wikis

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.

Create, manage, and track issues in GitHub, Linear, or GitLab. Use when the user asks to "create an issue", "file a bug", "check issues", "update a ticket", "create an epic", or anything about issue/ticket management.

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.

Structured feature planning workflow. Use when the user says "plan a feature", "design this", "how should we build", "feasibility check", or any pre-implementation planning work. Covers requirements, investigation, feasibility, and implementation planning.

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.

Generate AGENTS.md and .octobots/ 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.

Test-driven development workflow. Use when the user asks to "write tests first", "TDD", "add test coverage", "test this function", or wants to develop a feature test-first.

Microsoft 365 signal scanning — email, Teams channels, calendar, SharePoint. LLM-less scripts for scheduled scans; query.py for interactive Claude use via Bash tool.

Headless Obsidian vault operations for a personal-assistant agent. Use when the user says "save to vault", "log this note", "find my notes about X", "who is Y", "what's in my inbox", "open loops", "add a follow-up", or whenever you process an incoming signal (email, chat, voice memo) and need to file it. Also use to create or update people/project/meeting/decision notes. Pure file-system; does NOT require Obsidian to be running.

Browse, query, and generate AI-powered code wikis via a running Wikis instance. Use when you need to: read architecture documentation for a repository, ask questions about a codebase, run deep multi-step research on a repo, or generate a new wiki from a repository URL. Requires WIKIS_URL env var pointing to the Wikis app (web: :3000 or backend: :8000).

Bug reproduction specialist workflow. Use when a bug report is unclear, unconfirmed, or needs reproduction before investigation. Transforms vague reports into precise, repeatable steps with evidence. Does NOT fix code — reproduction and documentation only.

Root Cause Analysis workflow. Use when a bug is confirmed and needs deep investigation: tracing code paths, analyzing dependencies, identifying the exact location and cause. Does NOT fix code — investigation and documentation only.