Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Divide Conquer

ASecurity

Split a large task into independent subtasks, delegate them to child sessions for parallel execution, and merge the results. Use when a task can be broken into non-overlapping pieces that don't depend on each other's output. Not for consensus/review (use consensus-delegation) or benchmarks (use bench). Triggers: "분할 정복", "병렬 처리", "parallel execution", "split and process".

10 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsgosecurity

Works with

mcp

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add fritzprix/libr-agent --skill divide-conquer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Divide Conquer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Divide Conquer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/fritzprix-divide-conquer/badge)](https://www.skillsdirectory.com/skills/fritzprix-divide-conquer)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: divide-conquer
description: >
  Split a large task into independent subtasks, delegate them to child sessions
  for parallel execution, and merge the results. Use when a task can be broken
  into non-overlapping pieces that don't depend on each other's output.
  Not for consensus/review (use consensus-delegation) or benchmarks (use bench).
  Triggers: "분할 정복", "병렬 처리", "parallel execution", "split and process".
---

# Divide-Conquer

The Divide-Conquer pattern splits a complex task into independent subtasks, delegates them to parallel child sessions, collects their results, and merges them into a final output.

## 6-Stage Workflow

```
┌─────────────────────────────────────────────────────┐
│                    Parent Session                    │
│                                                      │
│  1. Decompose: break task into independent pieces    │
│  2. Assign: pick assistant(s) + workspace strategy   │
│  3. Spawn: batch children (respect concurrency limit)│
│  4. Monitor: poll/check each child                   │
│  5. Merge: assemble results into final output        │
│  6. Verify: final quality check                      │
└──────────┬──────────┬──────────┬─────────────────────┘
           │          │          │
     ┌─────▼─────┐ ┌─▼────────┐ ┌▼──────────┐
     │ Child 1   │ │ Child 2  │ │ Child N   │
     │ (Module A)│ │(Module B)│ │(Module C) │
     └───────────┘ └──────────┘ └───────────┘
```

1. **Decomposition**: Divide the task into non-overlapping, independent units. See [decomposition-rules.md](references/decomposition-rules.md).
2. **Assignment**: Assign subtasks to suitable assistants (homogeneous or heterogeneous). Before creating a child, inspect `agent__listAgents(type="sessions")` and reuse an Idle child with the same assistant ID when its workspace contract is compatible.
3. **Workspace Strategy**: Decide whether children share the parent workspace (`workspaceOverride`) or use isolated workspaces (**default: isolated** for plain `spawnSession`; org members inherit the org root unless overridden).
4. **Spawn & Monitor**: Spawn sessions in batches respecting the concurrency limit (default: `maxConcurrentActiveSessions` is 4).
5. **Merge**: Assemble output artifacts based on merge patterns. See [merge-patterns.md](references/merge-patterns.md).
6. **Verify**: Run build/tests to ensure integration integrity. Retries failed subtasks if needed. For strict proof-before-done (path invariants, reject/re-steer), follow **`delegation-eval-loop`** after `delegate` mechanics.

## 🛠️ MCP Tools Guide

- **Discovery**: Use `agent__listAgents(type="configs")` to find assistant IDs.
- **Delegation**: Use `agent__messageToSession(..., reset=true)` to assign fresh work to a suitable Idle matching-role child. Use `agent__spawnSession(..., waitForResult=false)` only when no suitable child exists, a different role or workspace is needed, or another parallel capacity slot is required.
- **Monitoring**: Check status via `agent__listAgents(type="sessions")` and wait for completion via `agent__checkSession(sessionId, wait=true)`.
- **Rework**: Use `agent__messageToSession(sessionId, message)` to wake/retry paused/error sessions.
- **Cancellation**: Use `agent__stopSession(sessionId)` to abort hung subtasks.

## ⚖️ `consensus-delegation` vs `divide-conquer`

| Aspect | Consensus Delegation | Divide-Conquer |
|--------|----------------------|----------------|
| **Goal** | Get multiple perspectives on one query | Complete a large task by dividing work |
| **Subtasks** | Same task, different angles (e.g. security, perf) | Different, non-overlapping work scopes |
| **Output** | Comparison, synthesis, final decision | Combined/merged physical artifacts |
| **Recovery** | Dialogue to resolve conflicts | Rework specific failed subtasks |

Attribution

fritzprixfritzprix
View sourceMore from fritzprix →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →