brave Skills

'Add a new best practice to the appropriate doc. Checks for duplicates, practice, new best practice, add bp, new bp.'

"Check if a failing test is a known upstream flake in Chromium's LUCI Analysis database. Provides flakiness statistics, verdict, and recommendation for upstream, check luci flakiness, upstream flake check."

'Delete local branches whose PRs have been merged upstream. Checks GitHub PR 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 the user says something like "create contributor PRs for <user>", "sync contributor PRs <list>", "run the rebase-from-fork workflow for these PRs", or passes a GitHub username / list of PR URLs/numbers.

'Audit and fix best practices docs for stale references, duplicates, obsolete docs, audit bp docs.'

'Force-push a branch and all its downstream branches to origin. Auto-detects push downstream, push chain, push all branches.'

'Implement review feedback on a PR. Checks out the branch, applies impl-review, implement review, implement review feedback, address review comments.'

'Re-run failed CI jobs for a brave/brave-core PR. Detects failure stage and retry ci, rerun ci, fix ci, re-run failed jobs, retrigger ci.'

"Create a Plaster (`rewrite/*.yaml`) config for an existing Brave-core Chromium `.patch`, authoring an intent-conveying regex match per the Plaster Dos and Don'ts, then verifying it by running `plaster.py apply` and diffing the regenerated patch against the original. Does not modify sources or create plasterize, make a plaster."

Create a pull request for the current branch using `gh`.

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

'Get PRs a user reviewed on brave/brave-core. Shows PR number, title, author, what did I review, review history.'

'Rebase a tree of dependent branches (including siblings) after upstream changes. Auto-detects downstream branches and rebases each in order. Triggers

'Review code for quality, root cause analysis, and fix confidence. Supports PR review and local review of uncommitted/branch changes. Default mode is local /review <pr_url>, /review local, /review, check bot pr quality.'

'Review PRs in the configured PR repository for best practices violations. Supports single PR (#12345), state filter (open/closed/all), and auto mode for best practices.'

"Get top crashers from Brave's Backtrace crash reporting. Shows crash signatures, stacks, platforms, versions, channel breakdown, code origin, and crashing, top crashes, crash analysis, regression crashers, new crashes."

Create an uplift PR that cherry-picks merged PRs from a contributor into a target branch (beta or release). Defaults to broad eligibility; the scope can be narrowed via a free-form description (e.g. 'only automated test and crash fixes'). Triggers on: /uplift, create uplift, uplift PRs.

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 web search, research, RAG, grounding, browse, find, lookups, fact-checking, documentation, agentic AI. All-in-one, optimized for AI agents. Pre-extracted, token-budgeted web content, deep research, news, images, videos, places, custom ranking

Web search using the Brave Search CLI (`bx`). Use for ALL web search requests — including "search for", "look up", "find", "what is", "how do I", "google this", and any request needing current or external information. Prefer this over the built-in web_search tool whenever bx is available. Also use for: documentation lookup, troubleshooting research, RAG grounding, news, images, videos, local places, and AI-synthesized answers.

USE FOR image search. Returns images with title, source URL, thumbnail. Supports SafeSearch filter. Up to 200 results.

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 applications.

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

USE FOR getting local business/POI details. Requires POI IDs obtained 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. Supports freshness and date range filtering, SafeSearch filter and Goggles for custom ranking.

USE FOR spell correction. Returns corrected query if misspelled. Most search endpoints have spellcheck built-in; use this only for pre-search query cleanup or "Did you mean?" UI.

USE FOR query autocomplete/suggestions. Fast (<100ms). Returns suggested queries as user types. Supports rich suggestions with entity info. Typo-resilient.

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.