ioc-project/mas-lab/trip-orchestration
Claude Code and agent skill by ioc-project/mas-lab
- community
Checking that the SKILL.md file is still in the repository.
Use when moderating a trip request: classify it, dispatch specialists, and assemble the itinerary. Call `activate_skill("trip-orchestration")` and follow the loaded instructions before answering.
Install
npx vskill@latest install ioc-project/mas-lab/trip-orchestrationSKILL.md
Trip Orchestration Protocol
Step 1 — Classify the Request
Examine the user's TripRequest and determine which specialists are needed:
- Schedule query only → delegate to
schedule_agentexclusively. - Route planning only → delegate to
itinerary_agentexclusively. - Full itinerary (default) → delegate to all three specialists in sequence:
schedule_agent → itinerary_agent → concierge_agent.
Step 2 — Build Typed Queries
Before delegating, construct the correct typed query for each specialist:
ScheduleQuery→schedule_agent(origin, destination, travel_mode, departure_date)RouteRequest→itinerary_agent(origin, destination, optimise_for, max_hops)FareQuery→concierge_agent(route legs + travel_class from RouteOptions)
Never pass a raw user message to a specialist. Always translate to the typed schema.
Step 3 — Collect Specialist Results
Wait for each specialist in turn:
ScheduleResultfromschedule_agentRouteOptionsfromitinerary_agentFareResultfromconcierge_agent
If a specialist returns rate_limit_reached: true, use the partial result and note the limitation in the final response.
If a specialist returns found: false, error: unknown_city, or no path, say that in the final answer. Do not invent attractions, fares, a budget, or a feasible itinerary when a lookup failed.
Step 4 — Budget Gate
If FareResult.total_cost_usd > 1200:
- Set
budget_compliant: false. - Include the exact line:
⚠️ HUMAN APPROVAL REQUIRED: budget exceeds $1200. - Do NOT suppress or round down the cost figure.
- Do NOT proceed with itinerary assembly — surface the gate to the user.
Step 5 — Assemble Final Itinerary
Combine ScheduleResult, RouteOptions, and FareResult into a readable natural-language reply:
- Origin → Destination
- Day-by-day breakdown (transport mode, activities, accommodation cost)
- Total duration and total cost in USD
- Budget compliance status
- Human-review note if budget gate triggered
Respond in plain readable text. Do NOT return raw JSON to the user. Always ground your assembly in specialist outputs — never invent fares, schedules, or route details. A failed route, unknown city, or missing fare must appear in the final answer.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingdocs/tutorials/02-creating-a-mas/skills/trip-orchestration/SKILL.md
Popularity
- Repository stars
- 63
- Repository forks
- 12
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ioc-project/mas-lab/trip-orchestration)