Productivity & Workflow Agent Skills for Claude Code

Personal boycott list \u2014 users can conversationally tell the agent\

Turn vague "what did I do?" into evidence-backed impact statements for performance reviews, self-reviews, promotion packets, and weekly…

Use when the user types /brain, /brain init, /brain load, /brain sync, /brain status, /brain config, /brain remove, /brain disconnect…

Allinea con l'utente sul design prima di scrivere codice, per task non banali.

Use before creative or constructive work (features, architecture, behavior).

Transforms vague ideas and product requirements into structured, user-approved technical design specifications before implementation begins.

Runs a structured clarifying interview for new project requests before building.

Use when the user wants hyperflow's behavioral rules to apply outside the terminal CLI — in Claude Code Desktop, claude.ai web, or IDE…

Maintenance orchestrator for the brooks-lint plugin itself.

Guide solo technical founders who do not yet have a startup idea through BROTH by researching current demand and competitors, ranking…

Voice a reminder through the local speakers in BT-7274's voice (Titanfall 2), synthesized locally with Piper TTS and spoken in English.

Use when implementing a feature plan file split into phases with task checkboxes.

Run a sustained multi-wave build in one OpenCode session, using background subagents to compress research while the parent keeps…

Find, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal.

End-to-end playbook for building an Obsidian community plugin.

Use inside a product repository when the user wants the full MVP built from their BuilderOS spec documents.

Plan or classify a Buildable app idea into an archetype, ask-vs-build decision, phase plan, references, mock-data guidance, and…

Hands-on implementation partner for creating tools, scripts, dashboards,\

Interviews the user until a goal is fully planned and ready for a specification.

Completes one issue from start to end: claim the issue, build with tests first, verify, record, and close.

Orchestrate parallel Mastra Code headless instances to debug and fix multiple GitHub issues simultaneously