Productivity & Workflow Agent Skills for Grok Build

A relentless interview to sharpen a plan or design.

Behavioral guidelines to reduce common LLM coding mistakes.

File-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use for multi-step tasks requiring >5 tool calls.

Generates comprehensive planning documentation for web application projects, structuring work into context-safe phases with built-in…

Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches…

Use when executing implementation plans with independent tasks in the current session - dispatches fresh subagent for each task with code…

Clear the freeze boundary set by /freeze, allowing edits to all directories again. (gstack)

Use when automating DaVinci Resolve Studio 20 through its local MCP server — timeline editing, color grading, Fusion compositing…

Detect second-order effects, diminishing returns and define explicit stop or rollback thresholds.

Cross-functional what-if modeling for cascading multi-variable scenarios.

Unified timeline of all deadlines from emails, calendar, and vault.

Write deal memos for PE acquisitions and CRE investments.

Find material deal changes; not a full deal review.

Have the Claude and GPT partners critique each other's answers across a configurable number of rounds (default 1) before converging on a…

Multi-model adversarial debate where Claude defends positions against external CLI models (Gemini, Codex, Qwen).

Build a structured, clause-referenced "Debt Document Review" of a leveraged debt document — a high-yield bond Offering Memorandum /…

Document debugging sessions with hypothesis tracking and knowledge base

Risolvi un bug, errore o comportamento inatteso trovando la causa radice prima di proporre fix.

Convenes a council of multiple independent perspectives (claude-council style) for important decisions.

Structure a choice between concrete options: elicit the real criteria and their weights, score each option honestly, run a sensitivity…

Decompose long transcripts, dictations, voice-memo exports, brainstorming notes, and exploratory conversations into traceable jobs to be…