Prepare a development branch for final maintainer review by checking security, unnecessary complexity, and billing abuse risks. Fix confirmed issues, run local checks and tests, then push changes and create or update the pull request.
Get a branch ready for the maintainer's final review. Review it for security, simplicity, and billing abuse, fix what's real, get checks passing, and open or update the PR. Use whenever the user says a feature, fix, or branch should be "merge ready", asks to get changes ready for review, or appends this to a build request ("build X and make it merge-ready").
Review the instructions the agent will receive before you install.
Get this branch ready for the maintainer's final review. If you were also asked to build something, build it first.
Fetch and merge origin/main if the branch is behind. Then review everything on the branch against it, including uncommitted and untracked files. Make sure you understand every product decision and change in functionality.
Is it secure?
Is it as simple as it can be? What can be deleted or simplified given the end state of the branch? Did an unlikely edge case lead to overengineering? We prefer to delete code.
Does it use APIs and SDKs (TanStack, DataForSEO, Autumn, Cloudflare) idiomatically? Watch for code that reinvents what they already do, works around limits they don't have, or pays for more than it needs. Check the docs only when something looks off.
Is there a significant way to abuse billing, like getting credits, paid features, or provider calls without paying? Ignore small leaks nobody would bother exploiting.
Beyond that, review it however you think best. Work out which parts could do the most damage if they're wrong and spend your time there. docs/maintainers/review-guidelines.md lists the repo's invariants and the things that look wrong but are intentional.
Fix what's real. Commit as you go. Get pnpm ci:check and pnpm test passing locally, then push. Those local runs stand in for CI, so don't wait for GitHub CI to finish.
Open or update the PR against main. Write the description in the simple-issue-description format, and put anything you left for the maintainer's judgment under Extra context.
Never merge. The maintainer reviews last.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Research questions about a market, examine recorded ChatGPT answers and cited websites, and identify themes where a brand appears or is missing. Receive ranked prompt groups and suggested questions for future tracking.
Audit how a brand appears in AI answers by examining mentions, website citations, competitors, and cited pages. Receive one to three evidence-based priorities, such as improving a page, seeking inclusion in a relevant source, or fixing access barriers.
Compare several competitors to see which sites lead a search market, what content earns rankings, and where opportunities remain. The report covers keyword reach, links from other sites, and practical next steps.
Analyze a named competitor's unpaid search traffic, ranking keywords, content themes, and links from other websites. Identify strengths, weaknesses, and relevant opportunities, with an optional comparison to your own site and a report of recommended actions.
Create or update skills using OpenSEO's repository conventions. Keep one canonical source, distinguish internal and public workflows, maintain Claude Code links, and register public skills in documentation, the in-app agent, and plugin bundles.
Edit blog posts, documentation, marketing copy, and PR descriptions to remove formulaic AI writing patterns. Replace filler, vague claims, and staged emphasis with plain statements while preserving concrete details and the writer's voice.