Work through design or implementation choices one at a time, with concise context and clear alternatives. You can also review completed code change by change, recording decisions, approvals, and requested revisions in a final table.
Walk the user through design or implementation decisions one at a time, or review completed code one change at a time. Use when the user says "walk me through each decision", "let's decide together", "help me work through these choices", "walk me through what you did", or "QA step by step". Present concise context, mutually exclusive options, log each answer, and finish with a summary.
Review the instructions the agent will receive before you install.
Before a design walkthrough, inspect the relevant code and record concrete bugs, inconsistencies, and decision points in plans/<YYYYMMDD>-<topic>.md or the appropriate app-scoped plans/ directory. Preserve existing edits; never discard speculative or user-authored work without explicit approval.
Order decisions by dependency and leverage, not document order.
For each decision:
## Decision N: <title>.ask_user when available. In Codex Plan mode, use request_user_input when that is the exposed interactive question tool.(Recommended).Other option when the client adds one automatically.Logged: <decision>. and continue.If the user acknowledges an issue without choosing, log the recommended choice and say they can correct the assumption.
At the end, provide a | # | Decision | Choice | table and offer to turn the audit into an implementation plan. Do not write implementation code during the decision walkthrough.
Use this mode when the user wants to review existing code step by step.
## Step N: <title>Looks good, next step (Recommended), Push back, change this, and, only for non-trivial code, Pause, explain more| # | Step | Verdict | table.If a step reveals a genuine design fork, pause the QA walkthrough and offer to switch to decision mode for that fork.
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.
Review how you use Superset and identify unused features that fit your workflow. Get a short list of suggestions, learn about each option, and set up selected features such as scheduled agents, parallel workspaces, or shared tasks.
Set up recurring tasks in Superset with an agent prompt, a schedule or event trigger, and a chosen execution workspace. After explicit confirmation, create the automation, check its saved settings, and review a real first run.
Browse pages, click controls, fill fields, and inspect screenshots or console messages through Superset's browser pane. Use it to preview a running web app, check interface behavior, and work through browser tasks in a visible session.
Build Stripe payments, subscriptions, and invoicing using verified documentation and API parameter definitions. The skill guides product selection, sandbox testing, and webhook handling, where server notifications determine payment and subscription state.
Verify desktop UI changes through the Chrome DevTools Protocol, a connection for controlling the running app. Reproduce the user’s actual steps and compare screenshots, measured state, and console errors to establish evidence before and after a fix.
Diagnose failed GitHub Actions runs by finding the first meaningful error, separating code problems from infrastructure issues and intermittent failures, and comparing the base branch. Get a focused report explaining the PR’s involvement and recommended next steps.