Loading...
Loading...
Found 51 Skills
Conduct a focused technical planning interview to produce an implementable, parallelizable plan or spec with clear dependencies, risks, and open questions.
Dynamic tool selection, composition, and error handling patterns for AI agents. Use when you need to efficiently leverage available tools and handle failures gracefully.
Create reusable workflow templates with steps, conditions, and parallel execution
Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via MCP Memory, and monitors progress
[EXPLICIT INVOCATION ONLY] Creates dependency-aware implementation plans optimized for parallel multi-agent execution.
Sequence tasks from a feature breakdown into an optimal execution order, identify dependencies and parallelization opportunities, and create an agent-ready execution sequence. Use when you have a feature breakdown and need to determine the correct order to build tasks and which can run in parallel.
Use Inngest step methods to build durable workflows. Covers step.run, step.sleep, step.waitForEvent, step.waitForSignal, step.sendEvent, step.invoke, step.ai, and patterns for loops and parallel execution.
Recursively find all git repositories and pull latest changes from remote IN PARALLEL. Use when syncing multiple projects across machines or after switching computers.
Execute a GRACE development plan in controller-managed parallel waves with selectable safety profiles, batched graph sync, and scoped reviews.
Turn an idea into a well-structured Linear project ready for hands-off parallel execution. Conversational — asks clarifying questions before scaffolding. Outputs a Linear project, per-scope-item tickets, and `.handoffs/<slug>/tickets.yaml` — the machine contract /project-start consumes (with file surface and per-ticket dependencies). Reads `.claude/conventions.yaml` for Linear team / ticket-prefix conventions. Requires the `/grilling` and `/domain-modeling` skills (mattpocock/skills).
Divide-and-conquer implementation from specs/plans. Decomposes a reference document into independent tasks, assigns each to a builder agent, executes in parallel waves respecting dependencies, then integrates results. Use when you have a spec, PRD, plan, or large feature to implement quickly with parallel execution.
AI-native software development lifecycle that replaces traditional SDLC. Triggers on "plan and build", "break this into tasks", "build this feature end-to-end", "sprint plan this", "absolute-human this", or any multi-step development task. Decomposes work into dependency-graphed sub-tasks, executes in parallel waves with TDD verification, and tracks progress on a persistent board. Handles features, refactors, greenfield projects, and migrations.