agentleFS
LocloveLoclove/cumcm-skills/skills/cumcm-problem-reader/SKILL.md

cumcm-problem-reader

Skill4 starsChanged 3 months agoMITView on GitHub

Read CUMCM problem statements, attachments, tables, and raw notes to produce a structured problem card, data inventory, subproblem dependency graph, deliverables, assumptions, and first-pass risk map. Use when the user provides a contest problem PDF/Word/text, problem screenshots, data attachments, or asks to parse a mathematical-modeling problem.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill before modeling.

    line 8
  2. Distinctive:

    Do not start algorithm selection before the deliverables are explicit.

    line 51
  3. Distinctive:

    Do not ignore units, time windows, coordinate systems, or sample definitions.

    line 52
  4. Distinctive:

    Do not compress multiple subquestions into one vague objective.

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CUMCM Problem Reader

Use this skill before modeling. It turns a messy contest statement into a precise work packet.

Workflow

  1. Load ../cumcm-shared/references/competition-ethics.md and identify contest mode.
  2. Extract text from the statement. Use scripts/extract_problem_packet.py for PDF/text files when useful.
  3. Build a subproblem DAG: which questions depend on which data, models, and outputs.
  4. Inventory all attachments: file type, dimensions if visible, fields, units, missing values, and likely joins.
  5. Identify required outputs: tables, figures, parameters, predicted values, decisions, policy recommendations, or code.
  6. Mark ambiguities as AUTHOR_DECISION_NEEDED rather than guessing.
  7. Hand off to cumcm-model-planner with a concise problem packet.

Output Contract

Problem card
- Domain:
- Objective:
- Subquestions:
- Inputs:
- Outputs:
- Constraints:
- Evaluation clues:

Data inventory
| File | Role | Fields | Unit/time/space coverage | Risks |

Subproblem DAG
- Q1 -> Q2 -> Q3 dependencies

Modeling hooks
- Candidate model families:
- Required assumptions:
- Validation opportunities:

First-night plan
- 0-2h:
- 2-6h:
- Overnight batch jobs:

Red Lines

  • Do not start algorithm selection before the deliverables are explicit.
  • Do not ignore units, time windows, coordinate systems, or sample definitions.
  • Do not compress multiple subquestions into one vague objective.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.