brave

Review code for quality, root cause analysis, and fix confidence. Supports PR review and local review of uncommitted/branch changes. Default mode is local (reviews current branch changes). Triggers on: review pr, review this pr, /review <pr_url>, /review…

Run all preflight checks (format, gn_check, presubmit, build, tests) to make sure the current work is ready for review.

Implement review feedback on a PR. Checks out the branch, applies reviewer-requested changes, runs preflight, commits, and pushes. Triggers on: impl-review, implement review, implement review feedback, address review comments.

Add a new best practice to the appropriate doc. Checks for duplicates, assigns stable IDs, creates new category docs if needed. Triggers on: add best practice, new best practice, add bp, new bp.

"Check and fix milestones on PRs and their associated issues. Sets PR milestones based on the branch they merged into, and issue milestones based on the smallest version with a merged uplift. Triggers on: check milestones, fix milestones, /check-milestones."

Check if a failing test is a known upstream flake in Chromium's LUCI Analysis database. Provides flakiness statistics, verdict, and recommendation for filter file decisions. Triggers on: check upstream flake, is this test flaky upstream, check luci flakiness,…

Delete local branches whose PRs have been merged upstream. Checks GitHub PR status for each branch. Triggers on: clean branches, delete merged branches, prune branches, branch cleanup.

For an external contributor's open PRs to brave/brave-core, ensure the `sync-and-rebase-pr-from-fork.yml` workflow has been dispatched for each PR's latest commit SHA — so a `contributor-*` draft PR exists inside brave/brave-core and CI can run. Invoke when…

Identify and safely remove expired Chromium histograms (dead metrics/technical debt). Use this skill when a contributor asks to clean up metrics, fix code health issues related to histograms, remove obsolete code, or work on a histogram cleanup task.

Extension pipeline to bump expiration dates of Chromium UMA histograms.

Orchestrator for the "Code Health Hub" framework. Trigger only when the user refers to the Hub or asks to see "available cleanup tasks" within the Chromium technical debt reduction system.

Identify and clean up inline fully qualified Java names (FQNs) in first-party code, replacing them with standard imports.

Add missing LINT.IfChange(...) / LINT.ThenChange(...) guards to enums in C++/Java and XML to keep them in sync. Trigger this skill ONLY when a contributor explicitly asks to add lint guards or synchronize enums using LINT guards.

Replace anonymous classes with lambdas where applicable (SAM interfaces)

Multi-agent consensus-driven code review. Audits changes using security, performance, and style checkers.

Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.

USE FOR AI-grounded answers via OpenAI-compatible /chat/completions. Two modes: single-search (fast) or deep research (enable_research=true, thorough multi-search). Streaming/blocking. Citations.

USE FOR RAG/LLM grounding. Returns pre-extracted web content (text, tables, code) optimized for LLMs. GET + POST. Adjust max_tokens/count based on complexity. Supports Goggles, local/POI. For AI answers use answers. Recommended for anyone building AI/agentic…

USE FOR getting AI-generated POI text descriptions. Requires POI IDs from local-place-search, or from web-search with result_filter=locations. Returns markdown descriptions grounded in web search context. Max 20 IDs per request.

USE FOR finding places in the physical world - businesses, POIs, street addresses, cities and streets. Results carry address, coordinates, rating, opening hours and phone, so basic details need no follow-up call. Standalone - no POI IDs or prior web search…

USE FOR getting local business/POI details. Requires POI IDs from local-place-search, or from web-search with result_filter=locations. Returns full business information including ratings, hours, contact info. Max 20 IDs.

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.

USE FOR video search. Returns videos with title, URL, thumbnail, duration, view count, creator. Supports freshness filters, SafeSearch, pagination.

USE FOR web search. Returns ranked results with snippets, URLs, thumbnails. Supports freshness filters, SafeSearch, Goggles for custom ranking, pagination. Primary search endpoint.

Scan org repos for open Dependabot alerts at or above a severity threshold and build notification messages for maintainers. Use when the user wants to check or nudge about Dependabot vulnerabilities.

Auto-detect top maintainers for each repo in an org and set the maintainers custom property via the GitHub API. Use when the user wants to populate or update maintainer metadata.

Validate metadata fields (author, source, category) in opengrep/semgrep YAML rule files. Use when the user wants to lint or check rule quality.

Clean up stale security-action Slack messages based on review signals (reactions, label removal, resolved threads). Use when the user wants to clean old notifications from a Slack channel.

Delete Slack messages from a channel filtered by bot username and repository names. Use when the user wants to bulk-delete bot messages for specific repos.

Auto-dismiss Dependabot alerts matching configurable hotwords (e.g. DoS) or a GHSA/CVE dismiss list. Use when the user wants to bulk-dismiss low-priority Dependabot alerts.

Fetch and parse a JSON config file from a GitHub repository. Use when the user wants to read a configuration file from a remote repo.

List all repositories in a GitHub org with their maintainers custom property. Use when the user wants to see who maintains each repo.