AOC Orchestrator
Main coordinator for the automated Advent of Code workflow. Orchestrates puzzle fetching, TDD solving, and submission for daily AoC challenges. Use when running the full automated solving pipeline or when user requests to solve an AoC day.
Best use case
AOC Orchestrator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Main coordinator for the automated Advent of Code workflow. Orchestrates puzzle fetching, TDD solving, and submission for daily AoC challenges. Use when running the full automated solving pipeline or when user requests to solve an AoC day.
Teams using AOC Orchestrator should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/aoc-orchestrator/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How AOC Orchestrator Compares
| Feature / Agent | AOC Orchestrator | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Main coordinator for the automated Advent of Code workflow. Orchestrates puzzle fetching, TDD solving, and submission for daily AoC challenges. Use when running the full automated solving pipeline or when user requests to solve an AoC day.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# AOC Orchestrator
## Purpose
This skill is the main coordinator for the automated Advent of Code workflow. It orchestrates the entire process from puzzle fetching to submission, managing the execution of other specialized skills and handling the overall workflow state.
## When to Use This Skill
- Automatically triggered by cron/launchd on puzzle unlock days (December 1-12, 2025)
- Can be manually invoked for testing or re-running specific days
- Used when the user wants to execute the full end-to-end workflow
## Workflow Steps
### 0. Pre-flight Check: Is This Day Already Solved?
**CRITICAL**: This MUST be the first step. Do not proceed if the puzzle is already complete.
1. Run `aoc calendar --year 2025` to see progress (completed days show decorations/artwork)
2. Check if report exists: `puzzles/day<DD>/report.md` - if it shows both parts completed, EXIT
3. Check state file if it exists: `state/day<DD>.json`
**If both parts are already solved**: DO NOT proceed. Report "Day X is already complete! Nothing to do." and EXIT.
### 1. Initialization (only if not already complete)
```bash
# Check current date and determine which day to solve
# Verify session cookie is configured
```
### 2. Invoke Puzzle Fetcher Skill
- Download puzzle description and input
- Parse examples and expected outputs
- Extract part 1 and part 2 requirements
### 3. Invoke TDD Solver Skill - Part 1
- Generate test cases from examples
- Implement solution using TDD
- Verify all tests pass
- Generate answer from real input
### 4. Invoke Submission Handler Skill - Part 1
- Submit part 1 answer
- Parse response
- Handle success/failure
### 5. If Part 1 Succeeds, Invoke TDD Solver Skill - Part 2
- Parse part 2 requirements
- Generate new test cases
- Extend or rewrite solution for part 2
- Verify all tests pass
### 6. Invoke Submission Handler Skill - Part 2
- Submit part 2 answer
- Handle final results
## Error Handling
### Puzzle Not Yet Available
```
If puzzle unlock time not reached:
- Log: "Puzzle for day X not yet available"
- Exit gracefully
- Next cron execution will retry
```
### Already Solved
```
If day already has both stars:
- Log: "Day X already completed"
- Exit gracefully
- No further action needed
```
### Network Errors
```
If network request fails:
- Log error details
- Retry up to 3 times with exponential backoff
- If still failing, exit and alert
```
### Compilation Errors
```
If Rust code fails to compile:
- Log compiler errors
- Attempt to fix based on error messages
- Retry compilation
- Max 5 fix attempts per part
```
## State Management
Track workflow state in `state/day{day}.json`:
```json
{
"day": 1,
"year": 2025,
"status": "in_progress",
"part1": {
"status": "completed",
"answer": 24000,
"submitted_at": "2025-12-01T05:01:23Z",
"attempts": 1
},
"part2": {
"status": "in_progress",
"answer": null,
"submitted_at": null,
"attempts": 0
},
"started_at": "2025-12-01T05:00:15Z",
"completed_at": null
}
```
## Success Criteria
- ✅ Both part 1 and part 2 answers accepted
- ✅ All tests passing
- ✅ Code compiles without warnings
- ✅ Solution completes in < 15 seconds
- ✅ State file updated correctly
## Logging
Log all actions to `logs/day{day}.log`:
```
[2025-12-01 05:00:15] INFO: Starting orchestration for Day 1
[2025-12-01 05:00:16] INFO: Invoking puzzle-fetcher skill
[2025-12-01 05:00:18] INFO: Puzzle downloaded successfully
[2025-12-01 05:00:18] INFO: Invoking tdd-solver skill for Part 1
[2025-12-01 05:02:45] INFO: Part 1 solution implemented, all tests pass
[2025-12-01 05:02:46] INFO: Invoking submission-handler for Part 1
[2025-12-01 05:02:47] SUCCESS: Part 1 answer accepted!
[2025-12-01 05:02:48] INFO: Invoking tdd-solver skill for Part 2
...
```
## Command Interface
When invoked manually:
```bash
# Run for today's puzzle
cargo run --bin aoc-orchestrator
# Run for specific day
cargo run --bin aoc-orchestrator -- --day 5
# Dry run (no submission)
cargo run --bin aoc-orchestrator -- --day 1 --dry-run
# Force re-run even if already solved
cargo run --bin aoc-orchestrator -- --day 1 --force
# Verbose debugging
cargo run --bin aoc-orchestrator -- --day 1 --debug
```
## Integration with Other Skills
### Calling Puzzle Fetcher
```rust
// Pseudo-code showing skill invocation
let puzzle_data = invoke_skill("puzzle-fetcher", {
"day": day_number,
"year": 2025
})?;
```
### Calling TDD Solver
```rust
let solution = invoke_skill("tdd-solver", {
"day": day_number,
"part": 1,
"examples": puzzle_data.examples,
"input": puzzle_data.input
})?;
```
### Calling Submission Handler
```rust
let result = invoke_skill("submission-handler", {
"day": day_number,
"part": 1,
"answer": solution.answer
})?;
```
## Performance Metrics
Track and report:
- Total time from start to completion
- Time per phase (fetch, solve part1, submit part1, solve part2, submit part2)
- Number of test iterations required
- Number of submission attempts
- Compilation time
## Post-Completion Actions
After both parts completed successfully:
- Generate solution summary
- Run `cargo fmt` to format code
- Run `cargo clippy` to check for issues
- Optionally commit to git with message: `"Solve Day {day} - {puzzle_title}"`
- Update calendar status file
## Failure Recovery
If workflow fails mid-execution:
- Save current state to state file
- Next invocation should resume from last successful step
- Don't re-fetch puzzle if already downloaded
- Don't re-solve part 1 if already acceptedRelated Skills
cascade-orchestrator
Creates sophisticated workflow cascades coordinating multiple micro-skills with sequential pipelines, parallel execution, conditional branching, and Codex sandbox iteration. Enhanced with multi-model routing (Gemini/Codex), ruv-swarm coordination, memory persistence, and audit-pipeline patterns for production workflows.
Proactive Orchestrator
Event-driven orchestrator that chains existing skills, edge functions, and agent capabilities into automated workflows triggered by real-time events. Receives events from webhooks (MeetingBaaS, email, calendar), cron jobs (morning brief, pipeline scan), and Slack interactions (button clicks, approvals), then executes multi-step sequences with context-aware routing, HITL approval gates, and self-invocation for long-running chains. This is the conductor — it connects 30+ existing Slack functions, 6 specialist agents, and the sequence executor into coherent, event-driven sales workflows. NOT triggered by user chat messages. Triggered by system events only.
ln-1000-pipeline-orchestrator
Meta-orchestrator (L0): reads kanban board, drives Stories through pipeline 300->310->400->500 in parallel via TeamCreate. Max 3 concurrent Stories. Auto squash-merge to develop on quality gate PASS.
archaeology-orchestrator
고고학 발굴조사 고찰 작성 자동화 파이프라인 마스터 오케스트레이터
adb-workflow-orchestrator
TOON workflow orchestration engine for coordinating ADB automation scripts across phases with error recovery
parallel-orchestrator
Orchestrate parallel agent workflows using HtmlGraph's ParallelWorkflow. Activate when planning multi-agent work, using Task tool for sub-agents, or coordinating concurrent feature implementation.
n8n-mcp-orchestrator
Expert MCP (Model Context Protocol) orchestration with n8n workflow automation. Master bidirectional MCP integration, expose n8n workflows as AI agent tools, consume MCP servers in workflows, build agentic systems, orchestrate multi-agent workflows, and create production-ready AI-powered automation pipelines with Claude Code integration.
ai-agent-orchestrator
Эксперт по оркестрации AI агентов. Используй для multi-agent systems, agent coordination, task delegation и agent workflows.
agent-swarm-orchestrator
Designs multi-agent systems with coordinated agent swarms, task distribution, inter-agent communication, and emergent collective behavior.
agent-run-orchestrator
Run section orchestrators to coordinate multi-component workflows. Use when starting work on a section.
Agent Orchestrator
Coordinate multiple AI agents and skills for complex workflows
agent-orchestrator-manager
Orchestrates multi-agent workflows by delegating ALL tasks to spawned subagents via /spawn command. Parallelizes independent work, supervises execution, tracks progress in UUID-based output directories, and generates summary reports. Never executes tasks directly. Triggers on keywords: orchestrate, manage agents, spawn agents, parallel tasks, coordinate agents, multi-agent, orc, delegate tasks