Multi-Perspective

3

flonat

Explore a research question from multiple independent perspectives with diverse epistemic priors. Spawns parallel agents with distinct disciplinary lenses, then synthesises findings.

system-audit

3

flonat

Run parallel system audits across skills, hooks, agents, rules, bibliographies, conventions, and documentation freshness. Report-only — never modifies files.

validate-bib

3

flonat

Cross-reference \cite{} keys against .bib files or embedded \bibitem entries. Finds missing, unused, and typo'd citation keys. Deep verification mode spawns parallel agents for DOI/metadata validation at scale. Read-only in standard mode.

Goose

3

RohiRIK

Parallel agent orchestration using Goose recipes. USE WHEN user wants to spawn agents, run recipes, review code, generate tests, refactor, roast code, security audit, or any autonomous development task. Supports non-blocking parallel execution.

system-audit

3

flonat

Run parallel system audits across skills, hooks, agents, rules, bibliographies, conventions, and documentation freshness. Report-only — never modifies files.

docs-seeker

3

zircote

Searches the internet for technical documentation using the llms.txt standard, analyzes GitHub repositories via Repomix, and performs parallel exploration. Use when you need: (1) the latest library/framework documentation, (2) documentation in llms.txt format, (3) GitHub repository analysis, (4) documentation from sources without direct llms.txt support, or (5) to query multiple documentation sources in parallel.

bib-validate

3

flonat

Cross-reference \cite{} keys against .bib files or embedded \bibitem entries. Finds missing, unused, and typo'd citation keys. Deep verification mode spawns parallel agents for DOI/metadata validation at scale. Read-only in standard mode.

multi-perspective

3

flonat

Explore a research question from multiple independent perspectives with diverse epistemic priors. Spawns parallel agents with distinct disciplinary lenses, then synthesizes findings.

sub-agents

3

blindlove200

Execute external CLI AIs as isolated sub-agents for task delegation, parallel processing, and context separation. Use when delegating complex multi-step tasks, running parallel investigations, needing fresh context without current conversation history, or leveraging specialized agent definitions. Returns structured JSON with agent output, exit code, and execution status.

multi-perspective

3

flonat

Explore a research question from multiple independent perspectives with diverse epistemic priors. Spawns parallel agents with distinct disciplinary lenses, then synthesises findings.

validate-bib

3

flonat

Cross-reference \cite{} keys against .bib files or embedded \bibitem entries. Finds missing, unused, and typo'd citation keys. Deep verification mode spawns parallel agents for DOI/metadata validation at scale. Read-only in standard mode.

deep-research

2

vlabsai

Agent-orchestrated research that takes input text and conducts parallel multi-agent investigation. Accepts research questions, briefs, or seed context. Spawns parallel agents for web research, local project analysis, and specialized investigation. Produces citation-backed markdown reports. Triggers: "deep research", "research X", "comprehensive analysis", "investigate", "compare X vs Y", "analyze trends". Do NOT use for simple lookups (1-2 searches), debugging, or document analysis without web research.

memory-guardian

2

frankxai

WSL2 memory safety and scaling guardrails for Claude Code sessions and parallel agents.

orchestrating-swarms

2

iliaal

This skill should be used when orchestrating multi-agent swarms using Claude Code's TeammateTool and Task system. It applies when coordinating multiple agents, running parallel code reviews, creating pipeline workflows with dependencies, building self-organizing task queues, or any task benefiting from divide-and-conquer patterns.

research

2

ashaykubal

Structured multi-viewpoint research using 5 parallel Sonnet sub-agents. Use when deep research is needed on a complex topic before implementation planning.

Swarm Orchestration

2

frankxai

Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.

Subagent Orchestration

2

joabgonzalez

Fresh subagents per task with two-stage reviews. Trigger: When coordinating parallel agents for complex workflows.

dispatching-parallel-agents

2

kamusis

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

dispatching-parallel-agents

2

izyanrajwani

Dispatches one subagent per independent domain to parallelize investigation/fixes. Use when you have 2+ unrelated failures (e.g., separate failing test files, subsystems, bugs) with no shared state or ordering dependencies.

adc-research

1

atakankarsli

Multi-channel Apple API research — launches 3 parallel agents (official docs, WWDC, community skills) to investigate a topic, then synthesizes findings into a verified summary. Use when researching Apple APIs for architecture decisions, evaluating framework choices, or verifying API capabilities.

infinite-gratitude

1

rootcastleco

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

agent-teams

1

michaelkeevildown

Agent Teams workflow — parallel multi-agent development with stack-aware coordination (build-first for frontend, TDD for Python/Rust), feature doc lifecycle, file ownership, and quality gates.

plan-review

1

101mare

Reviews implementation plans before coding begins. Checks completeness, architecture fit, risks, and requirement alignment. Uses specialized agents in parallel for thorough analysis. Proactively asks clarifying questions when uncertainties are found. Use when: reviewing plans, before implementation, user asks "ist der Plan gut?", "review my plan", "check this approach", "before I start coding".

V3 Deep Integration

1

jbeck018

Deep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building claude-flow as specialized extension rather than parallel implementation.

sub-agents-doc

1

hlibkoval

Reference documentation for Claude Code subagents -- creating and configuring specialized AI assistants with custom system prompts, tool restrictions, permission modes, model selection, persistent memory, lifecycle hooks, foreground/background execution, and patterns for delegation, context isolation, parallel research, and chaining.

parallel-code-audit

1

fratilanico

Use when conducting a comprehensive code review or security audit of a codebase — dispatches parallel review agents per file/module, triages findings by severity, then dispatches parallel fix agents.

parallel-agents

1

shousper

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

relay

1

vlting

Inter-agent communication server. Start/stop the relay, check status, or coordinate between multiple Claude Code agents running in parallel.

multi-agent-patterns

1

Kalyanikhandare29

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

dispatching-parallel-agents

1

fratilanico

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

dispatching-parallel-agents

1

rootcastleco

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

agent-teams

1

ungurenko

Use when facing complex tasks needing parallel collaboration between multiple agents with shared state, coordination, and direct inter-agent communication. Triggers on "создай команду", "agent team", "параллельная работа агентов", "team of agents"

parallel-agents

1

rootcastleco

Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.

scout

1

hoadh

Fast codebase scouting using parallel agents. Use for file discovery, task context gathering, quick searches across directories. Supports internal (Explore) and external (Gemini/OpenCode) agents.

pr-review

1

101mare

Orchestrates pull request reviews using specialized agents in parallel. Reads PR diff, selects relevant reviewers, aggregates findings. Use when reviewing PRs, before merging, or when user asks "review this PR". Recognizes: "pr-review", "review PR", "review pull request", "check this PR", "PR review", "code review", "merge review", "review before merge"

parallel-dev

1

escotilha

Parallel feature development using git worktrees and specialized agents. Orchestrates multiple features in isolation with CI reaction loops, progress monitoring, and progressive merge. Delegates to `ao` CLI when available.

team-builder

1

101mare

Knowledge for orchestrating Claude Code agent teams — multiple independent sessions coordinated by a team lead with shared tasks and inter-agent messaging. Use when work benefits from parallel exploration with communication between workers. Recognizes: "create a team", "agent team", "team-builder", "parallel teammates", "coordinate multiple agents", "spawn teammates", "team lead", "shared task list"

Dispatching Parallel Agents

owensun6

Use when you have 2+ independent tasks that can be worked on without shared state or sequential dependencies.

interserve

mistakeknot

Dispatch tasks to Codex CLI agents — single megaprompt for one task, parallel delegation for many. Includes structured debate triggers and Oracle escalation.

plan-implement

lucaswall

Execute the pending plan in PLANS.md using an agent team for parallel implementation. Use when user says "implement the plan", "execute the plan", "team implement", or after any plan-* skill creates a plan. Spawns worker agents in isolated git worktrees for full code isolation. Updates Linear issues in real-time. Falls back to single-agent mode if agent teams unavailable.

sus

Nathan13888

Finds suspicious, architecturally problematic, or high-impact maintainability issues in a codebase. Deploys parallel analysis agents to explore code, then synthesizes findings into a prioritized report. Use when user says "find problems", "audit code", "what's sus", "code review the repo", "find tech debt", or asks about code quality.

superpowerbi

genesis1tech

Build complete Power BI reports from Snowflake data using PBIR format, Snowflake CLI, DAX, and agent teams. Use when: creating Power BI reports from Snowflake tables, building SQL queries/views for BI, generating DAX measures/columns/tables, editing PBIR files programmatically, or orchestrating multi-page report builds with parallel agents. Triggers on: "build a report", "create a dashboard", "Power BI from Snowflake", "PBIR", "DAX measures", "Snowflake views for BI", "report story".

test-parallelizer

nivkazdan

Test Parallelizer - Auto-activating skill for Test Automation. Triggers on: test parallelizer, test parallelizer Part of the Test Automation skill category. Use when writing or running tests. Trigger with phrases like "test parallelizer", "test parallelizer", "test".

07-SKILL-DISPATCHING-PARALLEL-AGENTS

GO-Orizon

Use when you have 2+ independent tasks that can be processed in parallel without dependencies

Code Review

noodlemind

Performs comprehensive code reviews using parallel expert sub-agents for security, performance, and architecture analysis. Spawns three specialized reviewers that independently analyze the codebase, then synthesizes findings into a prioritized report. Use when asked to "review code", "code review", "check code quality", or "audit the code".

processing-api-batches

nivkazdan

Optimize bulk API requests with batching, throttling, and parallel execution. Use when processing bulk API operations efficiently. Trigger with phrases like "process bulk requests", "batch API calls", or "handle batch operations".

crewai

haniakrim21

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.

crewai

oki3505F

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.