borghei/Claude-Skills / engineering/agenthub
agenthub
VerifiedRuns a multi-agent job as a dependency graph: validates the DAG, tracks each agent's state on a board, then ranks and merges their outputs. Use when spawning parallel agents, monitoring a run, or merging results.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.8 KB |
| assets/sample_session.json | config | 4.5 KB |
| assets/sample_workflow.json | config | 1.5 KB |
| references/multi-agent-patterns.md | markdown | 5.6 KB |
| references/operations-and-quality.md | markdown | 2.9 KB |
| references/orchestration-core.md | markdown | 4.9 KB |
| scripts/board_manager.py | script | 10.9 KB |
| scripts/dag_analyzer.py | script | 13.5 KB |
| scripts/result_ranker.py | script | 11.0 KB |
| scripts/session_manager.py | script | 12.7 KB |
| skills/board.md | markdown | 2.2 KB |
| skills/eval.md | markdown | 2.2 KB |
| skills/init.md | markdown | 2.0 KB |
| skills/merge.md | markdown | 2.3 KB |
| skills/run.md | markdown | 2.1 KB |
| skills/spawn.md | markdown | 1.9 KB |
| skills/status.md | markdown | 2.1 KB |
assets/sample_session.json
View on GitHub{
"session_id": "0de18ecb",
"workflow_name": "competitive-analysis",
"workflow_description": "Research competitors, collect pricing, analyse positioning, write a summary",
"created_at": "2026-11-08T17:00:26.056011",
"started_at": "2026-11-08T17:00:26.056011",
"completed_at": null,
"state": "RUNNING",
"config": {
"max_parallel": 3,
"timeout_per_agent": 300,
"retry_on_failure": 1,
"quality_threshold": 0.7
},
"agents": {
"researcher": {
"state": "COMPLETED",
"task": "Research competitor landscape and market size",
"inputs": [
"product_description"
],
"expected_outputs": [
"competitor_list",
"market_size"
],
"dependencies": [],
"outputs": {
"competitor_list": "## Competitors\n- Acme (enterprise)\n- Bolt (SMB)\n- Corex (open source)",
"market_size": "Estimated 1.2B USD serviceable market, growing ~18% a year, based on three analyst reports."
},
"started_at": null,
"completed_at": "2026-11-08T17:00:26.090687",
"duration_s": null,
"retries": 0,
"max_retries": 1,
"eval_score": 0.82,
"error": null
},
"pricing_collector": {
"state": "COMPLETED",
"task": "Collect pricing tiers for each competitor",
"inputs": [
"competitor_list"
],
"expected_outputs": [
"pricing_data"
],
"dependencies": [
"researcher"
],
"outputs": {
"pricing_data": "## Pricing\n- Acme: 49/user/month, annual only\n- Bolt: 19/user/month\n- Corex: free core, 12/user hosted"
},
"started_at": null,
"completed_at": "2026-11-08T17:00:26.127149",
"duration_s": null,
"retries": 0,
"max_retries": 1,
"eval_score": 0.74,
"error": null
},
"feature_collector": {
"state": "COMPLETED",
"task": "Build a feature matrix for each competitor",
"inputs": [
"competitor_list"
],
"expected_outputs": [
"feature_matrix"
],
"dependencies": [
"researcher"
],
"outputs": {
"feature_matrix": "SSO: Acme yes, Bolt no, Corex paid."
},
"started_at": null,
"completed_at": "2026-11-08T17:00:26.163591",
"duration_s": null,
"retries": 0,
"max_retries": 1,
"eval_score": 0.61,
"error": null
},
"analyst": {
"state": "FAILED",
"task": "Analyse positioning opportunities and pricing strategy",
"inputs": [
"pricing_data",
"feature_matrix",
"market_size"
],
"expected_outputs": [
"positioning_report",
"pricing_recommendation"
],
"dependencies": [
"pricing_collector",
"feature_collector"
],
"outputs": null,
"started_at": null,
"completed_at": "2026-11-08T17:00:26.200608",
"duration_s": null,
"retries": 0,
"max_retries": 1,
"eval_score": null,
"error": "timeout after 180s"
},
"writer": {
"state": "PENDING",
"task": "Write an executive summary of the findings",
"inputs": [
"positioning_report",
"pricing_recommendation"
],
"expected_outputs": [
"executive_summary"
],
"dependencies": [
"analyst"
],
"outputs": null,
"started_at": null,
"completed_at": null,
"duration_s": null,
"retries": 0,
"max_retries": 1,
"eval_score": null,
"error": null
}
},
"history": [
{
"timestamp": "2026-11-08T17:00:26.056011",
"event": "session_created",
"detail": "Workflow: competitive-analysis"
},
{
"timestamp": "2026-11-08T17:00:26.090687",
"event": "agent_state_change",
"agent": "researcher",
"old_state": "READY",
"new_state": "COMPLETED",
"newly_ready": [
"pricing_collector",
"feature_collector"
]
},
{
"timestamp": "2026-11-08T17:00:26.127149",
"event": "agent_state_change",
"agent": "pricing_collector",
"old_state": "READY",
"new_state": "COMPLETED"
},
{
"timestamp": "2026-11-08T17:00:26.163591",
"event": "agent_state_change",
"agent": "feature_collector",
"old_state": "READY",
"new_state": "COMPLETED",
"newly_ready": [
"analyst"
]
},
{
"timestamp": "2026-11-08T17:00:26.200608",
"event": "agent_state_change",
"agent": "analyst",
"old_state": "READY",
"new_state": "FAILED"
}
]
}Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |