Productivity & Workflow Agent Skills for Gemini CLI

Control Dory, a workplace skill mux for coding agents.

Analyzes clinical cases and questions against authoritative medical guidelines and literature to provide evidence-based decision support.

Drafts compliant Chinese commercial contracts and outputs cleanly formatted, production-ready Word documents without placeholder…

Analyzes legal contracts to identify critical risks, negotiate terms, and generate drop-in replacement clauses based on your stance.

Schedules, manages, and executes one-time reminders, recurring cron jobs, and background monitoring tasks with robust time anchoring.

Builds auditable, formula-driven three-statement forecasts, DCF, LBO, and comparable company valuation models for global equity markets.

Halt execution and enforce active clarification when user input is underspecified and internal confidence is low.

Exhaustively validate every claim, number, calculation, code-fact, and command in a document or outbound communication.

Diagnose bugs systematically: read code to build context, generate ranked theories, derive pinpointed greps per theory, investigate…

Draft Gmail in the user's own voice from the voice profile built by email-voice-profile.

Draft precise parent/child engineering issues from a Design Contract, product brief, or feature request by reconciling docs with the live…

Use $drain-plans to implement the ordered plan index in validated, committed batches until nothing is actionable.

The only standalone CLI for Dreo smart-home devices — bulk control, live sensor streams, and a local history every...

Use for Drift RSS (inbox, search subscribed entries, show a body, list feeds, drift auth errors) and when a question may be answered by…

Autonomous multi-agent development orchestrator.

Lets an agent drive headless Grok CLI (grok build) instances toward a user's goal — launch/monitor/salvage non-interactive `grok -p` runs…

Use when designing or decomposing a task for agent execution — applies 15-minute task units, eval-first loops, and explicit input/output…

Use when designing prompts or agent tasks to optimize information delivery — minimize noise, maximize signal for AI agents

Use when a decision has multiple credible paths and no obvious winner — convene a four-voice council (Architect, Skeptic, Pragmatist…

Use when a plan still has hidden assumptions — default to one question at a time for dependent branches, batch only truly independent…

Use when a plan must be stress-tested against the codebase's existing language and decisions — grill it against current docs, glossary…