Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub · AI
Speckit Swarm
Orchestrates complex tasks by detecting keywords, decomposing work into parallel chunks, and coordinating multiple specialized agent personas for full execut...
skill openclawclawhub Free
Orchestrates complex tasks by detecting keywords, decomposing work into parallel chunks, and coordinating multiple specialized agent personas for full execut...
⬇ 0 downloads ★ 0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- SKILL.md, _meta.json, src/complexity.ts, src/concurrency.ts, src/index.ts, src/personas/explore.ts
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.1.0
Provenance
- Publisher
- Heldinhow
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Overview
Native implementation of oh-my-opencode-style orchestration using OpenClaw's tools.
Core Components
Ultrawork Detector - Detects "ulw"/"ultrawork" keywords and triggers parallel execution Agent Personas - Specialized system prompts for different tasks Task Planner - Breaks complex tasks into parallel chunks Continuation Enforcer - Ensures tasks complete fully
File Structure
skills/speckit-swarm/ ├── SKILL.md # This file ├── src/ │ ├── ultrawork.ts # Ultrawork detection & trigger │ ├── personas/ │ │ ├── mod.ts # Persona exports │ │ ├── sisyphus.ts # Main orchestrator │ │ ├── hephaestus.ts # Deep worker │ │ ├── oracle.ts # Design/debug │ │ ├── librarian.ts # Research/docs │ │ └── explore.ts # Fast scout │ ├── planner.ts # Task decomposition │ └── index.ts # Main entry
Manual Mode
# Use personas directly sessions_spawn task:"..." model:"minimax-m2.5" thinking:"high"
Ultrawork Mode
When user includes "ulw" or "ultrawork": Detect keyword Decompose task into parallel chunks Execute with parallel_spawn Aggregate results
Sisyphus (Main Orchestrator)
Model: minimax-m2.5 Thinking: high Behavior: Relentless execution, parallel coordination, todo tracking
Hephaestus (Deep Worker)
Model: minimax-m2.5 Thinking: high Behavior: Autonomous execution, no hand-holding, completes full scope
Oracle (Design/Debug)
Model: minimax-m2.5 Thinking: high Behavior: Architecture decisions, bug hunting, code review
Librarian (Research)
Model: minimax-m2.1 Thinking: medium Behavior: Docs lookup, code exploration, pattern finding
Explore (Scout)
Model: minimax-m2.5-highspeed Thinking: low Behavior: Fast grep, file finding, quick analysis
1. Direct Persona Usage
import { PERSONAS, buildTaskPrompt } from './speckit-swarm'; const persona = PERSONAS.hephaestus; const task = "Fix the login bug in auth.ts"; sessions_spawn({ task: buildTaskPrompt({ task, persona: 'hephaestus' }), model: persona.config.model, thinking: persona.config.thinking });
2. Ultrawork Mode (auto-detected)
When user includes "ulw" or "ultrawork": import { planTask, shouldUseUltrawork } from './speckit-swarm'; const task = "ulw refactor the auth module"; if (shouldUseUltrawork(task)) { const plan = planTask(task); // Execute plan.chunks with parallel_spawn }
3. Task Decomposition
import { planTask } from './speckit-swarm'; const plan = planTask("Create a new API endpoint"); // plan.chunks = [{ label: 'spec', ... }, { label: 'setup', ... }, ...]
Ultrawork Handler
O handler detecta "ulw" automaticamente e prepara tarefas para parallel_spawn.
Funções Exportadas
// Verifica se contém keyword ulw containsUltrawork(task: string): boolean // Limpa o prefixo ulw da tarefa cleanUltraworkTask(task: string): string // Prepara execução ultrawork prepareUltrawork(task: string): { shouldExecute: boolean; chunks: Array<{ label: string; task: string; model?: string; thinking?: string; }>; cleanedTask: string; }
Exemplo de Uso
// Na minha resposta, quando receber mensagem com "ulw": const ultrawork = prepareUltrawork("ulw create a new API"); if (ultrawork.shouldExecute) { // Executar com parallel_spawn parallel_spawn({ tasks: ultrawork.chunks, wait: "all" }); }
Análise de Segurança de Concorrência
Antes de paralelizar, verifico se não há conflitos: Tipo de TarefaEstratégiaCriar novo projeto/CLI/APIPARALLEL ✓Múltiplos arquivos novosPARALLEL ✓Refatorar móduloCAUTIOUS (verifica dependências)Corrigir bugSEQUENTIAL ✗Editar mesmo arquivoSEQUENTIAL ✗Tarefa simplesSINGLE
Fluxo de Decisão
Analiso complexidade - É uma tarefa grande? Verifico conflitos - Vai mexer no mesmo arquivo? Decido estratégia - parallel / sequential / single Isso evita problemas de concorrência quando múltiplos agentes tentam modificar o mesmo arquivo.
Exemplo de Uso
// Detecção automática const result = prepareParallelExecution("criar um novo CLI"); // result.shouldExecute = true (detectou complexidade) if (result.shouldExecute) { parallel_spawn({ tasks: result.chunks, wait: "all" }); }
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
4 Scripts1 Docs1 Config
- SKILL.md
- src/complexity.ts
- src/concurrency.ts
- src/index.ts
- src/personas/explore.ts
- _meta.json