brave-search
Brave Search API for web search. Use when user says "search web", "Brave search", or asks to "find on web" without specifying Google.
What this skill does
## Troubleshooting
If requests fail, run `zero doctor check-connector --env-name BRAVE_API_KEY` or `zero doctor check-connector --url https://api.search.brave.com/res/v1/web/search --method GET`
## How to Use
All examples below assume you have `BRAVE_API_KEY` set.
The base URL for the API is:
- `https://api.search.brave.com/res/v1`
Authentication uses the `X-Subscription-Token` header.
### 1. Basic Web Search
Search the web with a query:
```bash
curl -s "https://api.search.brave.com/res/v1/web/search?q=artificial+intelligence" -H "Accept: application/json" -H "X-Subscription-Token: $BRAVE_API_KEY" | jq '.web.results[:3] | .[] | {title, url, description}
```
### 2. Web Search with Parameters
Customize search with country, language, and result count:
Write to `/tmp/brave_query.txt`:
```
best restaurants
```
```bash
curl -s "https://api.search.brave.com/res/v1/web/search" -H "Accept: application/json" -H "X-Subscription-Token: $BRAVE_API_KEY" -G --data-urlencode "q@/tmp/brave_query.txt" -d "country=us" -d "search_lang=en" -d "count=5" | jq '.web.results[] | {title, url}'
```
**Parameters:**
- `q`: Search query (required, max 400 chars / 50 words)
- `country`: Two-letter country code (e.g., `us`, `gb`, `jp`)
- `search_lang`: Language code (e.g., `en`, `zh`, `ja`)
- `count`: Results per page (1-20, default: 10)
- `offset`: Pagination offset (0-9, default: 0)
### 3. Safe Search Filter
Control explicit content filtering:
Write to `/tmp/brave_query.txt`:
```
programming tutorials
```
```bash
curl -s "https://api.search.brave.com/res/v1/web/search" -H "Accept: application/json" -H "X-Subscription-Token: $BRAVE_API_KEY" -G --data-urlencode "q@/tmp/brave_query.txt" -d "safesearch=strict" | jq '.web.results[:3] | .[] | {title, url}
```
**Options:** `off`, `strict` (Note: Image/Video search only supports `off` and `strict`)
### 4. Freshness Filter
Filter results by time:
Write to `/tmp/brave_query.txt`:
```
tech news
```
```bash
curl -s "https://api.search.brave.com/res/v1/web/search" -H "Accept: application/json" -H "X-Subscription-Token: $BRAVE_API_KEY" -G --data-urlencode "q@/tmp/brave_query.txt" -d "freshness=pd" | jq '.web.results[:3] | .[] | {title, url, age}
```
**Options:**
- `pd`: Past day (24 hours)
- `pw`: Past week
- `pm`: Past month
- `py`: Past year
- `YYYY-MM-DDtoYYYY-MM-DD`: Custom date range
### 5. Image Search
Search for images:
Write to `/tmp/brave_query.txt`:
```
sunset beach
```
```bash
curl -s "https://api.search.brave.com/res/v1/images/search" -H "Accept: application/json" -H "X-Subscription-Token: $BRAVE_API_KEY" -G --data-urlencode "q@/tmp/brave_query.txt" -d "count=5" -d "safesearch=strict" | jq '.results[] | {title, url: .properties.url, thumbnail: .thumbnail.src}
```
Image search supports up to 200 results per request.
### 6. Video Search
Search for videos:
Write to `/tmp/brave_query.txt`:
```
learn python
```
```bash
curl -s "https://api.search.brave.com/res/v1/videos/search" -H "Accept: application/json" -H "X-Subscription-Token: $BRAVE_API_KEY" -G --data-urlencode "q@/tmp/brave_query.txt" -d "count=5" | jq '.results[] | {title, url, duration}
```
Video search supports up to 50 results per request.
### 7. News Search
Search for recent news articles:
Write to `/tmp/brave_query.txt`:
```
technology
```
```bash
curl -s "https://api.search.brave.com/res/v1/news/search" -H "Accept: application/json" -H "X-Subscription-Token: $BRAVE_API_KEY" -G --data-urlencode "q@/tmp/brave_query.txt" -d "count=3" | jq '.results[:3] | .[] | {title, url, age}
```
News search defaults to past day (`pd`) freshness.
### 8. Pagination
Get more results with offset:
Write to `/tmp/brave_query.txt`:
```
machine learning
```
```bash
curl -s "https://api.search.brave.com/res/v1/web/search" -H "Accept: application/json" -H "X-Subscription-Token: $BRAVE_API_KEY" -G --data-urlencode "q@/tmp/brave_query.txt" -d "count=10" -d "offset=1" | jq '.web.results[] | {title, url}
```
`offset=1` skips the first page of results.
### 9. Get Raw JSON Response
View the full response structure:
```bash
curl -s "https://api.search.brave.com/res/v1/web/search?q=test" -H "Accept: application/json" -H "X-Subscription-Token: $BRAVE_API_KEY" | jq 'keys'
```
Response includes: `query`, `mixed`, `type`, `web`, `videos`, `news`, etc.
## Response Structure
### Web Search Response
```json
{
"query": { "original": "search term" },
"web": {
"results": [
{
"title": "Page Title",
"url": "https://example.com",
"description": "Page description...",
"age": "2 days ago"
}
]
}
}
```
### Image Search Response
```json
{
"results": [
{
"title": "Image Title",
"properties": { "url": "https://..." },
"thumbnail": { "src": "https://..." }
}
]
}
```
## Guidelines
1. **URL encode queries**: Use `--data-urlencode` for special characters
2. **Respect rate limits**: Free tier is 1 query/second
3. **Use freshness for news**: Time-sensitive searches benefit from `pd` or `pw`
4. **Pagination limit**: Maximum offset is 9 (100 results total with count=10)
5. **Pro plan for local**: Local business search requires Pro subscription
6. **No tracking**: Brave doesn't track users or store search history
Related in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.