Delegation

Decide when and how to delegate work to subagents (planner, builder, designer, documenter, tester, reviewer). Use when dispatching subagents, running parallel tasks, choosing a subagent for a job, or deciding inline-vs-delegate. Front-load triggers: delegate, subagent, parallel, task dispatch, spawn agent, launch agents.

9 stars 1 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add PanPanFR/oh-my-openkilo --skill delegation
Manual install
git clone --depth 1 https://github.com/PanPanFR/oh-my-openkilo.git /tmp/oh-my-openkilo
mkdir -p ~/.claude/skills
cp -r /tmp/oh-my-openkilo/skills/delegation ~/.claude/skills/delegation

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

From the SKILL.md

# Delegation Policy

You have specialized subagents. Delegate when it improves quality or speed.

## Agents and Subagents

| Agent | Use for |
|----------|---------|
| `planner` | Pre-implementation design, brainstorming, architecture planning, implementation plans. Primary mode; user switches to planner directly for upfront design. Never Task-spawned |
| `builder` | Primary agent, never Task-spawned. Implementation, refactors, multi-step execution of well-defined tasks |
| `designer` | UI/frontend builds - components, design system, accessibility |
| `documenter` | Technical writing - create and improve documentation in `docs/` |
| `tester` | Test suites - write, run, iterate failures in isolation, report compact results |
| `reviewer` | Code + security review of diffs vs repo standards and spec (read-only) |

## When to Delegate (DO)

- Task matches a subagent's specialization AND benefits from isolated context
- Independent subtasks exist -> launch them ALL in parallel in a SINGLE message (multiple Task calls)
- Task is large-scale search/audit/research that would bloat your context
- Quick web grab (1-2 URLs, no synthesis needed) -> use native `webfetch`/`websearch` directly, don't delegate; deep multi-source research -> decompose into sub-questions, fetch natively
- Security-sensitive review -> `reviewer` (specialized checklist, verified findings)
- Writing tests alongside implementation -> `tester` (parallel: you implement, it tests)
Read the full skill on GitHub

Details

Skill name
delegation
Path
skills/delegation/SKILL.md
License
MIT
Repo updated
2 November 2026

FAQ

What does the Delegation skill do?

Decide when and how to delegate work to subagents (planner, builder, designer, documenter, tester, reviewer). Use when dispatching subagents, running parallel tasks, choosing a subagent for a job, or deciding inline-vs-delegate. Front-load triggers: delegate, subagent, parallel, task dispatch, spawn agent, launch agents.

How do I install the Delegation skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add PanPanFR/oh-my-openkilo --skill delegation. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Delegation popular?

It lives in PanPanFR/oh-my-openkilo, which has 9 GitHub stars and 1 forks.

Related skills

Adaptive

9

PanPanFR/oh-my-openkilo

Instructions to make or update an app's UI so that it adapts to different Android devices including phones, tablets, foldables, laptops, desktop, TV, Auto, and XR. It includes how to handle different window sizes, pointing devices (such as mouse) and text entry devices (such as keyboard) using the Compose MediaQuery API, and how to preserve UI, navigation, scroll, and media playback state across configuration changes (such as folding/unfolding a foldable, rotating a device, or resizing a window). It also covers multi-pane layouts using Navigation3 Scenes, adaptive UI components (such as button

Mobile Development

Agentmemory

9

PanPanFR/oh-my-openkilo

Index for agentmemory internals: how it is wired into a host agent, its architecture and ports, configuration flags, capture hooks, MCP tool surface, and REST fallback. Use when installing or debugging agentmemory itself, when a memory tool name or parameter is unclear, or when capture is not recording. For normal recall and save work, use agentmemory-ops instead.

AI, LLMs & Agents

Agentmemory History

9

PanPanFR/oh-my-openkilo

Read past work: resume the last session, recap recent sessions, list agent-linked commits, trace a line back to the session that wrote it, or compact the current conversation for handoff. Use when the user says "where were we", "resume", "recap", "session history", "what did we do", "why is this code here", "who wrote this", or "handoff".

AI, LLMs & Agents

Ml Kit Genai Prompt API

9

PanPanFR/oh-my-openkilo

Analyzes Android codebases to implement ML Kit GenAI Prompt API. Use this skill to send natural language requests on-device to Gemini Nano, use structured output with Prompt API, implement prefix caching, optimize the current prompt, or apply best practices.

AI, LLMs & Agents

Caveman Stats

9

PanPanFR/oh-my-openkilo

Show recorded output and cache-read token usage and mode attribution for the current Claude Code session, or locate the host's native usage report. Trigger: /caveman-stats.

AI, LLMs & Agents

Mlkit Agent API

9

PanPanFR/oh-my-openkilo

Builds autonomous on-device agentic workflows in Android apps using the ML Kit GenAI Agent API powered by Gemini Nano and AICore. Use this skill when implementing conversational agents, multi-turn chat with AgentSession in a ViewModel, autonomous tool calling using Android AppFunctions (@AppFunctionDeclaration and AppFunctionAgentTools.discover), ephemeral single-turn execution with runner.runSingleTurnAsync, or handling GenAiException error resilience. It solves the problem of orchestrating local reasoning loops, typed tool dispatch, and session persistence on-device with zero cloud latency a

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.