arozumenko

Measure the token/cost/time efficiency of AI coding-agent work — per session, per role, per day, and per individual sub-agent — with every dollar metered by ccusage. Use when the user asks "what did this cost", cost per session/role/test case, which role/sub-agent burned the most, tool-call/skill/time breakdowns, "before vs after" cost comparisons, or wants to audit AI spend over time.

Per-role persistent memory — durable facts, preferences, decisions, and a daily log, as plain markdown. Use when the user says "remember this" or "log this", asks "what did you learn yesterday", or whenever you discover something worth keeping across sessions.

UI/E2E test automation with Playwright MCP. Use when the user asks to "test the UI", "automate browser tests", "check the page", "take a screenshot", "run Playwright", "write E2E tests", or anything about browser-based testing.

Turn a vague bug report into precise, repeatable steps with evidence and a CONFIRMED / CANNOT-REPRODUCE / PARTIAL verdict. Use when a bug is unclear or unconfirmed and needs reproduction before RCA or any fix. Reproduction and documentation only — does not fix code.

Generate AGENTS.md and .agents/ configuration files for a new project. Use when the user asks to "seed the project", "onboard this repo", "generate project config", "create AGENTS.md", or after the scout has explored the codebase.

Use when a TMS test case needs to become an automated test, or when automating a regression batch — "automate TC-NNN", "convert this case to a framework test", any flow from a manual case to green framework tests. Pluggable TMS (Zephyr/TestRail/Xray/Azure/markdown).

Use when a TMS test case needs manual execution, handle discovery (selectors / endpoints / element-ids / metric queries — whatever the surface uses), or defect investigation before automation — "analyse SCRUM-T101", "run this case and emit an AFS", any pre-automation case exploration. Produces an Automation-Friendly Spec (AFS); does not write test code.

Microsoft 365 (Graph) access to email, Teams, calendar, and SharePoint. Use when the user asks to "check my email/Teams/calendar", "what meetings do I have", "any messages about X", or whenever a task needs live M365 data rather than memory. Scriptable scans + interactive query.py.

Testing-grade browser automation via Chrome DevTools Protocol (CDP). Direct access to the browser's DOM, JS runtime, network layer, cookies, computed styles, and console — without any external dependencies. Complements MCP-based tools by enabling arbitrary JS evaluation in page context and deep inspection that screenshot-only tools miss. Use when you need to: run JS in the page, inspect cookies/localStorage, check computed styles, enumerate third-party scripts, emulate devices, analyze network timing, or interact via real mouse and keyboard events.

End-to-end bugfix workflow. Test first, plan, fix, verify. Use when the user says "fix bug", "bugfix", "investigate issue", "fix

Review code for correctness, security, performance, and maintainability. Use when the user asks to "review this code", "check my changes", "review PR", "audit", or "what do you think of this approach".

Gather cross-channel context (local KB, email, Teams chats, optional web) about a person and topic before responding. Use when the user says "what do we know about X", "find prior discussions with Y", "context on this thread", or before drafting any reply where prior history matters.

Disk-first, checkpointed research workflow with three modes — trend research, topic analysis, and fact-checking. Use when the user asks to "research trends", "analyze a topic", "fact-check this", "verify claims", "what's the state of X", or hands you a document to vet.

Git operations, branching, commits, PRs, and release workflows. Use when the user asks to "commit", "create PR", "branch", "merge", "rebase", "cherry-pick", "tag", or manage git history.

Goal-backward verification — checks whether the desired outcome was achieved, not whether tasks were marked done. Use when the user asks to "verify", "did this actually work", "is X really done", or before closing an issue / merging a PR.

End-to-end feature implementation workflow. Use when the user says "implement", "build feature", "work on task", "start implementation", or any feature development work. Covers plan review, test writing, implementation, verification, and delivery.

Co-author demo video scripts by exploring the live product via browser. Use when user asks to "write a demo script", "plan a product video", "script a walkthrough", "create a demo storyboard", or "plan a recording". Generates structured JSON scripts with actions, narration, timing, and highlight styles ready for /record-demo.

Generate and synchronize AI voice-over narration for demo videos using ElevenLabs TTS. Use when user asks to "add voiceover", "generate narration", "add voice to video", "narrate the demo", or "create voice-over". Produces per-scene audio with character-level timestamps, automatic subtitle generation, and continuity chaining across segments.

Record product demo videos with automated browser interaction and screen capture. Use when user asks to "record a demo", "make a product video", "create a demo recording", "record a walkthrough", or "screen record with narration". Captures H.264 video via Playwright headful + ffmpeg avfoundation with action timestamps for voice-over sync.

Per-role persistent memory for Octobots roles. Curated typed entries (facts, preferences, decisions) and append-only daily logs (episodic, "what did I do today"). Use when the user says "remember this", "what did you learn yesterday", "log this", or whenever you discover something worth keeping across sessions.

Send and receive messages between Claude Code instances using a shared SQLite queue. Use when the user says "send to <instance>", "check inbox", "start listening", "check responses", or anything about inter-instance communication.

Use when asked to verify in browser, check the page, test in Chrome, take a screenshot, verify the UI, check if it renders, open in browser, browser test, visual verification, check the app, verify the layout, test the form, check for errors in browser, click the button, fill the form, test the flow, check responsive, or when needing to visually or functionally verify a web application using Chrome.

Reviews React Router code for proper data loading, mutations, error handling, and navigation patterns. Use when reviewing React Router v6.4+ code, loaders, actions, or navigation logic.