Brave Search
badlogic/pi-skills
Web search and content extraction via Brave Search API. An agent skill from badlogic/pi-skills.
A skill your agent uses FOR news search. An agent skill from brave/brave-search-skills.
$ npx skills add brave/brave-search-skills --skill news-search -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brave/brave-search-skills news-search --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/brave/brave-search-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/news-search .claude/skills/news-search && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "news-search" agent skill from https://github.com/brave/brave-search-skills/tree/main/skills/news-search into .claude/skills/news-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "news-search", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/brave/brave-search-skills/tree/main/skills/news-searchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add brave/brave-search-skills --skill news-search -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brave/brave-search-skills news-search --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brave/brave-search-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/news-search .agents/skills/news-search && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "news-search" agent skill from https://github.com/brave/brave-search-skills/tree/main/skills/news-search into .agents/skills/news-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "news-search", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add brave/brave-search-skills --skill news-search -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brave/brave-search-skills news-search --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brave/brave-search-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/news-search .cursor/skills/news-search && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "news-search" agent skill from https://github.com/brave/brave-search-skills/tree/main/skills/news-search into .cursor/skills/news-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "news-search", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/brave/brave-search-skills.git --path skills/news-search--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add brave/brave-search-skills --skill news-search -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brave/brave-search-skills news-search --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brave/brave-search-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/news-search .gemini/skills/news-search && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "news-search" agent skill from https://github.com/brave/brave-search-skills/tree/main/skills/news-search into .gemini/skills/news-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "news-search", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install brave/brave-search-skills news-searchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add brave/brave-search-skills --skill news-search -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/brave/brave-search-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/news-search .github/skills/news-search && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "news-search" agent skill from https://github.com/brave/brave-search-skills/tree/main/skills/news-search into .github/skills/news-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "news-search", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add brave/brave-search-skills --skill news-search -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install brave/brave-search-skills news-search --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brave/brave-search-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/news-search .opencode/skills/news-search && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "news-search" agent skill from https://github.com/brave/brave-search-skills/tree/main/skills/news-search into .opencode/skills/news-search/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "news-search", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
news-searchA skill your agent uses FOR news search. An agent skill from brave/brave-search-skills.
News Search is an agent skill from brave/brave-search-skills. USE FOR news search. Returns news articles with title, URL, description, age, thumbnail, profile. Supports freshness and date range filtering, SafeSearch filter and Goggles for custom ranking.
Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Productivity & Automation. It works with Brave Search API. The repository describes itself as: Official skills for using Brave Search API with AI coding agents. The licence is MIT.
Read from SKILL.md and the folder at commit 62793e0. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
curlFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
api.search.brave.comimgs.search.brave.comraw.githubusercontent.comAlso links to:
search.brave.comapi-dashboard.search.brave.comgithub.comFrom URLs in SKILL.md, links to its own repository left out.
Names these keys or tokens, usually read from environment variables:
BRAVE_SEARCH_API_KEYAPI_KEYFrom names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
News Search loads about 2k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 592 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from brave/brave-search-skills at commit 62793e0, republished under its MIT licence (© brave). 592 words, ~2,029 tokens.
.claude/skills/news-search/SKILL.md (or your agent's skills folder).Requires API Key: Get one at https://api.search.brave.com
Plan: Included in the Search plan. See https://api-dashboard.search.brave.com/app/subscriptions/subscribe
curl -s "https://api.search.brave.com/res/v1/news/search?q=space+exploration" \
-H "Accept: application/json" \
-H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}"curl -s "https://api.search.brave.com/res/v1/news/search" \
-H "Accept: application/json" \
-H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}" \
-G \
--data-urlencode "q=cybersecurity" \
--data-urlencode "country=US" \
--data-urlencode "freshness=pd" \
--data-urlencode "count=20"curl -s "https://api.search.brave.com/res/v1/news/search" \
-H "Accept: application/json" \
-H "X-Subscription-Token: ${BRAVE_SEARCH_API_KEY}" \
-G \
--data-urlencode "q=climate summit" \
--data-urlencode "freshness=2026-01-01to2026-01-31"GET https://api.search.brave.com/res/v1/news/search
POST https://api.search.brave.com/res/v1/news/searchAuthentication: X-Subscription-Token: <API_KEY> header
Note: Both GET and POST are supported. POST is useful for long queries or complex Goggles.
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
q | string | Yes | - | Search query (1-400 chars, max 50 words) |
country | string | No | US | Search country (2-letter country code or ALL) |
search_lang | string | No | en | Language preference (2+ char language code) |
ui_lang | string | No | en-US | UI language (e.g., "en-US") |
count | int | No | 20 | Number of results (1-50) |
offset | int | No | 0 | Page offset (0-9) |
safesearch | string | No | strict | Adult content filter (off/moderate/strict) |
freshness | string | No | - | Time filter (pd/pw/pm/py or date range) |
spellcheck | bool | No | true | Auto-correct query |
extra_snippets | bool | No | - | Up to 5 additional excerpts per result |
goggles | string or array | No | - | Custom ranking filter (URL or inline; repeat param for multiple) |
operators | bool | No | true | Apply search operators |
include_fetch_metadata | bool | No | false | Include fetch timestamps in results |
| Value | Description |
|---|---|
pd | Past day (24 hours) - ideal for breaking news |
pw | Past week (7 days) |
pm | Past month (31 days) |
py | Past year (365 days) |
YYYY-MM-DDtoYYYY-MM-DD | Custom date range |
{
"type": "news",
"query": {
"original": "space exploration"
},
"results": [
{
"type": "news_result",
"title": "New Developments in Space Exploration",
"url": "https://news.example.com/space-exploration",
"description": "Recent missions have advanced our understanding of...",
"age": "2 hours ago",
"page_age": "2026-01-15T14:30:00",
"page_fetched": "2026-01-15T15:00:00Z",
"meta_url": {
"scheme": "https",
"netloc": "news.example.com",
"hostname": "news.example.com",
"favicon": "https://imgs.search.brave.com/favicon/news.example.com",
"path": "/space-exploration"
},
"profile": {
"name": "Example Outlet",
"url": "https://news.example.com/space-exploration"
},
"thumbnail": {
"src": "https://imgs.search.brave.com/..."
}
}
]
}| Field | Type | Description |
|---|---|---|
type | string | Always "news" |
query.original | string | The original search query |
query.altered | string? | Spellcheck-corrected query (if changed) |
query.cleaned | string? | Cleaned/normalized query from spellchecker |
query.spellcheck_off | bool? | Whether spellcheck was disabled |
query.show_strict_warning | bool? | True if strict safesearch blocked results |
query.search_operators | object? | Applied search operators |
query.search_operators.applied | bool | Whether operators were applied |
query.search_operators.cleaned_query | string? | Query after operator processing |
query.search_operators.sites | list[str]? | Domains from site: operators |
results[].type | string | Always "news_result" |
results[].title | string | Article title |
results[].url | string | Source URL of the article |
results[].description | string? | Article description/summary |
results[].age | string? | Human-readable age (e.g. "2 hours ago") |
results[].page_age | string? | Publication date from source (ISO datetime) |
results[].page_fetched | string? | When page was last fetched (ISO datetime) |
results[].fetched_content_timestamp | int? | Fetch timestamp (only with include_fetch_metadata=true) |
results[].meta_url.scheme | string? | URL protocol scheme |
results[].meta_url.netloc | string? | Network location |
results[].meta_url.hostname | string? | Lowercased domain name |
results[].meta_url.favicon | string? | Favicon URL |
results[].meta_url.path | string? | URL path |
results[].thumbnail.src | string | Served thumbnail URL |
results[].thumbnail.original | string? | Original thumbnail URL |
results[].extra_snippets | list[str]? | Up to 5 additional excerpts per result |
results[].profile.name | string? | Name of the site |
results[].profile.url | string? | The original URL where the profile is available |
results[].profile.long_name | string? | The long name of the site |
results[].profile.img | string? | The served image URL representing the profile |
Goggles let you re-rank news results — boost trusted outlets or suppress unwanted sources.
| Method | Example |
|---|---|
| Hosted | --data-urlencode "goggles=https://raw.githubusercontent.com/brave/goggles-quickstart/main/goggles/hacker_news.goggle" |
| Inline | --data-urlencode 'goggles=$discard\n$site=example.com' |
Hosted goggles must be on GitHub/GitLab, include
! name:,! description:,! author:headers, and be registered at https://search.brave.com/goggles/create. Inline rules need no registration.
Syntax: Rules start with $ + comma-separated options. Actions (pick one): discard, boost[=N], downrank[=N] — N is an integer 1–10. Site filter: site=DOMAIN. Example: $site=example.com,boost=3. Separate rules with \n (%0A).
Allow list: $discard\n$site=docs.python.org\n$site=developer.mozilla.org — Block list: $discard,site=pinterest.com\n$discard,site=quora.com
Resources: Discover · Syntax · Quickstart
Use search operators to refine results:
site:local-paper.com - Limit to specific news site"exact phrase" - Match exact phrase-exclude - Exclude termSet operators=false to disable operator parsing.
freshness=pd for the most recent articles on a topic.freshness=YYYY-MM-DDtoYYYY-MM-DD to find articles from specific time periods.country, search_lang, and ui_lang for cross-locale results.include_fetch_metadata=true for fetched_content_timestamp on each result.strictoffset (0-9) with countextra_snippets=true© brave, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/news-search of brave/brave-search-skills.
Open the folder on GitHubat commit 62793e0
News Search next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| News Search this skillbrave/brave-search-skills | 183 | — | ~2k | Automated safety check: Pass | MIT | |
| Brave Searchbadlogic/pi-skills | 2.6k | 5 repos | ~592 | Automated safety check: Pass | MIT | |
| Web Searchtmustier/pi-for-excel | 434 | — | ~410 | Automated safety check: Pass | MIT | |
| Web Search Bravejwynia/agent-skills | 170 | — | ~2k | Automated safety check: Pass | MIT | |
| Brave SearchLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.6k | Automated safety check: Pass | MIT | |
| Brave SearchAnil-matcha/awesome-muse-connectors | 1.3k | — | ~440 | Automated safety check: Pass | MIT |
badlogic/pi-skills
Web search and content extraction via Brave Search API. An agent skill from badlogic/pi-skills.
tmustier/pi-for-excel
Search the public web for up-to-date facts. An agent skill from tmustier/pi-for-excel.
jwynia/agent-skills
Search the web using Brave Search API for fast, privacy-respecting results with localization, freshness filtering, and extra snippets.
LeoYeAI/openclaw-master-skills
Brave Search API integration with managed authentication. An agent skill from LeoYeAI/openclaw-master-skills.
Anil-matcha/awesome-muse-connectors
Independent web search from Brave's own index. An agent skill from Anil-matcha/awesome-muse-connectors.
aiskillstore/marketplace
Search the web with multiple output formats using the Qryma API.
brave/brave-search-skills
Calls the Brave Search Answers endpoint for AI-grounded, cited answers, either a fast single-search reply or a slower multi-search deep research run.
brave/brave-search-skills
Searches images through the Brave Search API and returns titles, source pages, thumbnails and original image URLs, with a SafeSearch filter and up to 200 results.
brave/brave-search-skills
Documents Brave's LLM Context API, which returns pre-extracted, ranked web page content for grounding agent and RAG answers, with GET and POST calls and Goggles filters.
brave/brave-search-skills
Fetches AI-written text descriptions for local places from the Brave Search API, using place IDs returned by an earlier local search.
brave/brave-search-skills
Looks up businesses, points of interest, addresses and streets through the Brave Search place endpoint, returning contact details, ratings and hours in one call.
brave/brave-search-skills
Looks up full details for local businesses and places, including ratings, hours and contact information, from Brave Search API point-of-interest IDs.
Works with
Categories
A skill your agent uses FOR news search. An agent skill from brave/brave-search-skills. News Search is an agent skill from brave/brave-search-skills. USE FOR news search.
News Search fits situations like: productivity & Automation work in your project.
Run `npx skills add brave/brave-search-skills --skill news-search -a claude-code`. Or copy the skill folder (skills/news-search in brave/brave-search-skills) into .claude/skills/news-search in your project. Claude Code loads it when a task matches its description.
Run `npx skills add brave/brave-search-skills --skill news-search -a codex`. Or copy the skill folder (skills/news-search in brave/brave-search-skills) into .agents/skills/news-search in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add brave/brave-search-skills --skill news-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/news-search, .gemini/skills/news-search, .github/skills/news-search and .opencode/skills/news-search in your project.
Going by SKILL.md and its folder, News Search needs the command-line tools its instructions call (curl) and credentials named BRAVE_SEARCH_API_KEY and API_KEY. Our summary lists: A credential in BRAVE_SEARCH_API_KEY; A credential in API_KEY.
SKILL.md names 6 domains. In commands or code: api.search.brave.com, imgs.search.brave.com and raw.githubusercontent.com; the agent is likely to contact these when it follows the instructions. As links in the text: search.brave.com, api-dashboard.search.brave.com and github.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
News Search is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with News Search: Brave Search (badlogic/pi-skills, 2.6k stars), Web Search (tmustier/pi-for-excel, 434 stars), Web Search Brave (jwynia/agent-skills, 170 stars) and Brave Search (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
brave (a GitHub organization) maintains it in brave/brave-search-skills, which has 183 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on September 23, 2026.
Source: brave/brave-search-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.