Fan Out

Orchestration pattern for parallelizable tasks. When facing work that can be split into independent subtasks (research multiple topics, analyze multiple files, test multiple scenarios), spawn parallel agents and aggregate results. Use when subtasks have no dependencies on each other.

62 stars 2 forksTesting & QA

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add ElliotJLT/Claude-Skill-Potions --skill fan-out
Manual install
git clone --depth 1 https://github.com/ElliotJLT/Claude-Skill-Potions.git /tmp/Claude-Skill-Potions
mkdir -p ~/.claude/skills
cp -r /tmp/Claude-Skill-Potions/skills/fan-out ~/.claude/skills/fan-out

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Fan-Out

<purpose>
Some tasks are embarrassingly parallel - researching 5 APIs, analyzing 10 files,
testing 3 approaches. Running them sequentially wastes time. This elixir
orchestrates parallel execution: decompose work, fan out to agents, collect
and synthesize results.
</purpose>

## When To Activate

Trigger when:

- Task involves analyzing multiple independent items
- Research spans several unrelated topics
- Need to explore multiple approaches simultaneously
- Batch processing with no inter-item dependencies
- User says "check all of these" or "investigate each"

Do NOT trigger for:

- Sequential tasks where B depends on A
- Single-item deep analysis
- Tasks requiring context accumulation across items
- When parallel execution would overwhelm system resources

## The Pattern

```
                    ┌──→ [Agent 1] ──→ Result 1 ──┐
                    │                              │
[Task] → Decompose ─┼──→ [Agent 2] ──→ Result 2 ──┼──→ Aggregate → [Final]
                    │                              │
                    └──→ [Agent 3] ──→ Result 3 ──┘
```

## Instructions

### Step 1: Validate Parallelizability

Confirm the task is fan-out appropriate:

```
Subtask independence check:
- Can subtask B complete without subtask A's result? [YES/NO]
- Do subtasks share mutable state? [YES/NO - should be NO]
- Is order of completion irrelevant? [YES/NO - should be YES]

If any check fails → Use 'pipeline' pattern instead
```

### Step 2: Decompose the Task
Read the full skill on GitHub

Details

Skill name
fan-out
Path
skills/fan-out/SKILL.md
License
MIT
Repo updated
12 February 2026

FAQ

What does the Fan Out skill do?

Orchestration pattern for parallelizable tasks. When facing work that can be split into independent subtasks (research multiple topics, analyze multiple files, test multiple scenarios), spawn parallel agents and aggregate results. Use when subtasks have no dependencies on each other.

How do I install the Fan Out skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ElliotJLT/Claude-Skill-Potions --skill fan-out. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Fan Out popular?

It lives in ElliotJLT/Claude-Skill-Potions, which has 62 GitHub stars and 2 forks.

Related skills

Agent Audit

62

ElliotJLT/Claude-Skill-Potions

When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, and strips the agent to minimum viable form. Answers: "What can we remove without degrading quality?" The goal is the leanest agent that still works.

AI, LLMs & Agents

Battle Plan

62

ElliotJLT/Claude-Skill-Potions

Before ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in sequence: rubber-duck (clarify scope) -> pre-mortem (assess risks) -> eta (estimate time) -> final confirmation. Do not start coding until the battle plan is approved.

Software Development

Breadcrumbs

62

ElliotJLT/Claude-Skill-Potions

Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records what was tried, what worked, what failed, and context for next time. On session start, reads breadcrumbs to understand history. Session-to-session memory without manual updates.

Productivity & Notes

Loose Ends

62

ElliotJLT/Claude-Skill-Potions

Before declaring work complete, checks for loose ends: unused imports, TODO comments created, missing tests, stale references, incomplete error handling. Activates after implementing features or fixes. The cleanup that always gets skipped.

Testing & QA

Creating Skills

43

obra/clank

TDD for process documentation - test with subagents before writing, iterate until bulletproof

Testing & QA26

Pipeline

62

ElliotJLT/Claude-Skill-Potions

Orchestration pattern for sequential, dependent tasks. When work must flow through stages where each stage depends on the previous (design → implement → test → review), structure as a pipeline with explicit handoffs. Each stage completes before the next begins.

Testing & QA

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.