Brave Search
ListedSearches Badlogic's internal knowledge base for creative writing prompts, game design ideas, and worldbuilding inspiration.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add badlogic/pi-skills --skill brave-search -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
badlogic
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.
No undeclared network calls: failed
Contacts 4 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: api-dashboard.search.brave.com, api.search.brave.com, doc.rust-lang.org, opencollective.com.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
Hosts contacted
doc.rust-lang.orgundeclaredgithub.comsource hostopencollective.comundeclaredapi-dashboard.search.brave.comundeclaredapi.search.brave.comundeclaredWhat it found (3 of 9)
- brave-search/content.js:15contacts doc.rust-lang.org
console.log(" content.js https://doc.rust-lang.org/book/ch04-01-what-is-ownership.html"); - brave-search/package-lock.json:61contacts opencollective.com
"url": "https://opencollective.com/csstools" - brave-search/package-lock.json:80contacts opencollective.com
"url": "https://opencollective.com/csstools"
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned badlogic/pi-skills at 90bb51cae3.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 90bb51cae3
- Manifest
- brave-search/SKILL.md
- Scanned
- 5 files, 994 lines
About this skill
What it does
The badlogic-brave-search skill enables AI agents to perform live web searches using the Brave search engine. It allows agents to retrieve current information, verify facts from recent sources, and answer queries that require up-to-date data beyond static training sets.
When to use it
- Fact-checking: Verify news events or statistics published after your knowledge cutoff.
- Real-time data: Retrieve live prices, weather updates, or stock market trends.
- Current events: Investigate breaking news stories or recent technological developments.
- Source verification: Cross-reference information found in documents with current online discussions.
Key capabilities
- Executes queries directly against the Brave search engine index.
- Returns results relevant to the specific question asked by the user.
- Integrates seamlessly into the
badlogic/pi-skillsframework for agent workflows.
Example prompts
- "What are the latest updates on the new iPhone release schedule?"
- "Search for current reviews of the best running shoes available this month."
- "Find recent news articles about changes to the US tax code in 2024."
Tips & gotchas
This skill relies entirely on internet connectivity; it will not function if the agent has no network access. While it provides current data, always review the specific search results returned by the agent to ensure they meet your accuracy standards, as search engines can occasionally return outdated or irrelevant snippets.