{"id":"fd4e98e9-6b7f-4e03-bbdb-2b50a964fb1b","entityType":"agent","slug":"clawhub-heldinhow-speckit-swarm","name":"Speckit Swarm","canonicalUrl":"https://www.xpersona.co/agent/clawhub-heldinhow-speckit-swarm","canonicalPath":"/agent/clawhub-heldinhow-speckit-swarm","generatedAt":"2026-10-11T03:55:35.857Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T00:48:01.481Z","emptyReason":null},"description":"Orchestrates complex tasks by detecting keywords, decomposing work into parallel chunks, and coordinating multiple specialized agent personas for full execut... Skill: Speckit Swarm Owner: heldinhow Summary: Orchestrates complex tasks by detecting keywords, decomposing work into parallel chunks, and coordinating multiple specialized agent personas for full execut... Tags: latest:1.1.0 Version history: v1.1.0 | 2026-02-18T00:22:42.436Z | user Added concurrency safety check - prevents parallel conflicts v1.0.0 | 2026-02-18T00:19:36.381Z | user Initial release: agent orchestrat","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s17fhz4zhpt7ak28aaembt0hph8859pq:speckit-swarm","sourceUrl":"https://clawhub.ai/heldinhow/speckit-swarm","homepage":"https://clawhub.ai/heldinhow/skills/speckit-swarm","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/heldinhow/speckit-swarm","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/heldinhow/skills/speckit-swarm","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":62,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Orchestrates complex tasks by detecting keywords, decomposing work into parallel chunks, and coordinating multiple specialized agent personas for full execut..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T00:48:01.481Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T00:48:01.481Z","emptyReason":null},"stars":null,"forks":null,"downloads":1215,"packageName":null,"latestVersion":"1.1.0","tractionLabel":"1.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T00:48:01.417Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T00:48:01.481Z","lastCrawledAt":"2026-10-11T00:48:01.417Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T00:48:01.417Z","lastVerifiedAt":null,"highlights":[{"version":"1.1.0","createdAt":"2026-02-18T00:22:42.436Z","changelog":"Added concurrency safety check - prevents parallel conflicts","fileCount":14,"zipByteSize":14717},{"version":"1.0.0","createdAt":"2026-02-18T00:19:36.381Z","changelog":"Initial release: agent orchestration with auto-parallelization","fileCount":13,"zipByteSize":13167}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17fhz4zhpt7ak28aaembt0hph8859pq:speckit-swarm","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-speckit-swarm/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-speckit-swarm/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-speckit-swarm/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-speckit-swarm/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-speckit-swarm/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-speckit-swarm/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T03:55:35.857Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-speckit-swarm/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-speckit-swarm/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-speckit-swarm/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-heldinhow-speckit-swarm/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T00:48:01.481Z","emptyReason":null},"readme":"Skill: Speckit Swarm\n\nOwner: heldinhow\n\nSummary: Orchestrates complex tasks by detecting keywords, decomposing work into parallel chunks, and coordinating multiple specialized agent personas for full execut...\n\nTags: latest:1.1.0\n\nVersion history:\n\nv1.1.0 | 2026-02-18T00:22:42.436Z | user\n\nAdded concurrency safety check - prevents parallel conflicts\n\nv1.0.0 | 2026-02-18T00:19:36.381Z | user\n\nInitial release: agent orchestration with auto-parallelization\n\nArchive index:\n\nArchive v1.1.0: 14 files, 14717 bytes\n\nFiles: _meta.json (132b), SKILL.md (4863b), src/complexity.ts (2931b), src/concurrency.ts (3835b), src/index.ts (1005b), src/personas/explore.ts (1124b), src/personas/hephaestus.ts (1344b), src/personas/librarian.ts (1270b), src/personas/mod.ts (998b), src/personas/oracle.ts (1185b), src/personas/sisyphus.ts (1432b), src/planner.ts (3528b), src/ultrawork.ts (1721b), ultrawork-handler.ts (6179b)\n\nFile v1.1.0:SKILL.md\n\n# Speckit Swarm - Agent Orchestration System\n\n## Overview\n\nNative implementation of oh-my-opencode-style orchestration using OpenClaw's tools.\n\n## Architecture\n\n### Core Components\n\n1. **Ultrawork Detector** - Detects \"ulw\"/\"ultrawork\" keywords and triggers parallel execution\n2. **Agent Personas** - Specialized system prompts for different tasks\n3. **Task Planner** - Breaks complex tasks into parallel chunks\n4. **Continuation Enforcer** - Ensures tasks complete fully\n\n## File Structure\n\n```\nskills/speckit-swarm/\n├── SKILL.md                      # This file\n├── src/\n│   ├── ultrawork.ts              # Ultrawork detection & trigger\n│   ├── personas/\n│   │   ├── mod.ts               # Persona exports\n│   │   ├── sisyphus.ts          # Main orchestrator\n│   │   ├── hephaestus.ts        # Deep worker\n│   │   ├── oracle.ts            # Design/debug\n│   │   ├── librarian.ts         # Research/docs\n│   │   └── explore.ts            # Fast scout\n│   ├── planner.ts               # Task decomposition\n│   └── index.ts                 # Main entry\n```\n\n## Usage\n\n### Manual Mode\n```bash\n# Use personas directly\nsessions_spawn task:\"...\" model:\"minimax-m2.5\" thinking:\"high\"\n```\n\n### Ultrawork Mode\nWhen user includes \"ulw\" or \"ultrawork\":\n1. Detect keyword\n2. Decompose task into parallel chunks\n3. Execute with parallel_spawn\n4. Aggregate results\n\n## Personas\n\n### Sisyphus (Main Orchestrator)\n- Model: minimax-m2.5\n- Thinking: high\n- Behavior: Relentless execution, parallel coordination, todo tracking\n\n### Hephaestus (Deep Worker)\n- Model: minimax-m2.5\n- Thinking: high\n- Behavior: Autonomous execution, no hand-holding, completes full scope\n\n### Oracle (Design/Debug)\n- Model: minimax-m2.5\n- Thinking: high\n- Behavior: Architecture decisions, bug hunting, code review\n\n### Librarian (Research)\n- Model: minimax-m2.1\n- Thinking: medium\n- Behavior: Docs lookup, code exploration, pattern finding\n\n### Explore (Scout)\n- Model: minimax-m2.5-highspeed\n- Thinking: low\n- Behavior: Fast grep, file finding, quick analysis\n\n## How to Use\n\n### 1. Direct Persona Usage\n```typescript\nimport { PERSONAS, buildTaskPrompt } from './speckit-swarm';\n\nconst persona = PERSONAS.hephaestus;\nconst task = \"Fix the login bug in auth.ts\";\n\nsessions_spawn({\n  task: buildTaskPrompt({ task, persona: 'hephaestus' }),\n  model: persona.config.model,\n  thinking: persona.config.thinking\n});\n```\n\n### 2. Ultrawork Mode (auto-detected)\nWhen user includes \"ulw\" or \"ultrawork\":\n```typescript\nimport { planTask, shouldUseUltrawork } from './speckit-swarm';\n\nconst task = \"ulw refactor the auth module\";\nif (shouldUseUltrawork(task)) {\n  const plan = planTask(task);\n  // Execute plan.chunks with parallel_spawn\n}\n```\n\n### 3. Task Decomposition\n```typescript\nimport { planTask } from './speckit-swarm';\n\nconst plan = planTask(\"Create a new API endpoint\");\n// plan.chunks = [{ label: 'spec', ... }, { label: 'setup', ... }, ...]\n```\n\n## Ultrawork Handler\n\nO handler detecta \"ulw\" automaticamente e prepara tarefas para parallel_spawn.\n\n### Funções Exportadas\n\n```typescript\n// Verifica se contém keyword ulw\ncontainsUltrawork(task: string): boolean\n\n// Limpa o prefixo ulw da tarefa\ncleanUltraworkTask(task: string): string\n\n// Prepara execução ultrawork\nprepareUltrawork(task: string): {\n  shouldExecute: boolean;\n  chunks: Array<{\n    label: string;\n    task: string;\n    model?: string;\n    thinking?: string;\n  }>;\n  cleanedTask: string;\n}\n```\n\n### Exemplo de Uso\n\n```typescript\n// Na minha resposta, quando receber mensagem com \"ulw\":\n\nconst ultrawork = prepareUltrawork(\"ulw create a new API\");\n\nif (ultrawork.shouldExecute) {\n  // Executar com parallel_spawn\n  parallel_spawn({\n    tasks: ultrawork.chunks,\n    wait: \"all\"\n  });\n}\n```\n\n### Como Eu Detecto e Executo\n\n### Análise de Segurança de Concorrência\n\nAntes de paralelizar, verifico se não há conflitos:\n\n| Tipo de Tarefa | Estratégia |\n|----------------|------------|\n| Criar novo projeto/CLI/API | **PARALLEL** ✓ |\n| Múltiplos arquivos novos | **PARALLEL** ✓ |\n| Refatorar módulo | CAUTIOUS (verifica dependências) |\n| Corrigir bug | **SEQUENTIAL** ✗ |\n| Editar mesmo arquivo | **SEQUENTIAL** ✗ |\n| Tarefa simples | SINGLE |\n\n### Fluxo de Decisão\n\n1. **Analiso complexidade** - É uma tarefa grande?\n2. **Verifico conflitos** - Vai mexer no mesmo arquivo?\n3. **Decido estratégia** - parallel / sequential / single\n\nIsso evita problemas de concorrência quando múltiplos agentes tentam modificar o mesmo arquivo.\n\n### Exemplo de Uso\n\n```typescript\n// Detecção automática\nconst result = prepareParallelExecution(\"criar um novo CLI\");\n// result.shouldExecute = true (detectou complexidade)\n\nif (result.shouldExecute) {\n  parallel_spawn({\n    tasks: result.chunks,\n    wait: \"all\"\n  });\n}\n```\n\nFile v1.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn74nrx32v4n0423jptzg1v5kx80ssnf\",\n  \"slug\": \"speckit-swarm\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1771374162436\n}\n\nArchive v1.0.0: 13 files, 13167 bytes\n\nFiles: _meta.json (132b), SKILL.md (4559b), src/complexity.ts (2931b), src/index.ts (1005b), src/personas/explore.ts (1124b), src/personas/hephaestus.ts (1344b), src/personas/librarian.ts (1270b), src/personas/mod.ts (998b), src/personas/oracle.ts (1185b), src/personas/sisyphus.ts (1432b), src/planner.ts (3528b), src/ultrawork.ts (1721b), ultrawork-handler.ts (6179b)\n\nFile v1.0.0:SKILL.md\n\n# Speckit Swarm - Agent Orchestration System\n\n## Overview\n\nNative implementation of oh-my-opencode-style orchestration using OpenClaw's tools.\n\n## Architecture\n\n### Core Components\n\n1. **Ultrawork Detector** - Detects \"ulw\"/\"ultrawork\" keywords and triggers parallel execution\n2. **Agent Personas** - Specialized system prompts for different tasks\n3. **Task Planner** - Breaks complex tasks into parallel chunks\n4. **Continuation Enforcer** - Ensures tasks complete fully\n\n## File Structure\n\n```\nskills/speckit-swarm/\n├── SKILL.md                      # This file\n├── src/\n│   ├── ultrawork.ts              # Ultrawork detection & trigger\n│   ├── personas/\n│   │   ├── mod.ts               # Persona exports\n│   │   ├── sisyphus.ts          # Main orchestrator\n│   │   ├── hephaestus.ts        # Deep worker\n│   │   ├── oracle.ts            # Design/debug\n│   │   ├── librarian.ts         # Research/docs\n│   │   └── explore.ts            # Fast scout\n│   ├── planner.ts               # Task decomposition\n│   └── index.ts                 # Main entry\n```\n\n## Usage\n\n### Manual Mode\n```bash\n# Use personas directly\nsessions_spawn task:\"...\" model:\"minimax-m2.5\" thinking:\"high\"\n```\n\n### Ultrawork Mode\nWhen user includes \"ulw\" or \"ultrawork\":\n1. Detect keyword\n2. Decompose task into parallel chunks\n3. Execute with parallel_spawn\n4. Aggregate results\n\n## Personas\n\n### Sisyphus (Main Orchestrator)\n- Model: minimax-m2.5\n- Thinking: high\n- Behavior: Relentless execution, parallel coordination, todo tracking\n\n### Hephaestus (Deep Worker)\n- Model: minimax-m2.5\n- Thinking: high\n- Behavior: Autonomous execution, no hand-holding, completes full scope\n\n### Oracle (Design/Debug)\n- Model: minimax-m2.5\n- Thinking: high\n- Behavior: Architecture decisions, bug hunting, code review\n\n### Librarian (Research)\n- Model: minimax-m2.1\n- Thinking: medium\n- Behavior: Docs lookup, code exploration, pattern finding\n\n### Explore (Scout)\n- Model: minimax-m2.5-highspeed\n- Thinking: low\n- Behavior: Fast grep, file finding, quick analysis\n\n## How to Use\n\n### 1. Direct Persona Usage\n```typescript\nimport { PERSONAS, buildTaskPrompt } from './speckit-swarm';\n\nconst persona = PERSONAS.hephaestus;\nconst task = \"Fix the login bug in auth.ts\";\n\nsessions_spawn({\n  task: buildTaskPrompt({ task, persona: 'hephaestus' }),\n  model: persona.config.model,\n  thinking: persona.config.thinking\n});\n```\n\n### 2. Ultrawork Mode (auto-detected)\nWhen user includes \"ulw\" or \"ultrawork\":\n```typescript\nimport { planTask, shouldUseUltrawork } from './speckit-swarm';\n\nconst task = \"ulw refactor the auth module\";\nif (shouldUseUltrawork(task)) {\n  const plan = planTask(task);\n  // Execute plan.chunks with parallel_spawn\n}\n```\n\n### 3. Task Decomposition\n```typescript\nimport { planTask } from './speckit-swarm';\n\nconst plan = planTask(\"Create a new API endpoint\");\n// plan.chunks = [{ label: 'spec', ... }, { label: 'setup', ... }, ...]\n```\n\n## Ultrawork Handler\n\nO handler detecta \"ulw\" automaticamente e prepara tarefas para parallel_spawn.\n\n### Funções Exportadas\n\n```typescript\n// Verifica se contém keyword ulw\ncontainsUltrawork(task: string): boolean\n\n// Limpa o prefixo ulw da tarefa\ncleanUltraworkTask(task: string): string\n\n// Prepara execução ultrawork\nprepareUltrawork(task: string): {\n  shouldExecute: boolean;\n  chunks: Array<{\n    label: string;\n    task: string;\n    model?: string;\n    thinking?: string;\n  }>;\n  cleanedTask: string;\n}\n```\n\n### Exemplo de Uso\n\n```typescript\n// Na minha resposta, quando receber mensagem com \"ulw\":\n\nconst ultrawork = prepareUltrawork(\"ulw create a new API\");\n\nif (ultrawork.shouldExecute) {\n  // Executar com parallel_spawn\n  parallel_spawn({\n    tasks: ultrawork.chunks,\n    wait: \"all\"\n  });\n}\n```\n\n### Como Eu Detecto e Executo\n\n### Modo Automático (padrão)\nAgora não preciso de palavras-chave! Analiso a complexidade da tarefa:\n\n- **Tarefas simples** → executo diretamente\n- **Tarefas complexas** → uso parallel_spawn automaticamente\n\nIndicadores de complexidade:\n- \"criar\", \"implementar\", \"construir\", \"refatorar\"\n- Múltiplos passos (\"fazer X e depois Y\")\n- Múltiplos arquivos/deliverables\n- Palavras como \"ulw\" ou \"ultrawork\" (opcional)\n\n### Exemplo de Uso\n\n```typescript\n// Detecção automática\nconst result = prepareParallelExecution(\"criar um novo CLI\");\n// result.shouldExecute = true (detectou complexidade)\n\nif (result.shouldExecute) {\n  parallel_spawn({\n    tasks: result.chunks,\n    wait: \"all\"\n  });\n}\n```\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn74nrx32v4n0423jptzg1v5kx80ssnf\",\n  \"slug\": \"speckit-swarm\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1771373976381\n}","readmeExcerpt":"Skill: Speckit Swarm Owner: heldinhow Summary: Orchestrates complex tasks by detecting keywords, decomposing work into parallel chunks, and coordinating multiple specialized agent personas for full execut... Tags: latest:1.1.0 Version history: v1.1.0 | 2026-02-18T00:22:42.436Z | user Added concurrency safety check - prevents parallel conflicts v1.0.0 | 2026-02-18T00:19:36.381Z | user Initial release: agent orchestrat","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"skills/speckit-swarm/\n├── SKILL.md                      # This file\n├── src/\n│   ├── ultrawork.ts              # Ultrawork detection & trigger\n│   ├── personas/\n│   │   ├── mod.ts               # Persona exports\n│   │   ├── sisyphus.ts          # Main orchestrator\n│   │   ├── hephaestus.ts        # Deep worker\n│   │   ├── oracle.ts            # Design/debug\n│   │   ├── librarian.ts         # Research/docs\n│   │   └── explore.ts            # Fast scout\n│   ├── planner.ts               # Task decomposition\n│   └── index.ts                 # Main entry"},{"language":"bash","snippet":"# Use personas directly\nsessions_spawn task:\"...\" model:\"minimax-m2.5\" thinking:\"high\""},{"language":"typescript","snippet":"import { PERSONAS, buildTaskPrompt } from './speckit-swarm';\n\nconst persona = PERSONAS.hephaestus;\nconst task = \"Fix the login bug in auth.ts\";\n\nsessions_spawn({\n  task: buildTaskPrompt({ task, persona: 'hephaestus' }),\n  model: persona.config.model,\n  thinking: persona.config.thinking\n});"},{"language":"typescript","snippet":"import { planTask, shouldUseUltrawork } from './speckit-swarm';\n\nconst task = \"ulw refactor the auth module\";\nif (shouldUseUltrawork(task)) {\n  const plan = planTask(task);\n  // Execute plan.chunks with parallel_spawn\n}"},{"language":"typescript","snippet":"import { planTask } from './speckit-swarm';\n\nconst plan = planTask(\"Create a new API endpoint\");\n// plan.chunks = [{ label: 'spec', ... }, { label: 'setup', ... }, ...]"},{"language":"typescript","snippet":"// Verifica se contém keyword ulw\ncontainsUltrawork(task: string): boolean\n\n// Limpa o prefixo ulw da tarefa\ncleanUltraworkTask(task: string): string\n\n// Prepara execução ultrawork\nprepareUltrawork(task: string): {\n  shouldExecute: boolean;\n  chunks: Array<{\n    label: string;\n    task: string;\n    model?: string;\n    thinking?: string;\n  }>;\n  cleanedTask: string;\n}"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"# Speckit Swarm - Agent Orchestration System\n\n## Overview\n\nNative implementation of oh-my-opencode-style orchestration using OpenClaw's tools.\n\n## Architecture\n\n### Core Components\n\n1. **Ultrawork Detector** - Detects \"ulw\"/\"ultrawork\" keywords and triggers parallel execution\n2. **Agent Personas** - Specialized system prompts for different tasks\n3. **Task Planner** - Breaks complex tasks into parallel chunks\n4. **Continuation Enforcer** - Ensures tasks complete fully\n\n## File Structure\n\n```\nskills/speckit-swarm/\n├── SKILL.md                      # This file\n├── src/\n│   ├── ultrawork.ts              # Ultrawork detection & trigger\n│   ├── personas/\n│   │   ├── mod.ts               # Persona exports\n│   │   ├── sisyphus.ts          # Main orchestrator\n│   │   ├── hephaestus.ts        # Deep worker\n│   │   ├── oracle.ts            # Design/debug\n│   │   ├── librarian.ts         # Research/docs\n│   │   └── explore.ts            # Fast scout\n│   ├── planner.ts               # Task decomposition\n│   └── index.ts                 # Main entry\n```\n\n## Usage\n\n### Manual Mode\n```bash\n# Use personas directly\nsessions_spawn task:\"...\" model:\"minimax-m2.5\" thinking:\"high\"\n```\n\n### Ultrawork Mode\nWhen user includes \"ulw\" or \"ultrawork\":\n1. Detect keyword\n2. Decompose task into parallel chunks\n3. Execute with parallel_spawn\n4. Aggregate results\n\n## Personas\n\n### Sisyphus (Main Orchestrator)\n- Model: minimax-m2.5\n- Thinking: high\n- Behavior: Relentless execution, parallel coordination, todo tracking\n\n### Hephaestus (Deep Worker)\n- Model: minimax-m2.5\n- Thinking: high\n- Behavior: Autonomous execution, no hand-holding, completes full scope\n\n### Oracle (Design/Debug)\n- Model: minimax-m2.5\n- Thinking: high\n- Behavior: Architecture decisions, bug hunting, code review\n\n### Librarian (Research)\n- Model: minimax-m2.1\n- Thinking: medium\n- Behavior: Docs lookup, code exploration, pattern finding\n\n### Explore (Scout)\n- Model: minimax-m2.5-highspeed\n- Thinking: low\n- Behavior: Fast grep, file finding, quick analysis\n\n## How to Use\n\n### 1. Direct Persona Usage\n```typescript\nimport { PERSONAS, buildTaskPrompt } from './speckit-swarm';\n\nconst persona = PERSONAS.hephaestus;\nconst task = \"Fix the login bug in auth.ts\";\n\nsessions_spawn({\n  task: buildTaskPrompt({ task, persona: 'hephaestus' }),\n  model: persona.config.model,\n  thinking: persona.config.thinking\n});\n```\n\n### 2. Ultrawork Mode (auto-detected)\nWhen user includes \"ulw\" or \"ultrawork\":\n```typescript\nimport { planTask, shouldUseUltrawork } from './speckit-swarm';\n\nconst task = \"ulw refactor the auth module\";\nif (shouldUseUltrawork(task)) {\n  const plan = planTask(task);\n  // Execute plan.chunks with parallel_spawn\n}\n```\n\n### 3. Task Decomposition\n```typescript\nimport { planTask } from './speckit-swarm';\n\nconst plan = planTask(\"Create a new API endpoint\");\n// plan.chunks = [{ label: 'spec', ... }, { label: 'setup', ... }, ...]\n```\n\n## Ultrawork Handler\n\nO handler detecta \"ulw\" automaticamente e prepara tarefas para paral"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn74nrx32v4n0423jptzg1v5kx80ssnf\",\n  \"slug\": \"speckit-swarm\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1771374162436\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Orchestrates complex tasks by detecting keywords, decomposing work into parallel chunks, and coordinating multiple specialized agent personas for full execut... Skill: Speckit Swarm Owner: heldinhow Summary: Orchestrates complex tasks by detecting keywords, decomposing work into parallel chunks, and coordinating multiple specialized agent personas for full execut... Tags: latest:1.1.0 Version history: v1.1.0 | 2026-02-18T00:22:42.436Z | user Added concurrency safety check - prevents parallel conflicts v1.0.0 | 2026-02-18T00:19:36.381Z | user Initial release: agent orchestrat","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":586,"uniquenessScore":65,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T00:48:01.481Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T00:48:01.481Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T03:55:35.857Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}