Claude Skills by Actual-Chat

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Three modes: SCOPE EXPANSION (dream big), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials).

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations.

Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead.

Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only.

Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas.

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues.

Drive the Voxt UI from Codex — chrome-devtools MCP setup, debugUI helpers, fast multi-user sign-in

Stream and search iOS device logs. Use proactively when debugging iOS issues or when user asks to check device logs.

Build, deploy and start iOS app on device. Use proactively when user asks to test, run, or deploy iOS changes.

Create a GitHub issue, assign to current user, and set status to In Progress

Build and start the Mac Catalyst app on this Mac. Use proactively when user asks to test, run, or deploy macOS (Mac Catalyst) changes.

Find orphan processes holding the server port

Show status of all running ActualChat servers

Stop the ActualChat server

Answer questions about Voxt — its features, what shipped and when, and how to use it — grounded in three sources: the public "Voxt Announcements" chat, the Landing pages, and the user guide. Use when asked things like "what features shipped this year", "list new features", "how do I use <feature>", "what is Voxt", or any product/usage question about Voxt. Answers are cited to the source.

Use when work on a branch is finished and the next step is a pull request — "create a PR", "open a PR", "push and PR this", "/create-pr" — or right after a PR has been created and the team has not been told about it yet.

Search Google Cloud (GKE) server logs of the DEV environment (dev.voxt.ai). Use when troubleshooting anything that needs the server side of the story — stream stalls, RPC peer changes / reconnects, watchdog closures, mesh/node churn, pod restarts — or when the user says "check GCP logs", "check server logs on dev", or gives a dev.voxt.ai timeline from a client console log.

Search Google Cloud (GKE) server logs of the PROD environment. Use when troubleshooting a production incident that needs the server side of the story — stream stalls, RPC peer changes / reconnects, watchdog closures, mesh/node churn, pod restarts — or when the user says "check PROD logs", "check production server logs", or gives a production timeline from a client console log.

CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Three modes: SCOPE EXPANSION (dream big), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials).

Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations.

Use when a feature branch is complete and its history must be cleaned up before merging back to dev — as the final step before creating or merging a PR, or when the user says "prepare for merge", "squash the branch", "clean up branch history", or "/prepare-merge".

Cut a new Voxt release. Use when the user says "prepare a release", "cut a release", "release Voxt", "do a release", "/prepare-release", or wants to run nbgv prepare-release, bump the version, generate end-user release notes, and announce them in the Releases chat.

Publish a tested Voxt release to the stores: Google Play production, App Store review (iOS + Mac Catalyst), Microsoft Store certification. Use when the user says "promote the release", "publish the apps", "release to the stores", "/promote-release", or after /prepare-release once the staged builds have been tested.

Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead.

Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only.

Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas.

Pre-landing PR review. Analyzes diff against the base branch for SQL safety, LLM trust boundary violations, conditional side effects, and other structural issues.

Inspect and manually purge the Soniox artifacts — transcriptions and uploaded audio files — that offline transcription leaves behind, on dev or prod. Use when offline transcription silently stops working, when Soniox answers 429 `limit_exceeded`, when `SonioxTranscriberTest.OfflineTranscribeWorks` and `CleanerDeletesEnqueuedArtifacts` fail together, or when the user says "sweep Soniox", "soniox/sonoix sweep", "sonoix swipe", "purge Soniox", "check Soniox files", or "is Soniox at the cap".

Use when work on a task is about to start or has just started — after a design or plan is approved, when a feature branch is created or resumed in a new session, when the first commit lands on a branch that was only claimed — or when the user says "link this to an issue", "find the issue for this", "put it on the board", "claim the issue", or "/track-issue".

Instruments and workflow for debugging the VirtualList — the chat transcript (`InfiniteList`) and the sidebar (`FiniteList`). Covers the built-in consistency checker, the on-screen overlay, the five `?vl*` URL flags, the touch-gesture rig, the frame recorder, attaching to a real Android device over CDP, and how to read a trace without being fooled by a measurement artifact. Use when the list jumps while scrolling, blanks, sticks on skeletons, or the overscroll/bounce misbehaves. The component...

Answer questions about Voxt — its features, what shipped and when, and how to use it — grounded in three sources: the public "Voxt Announcements" chat, the Landing pages, and the user guide. Use when asked things like "what features shipped this year", "list new features", "how do I use <feature>", "what is Voxt", or any product/usage question about Voxt. Answers are cited to the source.