","reason":"Most authoritative"}]' \
77	--missing-content '[
78	{"topic":"useDeferredValue","description":"No example of useDeferredValue with Suspense"},
79	{"topic":"useTransition","description":"No coverage of useTransition for routing"}
80	]' \
81	--query-suggestions "Boost react.dev for queries about react hooks" \
82	--silent &
83
84	# Results were partially useful — multiple missing topics, one entry per topic
85	firecrawl search-feedback "$SEARCH_ID" \
86	--rating partial \
87	--missing-content '[
88	{"topic":"useDeferredValue"},
89	{"topic":"useTransition","description":"Need React 18+ examples"},
90	{"topic":"Server Components hooks"}
91	]' \
92	--silent &
93
94	# Quick form — repeat --missing-content or use comma-separated topics
95	firecrawl search-feedback "$SEARCH_ID" \
96	--rating bad \
97	--missing-content "official api reference: missing v2 endpoints" \
98	--missing-content "code examples in python" \
99	--silent &
100	```
101
102	`--missing-content` accepts:
103
104	- JSON array of `{topic, description?}` objects (richest, preferred)
105	- `"topic: description"` strings (shorthand)
106	- Plain `"topic1, topic2, topic3"` (when you only have topic names)
107	- Repeated `--missing-content` flags
108
109	`--silent` suppresses output and `&` runs it in the background so feedback never blocks you.
110
111	## See also
112
113	- [firecrawl-scrape](../firecrawl-scrape/SKILL.md) — scrape a specific URL
114	- [firecrawl-map](../firecrawl-map/SKILL.md) — discover URLs within a site
115	- [firecrawl-crawl](../firecrawl-crawl/SKILL.md) — bulk extract from a site

6 picks

Type

Run `npx skills use "https://github.com/firecrawl/cli" --skill "firecrawl/cli/firecrawl-search"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.

Use the skills in "https://github.com/firecrawl/cli" that are relevant to the current task. Run `npx skills add "https://github.com/firecrawl/cli"` and select the relevant skills, then follow their instructions.

firecrawl-search

How to install firecrawl-search?

Related

firecrawl-search

How to install firecrawl-search?

Related