boris-vibe-coding

XY-Showing

Use when starting a vibe coding session or managing parallel AI agents for development - fleet management, plan-first execution, browser verification loops, shared team memory

autonomous-engineering

davisbuilds

Full autonomous engineering workflows that run a complete feature development cycle: plan, deepen, implement, review, resolve, test, and record. Use when asked to build a feature end-to-end, go autonomous, or when user says 'lfg' or 'slfg'. Includes a sequential variant (lfg) and a swarm-parallel variant (slfg) for faster execution of large features.

subagent-delegation

PracticalSwan

Delegate routine work to subagents — boilerplate generation, data transformation, file analysis, documentation drafting. Use when splitting tasks into independent subtasks for parallel subagent execution.

workflow-automation

haniakrim21

Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off. This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation. Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility.

subagent-execution

mahsumaktas

Execute implementation plans using subagents. Three modes: single-task, batch (sequential), and parallel. Two-stage review for every task.

Infinite Gratitude

haniakrim21

Multi-agent research skill for parallel research execution (10 agents, battle-tested with real case studies).

recovering-sessions

miethe

Recover from crashed, failed, or interrupted Claude Code sessions. Use this skill when: session crashed during multi-agent parallel execution, need to determine what work was completed vs incomplete, want to generate resumption commands for interrupted tasks, recovering from context window exhaustion, or handling session handoffs. Analyzes agent logs, verifies on-disk state, and creates resumption plans with ready-to-execute Task() commands.

Infinite Gratitude

reikiplanet

Multi-agent research skill for parallel research execution (10 agents, battle-tested with real case studies).

ue-async-threading

quodsoler

Use this skill when working with Unreal Engine async operations, threading, parallel execution, or concurrency. Also use when the user mentions 'FRunnable', 'FAsyncTask', 'TaskGraph', 'UE::Tasks', 'ParallelFor', 'TFuture', 'TPromise', 'Async()', 'thread safety', 'FCriticalSection', 'FRWLock', 'background thread', 'game thread dispatch', or 'thread pool'. For networking async (RPCs, replication), see ue-networking-replication. For asset streaming, see ue-data-assets-tables.

agent-swarm

streeboga

Use when the user gives a coding task that should run in parallel, asks to create an agent, says "run an agent", "do it in a separate branch", "agent new", or when multiple independent tasks need parallel execution. Manages coding agents via tmux + git worktree + claude -p.

task-orchestrator

frekyr17-png

Autonomous multi-agent task orchestration with dependency analysis, parallel tmux/Codex execution, and self-healing heartbeat monitoring. Use for large projects with multiple issues/tasks that need coordinated parallel execution.

workflow-automation

oki3505F

Workflow automation is the infrastructure that makes AI agents reliable. Without durable execution, a network hiccup during a 10-step payment flow means lost money and angry customers. With it, workflows resume exactly where they left off. This skill covers the platforms (n8n, Temporal, Inngest) and patterns (sequential, parallel, orchestrator-worker) that turn brittle scripts into production-grade automation. Key insight: The platforms make different tradeoffs. n8n optimizes for accessibility

swift-testing-expert

jajaaa2

Expert guidance for Swift Testing: test structure, #expect/#require macros, traits and tags, parameterized tests, test plans, parallel execution, async waiting patterns, and XCTest migration. Use when writing new Swift tests, modernizing XCTest suites, debugging flaky tests, or improving test quality and maintainability in Apple-platform or Swift server projects.

shipkit-dev-team

stefan-stepzero

Orchestrates Shipkit framework development using Agent Teams. Creates coordinated teams from dev plans for parallel implementation, review, and release. Use when a framework change is big enough for team execution.

orchestrator

wyattowalsh

Build and deploy parallel execution via subagent waves, agent teams, and multi-wave pipelines. Use when the Decomposition Gate identifies 2+ independent actions or when spawning teams. NOT for single-action tasks or non-parallel work.

polars

reikiplanet

Fast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy evaluation, parallel execution, Apache Arrow backend. Best for 1–100 GB datasets, ETL pipelines, and as a faster pandas replacement. For datasets larger than available RAM, use out-of-core frameworks like Dask or Vaex.

builder

socalfinanceinsights

Build execution orchestrator — spawns spock for code writing in parallel waves, reagan for verification after each wave. Activates on '/build', 'build this', 'implement this', 'proceed with implementation', or when REQUIREMENTS/PLAN docs with task blocks are ready.

orchestrating-test-execution

nivkazdan

Test coordinate parallel test execution across multiple environments and frameworks. Use when performing specialized testing. Trigger with phrases like "orchestrate tests", "run parallel tests", or "coordinate test execution".

Shipkit Team

stefan-stepzero

Create an agent team from an implementation plan to build features in parallel. Reads plan.json, decomposes tasks by file ownership, spawns implementer and reviewer teammates with quality gates. Use when ready to implement a plan with parallel team execution.

web-testing-playwright-e2e

agents-inc

Playwright E2E testing patterns - test structure, Page Object Model, locator strategies, assertions, network mocking, visual regression, parallel execution, fixtures, and configuration

multi-agent patterns

oki3505F

This skill should be used when the user asks to "design a multi-agent system", "implement a supervisor pattern", "create a swarm architecture", "coordinate multiple agents", or when they mention multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.

manager

metyatech

Task orchestrator that receives work, decomposes it, and dispatches background agents or teams for parallel execution. Use when managing multiple tasks, coordinating agents, or optimizing work distribution. Triggers on: 'manage', 'orchestrate', 'dispatch', 'coordinate', 'delegate'.

Task Decomposition

abujiletsgo

This skill should be used when facing a large feature, multi-step implementation, or when the user asks to 'break this down', 'decompose', 'plan the steps', or 'estimate effort'. It breaks down complex tasks into atomic, time-estimated micro-tasks with parallel execution markers.

Infinite Gratitude

oki3505F

Multi-agent research skill for parallel research execution (10 agents, battle-tested with real case studies).

symfony-phpunit-bridge

krzysztofsurdy

Utilities for testing with enhanced PHPUnit features including deprecation reporting, function mocking for time/DNS/class-existence tests, parallel test execution, and multi-version PHPUnit compatibility.

agent-team-orchestration

JuanJoseGonGi

Orchestrate multi-agent teams for parallel development, reviews, and debugging. Covers team composition (sizing, presets, agent types), task coordination (decomposition, dependency graphs, workload balancing), communication protocols (message types, plan approval, shutdown), and parallel feature development (file ownership, conflict avoidance, integration patterns). Use when spawning agent teams, breaking down work for parallel execution, establishing file ownership boundaries, or coordinating multi-agent workflows.