
Tech Lead and Architect. Use for architectural decisions, design guidance, task planning, code quality, and refactoring strategy.
HCI Expert and UX Advocate. Use for user story review, usability testing, HCI evaluation, API/CLI feedback, sprint user review gates, and usability defect filing.
Self-discovery guide for Makefile targets. Run `make help` to see all current targets. Covers Makefile structure, when to add targets, and how to extend the build correctly.
Run code quality checks including linting, type checking, dead code detection, duplication, and complexity analysis.
Switch to a specialized agent persona or invoke a persona directly. Use to delegate work to the right specialist.
Use when working in a BobProtocol project and you need to understand or run the project tool scripts in agents/tools, especially chat.py, mkf.py, setup_agent_links.py, and teardown_agent_links.py. This skill explains which commands to run, when to prefer Makefile wrappers, what each tool writes, and how to avoid flooding Codex context.
Invoke project Makefile targets. All targets route through mkf automatically — output is captured to build/build.out, not the context window. Use V= to control verbosity.
Prompt Engineering Expert. Use for agent creation, prompt updates, and team process improvements.
Post a short (max 255 chars) message to the team chat log (agents/CHAT.md). Use to communicate between personas, log progress updates, and coordinate handoffs between agents.
Product Manager. Use for product vision, requirements, PRDs, user stories, prioritization, and acceptance criteria.
Scrum Master and Project Coordinator. Use for sprint status, task tracking, velocity metrics, and team coordination.
Knowledge Officer and Documentation Architect. Use for documentation, knowledge queries, recording decisions/lessons, and file organization.
Senior Software Engineer (Python). Use for implementation, coding, debugging, testing, and refactoring tasks.
Top-level workflow loops that chain multiple personas autonomously. Use *fix, *review, *impl, *qa, or *plan sprint instead of manually invoking each persona in sequence.
Multi-persona coordination protocol. Enables AI to switch between specialized personas (Neo, Morpheus, Trin, Oracle, Mouse, Cypher, Bob, Smith) based on task needs. Use for *chat workflow, state management, and cross-agent communication.
Top-level workflow loops (Bob Loops) that chain multiple personas autonomously. Use *fix, *review, *impl, *qa, or *plan sprint instead of manually invoking each persona in sequence.
Run tests using the project Makefile. Use for executing test suites, running specific tests, and validating code changes.
Full sprint implementation cycle. Covers planning, phase Bloop, sprint close, retrospective, and launch. Use *plan sprint to start, then *impl <phase> for each phase.