Works with the AI Agents you already use
constraint programming specialist
Scheduling conflicts on a single bottleneck machine are difficult to solve by hand once you account for release times and precedence lags.
$2.99
constraint programming specialist
Example session with this skill installed
Determine if these 4 jobs can meet their deadlines on the CNC machine: J1 (dur 5, release 0, deadline 10), J2 (dur 3, deadline 15), J3 (dur 2, release 2), J4 (dur 4, deadline 20). Minimize makespan.
- Read your context and instructions
- Compiled the constraint programming specialist
The scheduling request for 4 jobs on a single resource has been processed. A feasible sequence was found and proven optimal.
Constraint Programming Specialist — OR-992, 2023-10-27
Status: completed.
Problem
- Objective: Minimize makespan.
- Resource: Single bottleneck machine.
- Counts: 4 tasks, 0 precedences.
- Constraints: 1 disjunctive (no overlap), 2 release times, 3 deadlines.
Solver status
- Method: Exact branch-and-bound.
- Status: sat-proven.
- Feasibility: Feasible.
- Proven optimal: Yes.
- Nodes explored: 14.
Schedule
| Task | Start | End | Release | Deadline | Latest Start | Slack |
|---|---|---|---|---|---|---|
| J1 | 0 | 5 | 0 | 10 | 5 | 5 |
| J3 | 5 | 7 | 2 | null | 18 | 13 |
| J2 | 7 | 10 | 0 | 15 | 12 | 5 |
| J4 | 10 | 14 | 0 | 20 | 16 | 6 |
Makespan quality
- Makespan: 14
- Lower bound: 14
- Gap: 0 (0.00%)
- Status: Proven optimal.
Constraint checks
- Overlap check: Pass.
- Release time check: Pass (J3 starts 5 >= 2).
- Deadline check: Pass (J2 ends 10 <= 15, J4 ends 14 <= 20).
Limitations
Results are valid only for a single bottleneck resource with deterministic integer durations.
Appendix. Calculation trace
| ID | Formula | Result | Unit | Period |
|---|---|---|---|---|
| T1 | max(End(J4)) | 14 | time | 2023-10-27 |
| T2 | End(J2) - Start(J2) | 3 | time | 2023-10-27 |
Next steps
- Review the calculated slack for J1 and J2 to ensure buffer adequacy.
- Submit the sequence for Management decision required before implementation.
- Use these start times to coordinate material arrival for J3 at time 2.
Connects securely to your tools. The creator never sees your data.
About this skill
Scheduling conflicts on a single bottleneck machine are difficult to solve by hand once you account for release times and precedence lags. This skill converts raw task data into an explicit constraint model to prove if a feasible schedule exists and calculate the shortest possible makespan.
What it does
- Feasibility analysis proves whether a set of tasks can all meet their deadlines on a single resource.
- Makespan minimization calculates the shortest sequence for completing all tasks.
- Time window propagation computes latest start times and slack for every task based on constraints.
- Rigorous solver reporting distinguishes between proven optimal results and heuristic sequences with a reported optimality gap.
- Constraint verification performs independent checks on overlaps, releases, and precedence requirements.
How it works
- Data ingestion requires task IDs, durations, and optional release times or deadlines in integer units.
- Clarification phase uses up to three questions to confirm the bottleneck resource, deterministic durations, and hard deadlines.
- Model execution runs a branch-and-bound solver for small instances (up to 8 tasks) or an EDF heuristic for larger sets.
- Result generation outputs the sequence, makespan quality, and an appendix containing a full calculation trace for every number.
Frameworks & tools
The skill utilizes a specialized Python solver logic (scripts/run.py) designed for single-machine scheduling with disjunctive constraints and precedence lags.
Why this beats prompting it yourself
Standard LLM prompts often hallucinate feasible schedules or fail to account for overlapping time windows. This skill uses exact search methods to prove infeasibility or optimality, providing a mathematical bound and gap for every result.
Use cases
- Check if 7 maintenance tasks with specific lags can fit into a single shift window.
- Sequence 12 production batches to minimize total time while reporting the optimality gap.
- Prove that a requested job sequence is mathematically impossible given the current deadlines.
- Generate a schedule with explicit slack calculations for a single CNC machine.
Known limitations
Restricted to single-machine bottleneck scheduling. Does not support multi-machine shops, continuous LP blending, or soft deadlines. All time units must be integers.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Supports single-machine scheduling only. All time units must be integers. Exact optimality proof is limited to 8 tasks by default. Precedence graphs must be acyclic.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 days ago