SuperAPI AI Directory
Partner中文AI newsFavorites
Skillsproblem-doc-model-selector

problem-doc-model-selector

General & other

View repository

Updated 10-16 07:23

About this skill

Automatic Parsing of Competition Problem Documents and Model Selection

Global Workflow Collaboration Constraints (Long-Conversation Drift Prevention)

  • This skill must not be used as an isolated entry point. When the user requests a complete paper, Word generation, workflow continuation, or the stage is uncertain, first return to paper-workflow-orchestrator to determine the current S0-S8 stage.
  • Before starting or continuing the formal tasks of this skill, you must run: 
    python .claude/skills/paper-workflow-orchestrator/scripts/workflow_guard.py --skill problem-doc-model-selector
  • If the output is [WORKFLOW FAIL] or the report shows status != "PASS", stop this skill and backfill the prerequisite stages according to the failed items in paper_output/qa/workflow_guard_report.json ; do not continue from memory.
  • This skill only writes the paper_output/ artifacts within its own contract scope; after completion, you must return to paper-workflow-orchestrator to determine the next step, and use context-memory-keeper to record completed artifacts, blockers, and the next step.
  • In a long conversation, if the context grows long, the stage is uncertain, or the user invokes skills separately, first run: 
    python .claude/skills/paper-workflow-orchestrator/scripts/workflow_guard.py --status
    then read paper_output/qa/workflow_guard_report.json、paper_output/preflight_report.json、paper_output/input_manifest.json、paper_output/results/run_manifest.json and this skill's upstream JSON contract, and continue according to the recommended_skill and next_action in the report.
  • Before continuing the workflow, you must treat paper_output/context/workflow_memory.json as a long-term breakpoint record; if its current_step、next_step、recommended_skill and workflow_guard.py --status are inconsistent, the guard report takes precedence.
  • After completing this skill's artifacts each time, first return to paper-workflow-orchestrator or run workflow_guard.py --status, then update workflow memory: 
    python .claude/skills/context-memory-keeper/scripts/update_workflow_memory.py
    after updating, read paper_output/context/workflow_memory.json / .mdto confirm that the next step and recommended skill have been recorded.

Execution Contract

  • Upstream input:problem_files/ the competition problem PDF/Word/TXT and attachment data in .
  • Required output:paper_output/step1/problem_analysis.json, as well as A_题意对齐.md、B_论文大纲.md、C_评分点对齐表.md、D_模型路线.json。
  • Downstream handoff:modeling-paper-rubric-and-model-selector reads problem_analysis.json to generate the model route; the complete workflow is chained together by paper-workflow-orchestrator .
  • Recommended next step: after completing the problem analysis, proceed to modeling-paper-rubric-and-model-selector; if the user's goal is a complete paper, return to paper-workflow-orchestrator to determine the subsequent stages.
  • Failure fallback: if problem_files/ is empty, stop and prompt for the competition problem to be provided; if some documents cannot be parsed, retain the parseable content and record the missing field profile in the output.

Goal

  • Input the competition problem PDF/Word document or problem statement text, automatically extract the task type, data conditions, and constraints of "each question", and output a problem-specific model selection and validation route.
  • Generate a scoring-friendly deliverable: a one-page problem alignment, paper outline, scoring point alignment table, and model route (baseline/improvement/validation/risk).

Stage Transitions

  • After parsing is complete, do not stop at a vague "are you satisfied" question; instead, explain the generated problem contract and provide the next recommended stage.
  • If the user's intent is a complete paper, after outputting A/B/C/D, return to paper-workflow-orchestrator, and the main entry point will decide whether to continue generating the model route, data plan, QA, and main text.
  • Refuse to Cut Corners: you must output all four complete parts A/B/C/D, and must not omit any.

When to Apply

  • When the user provides a competition problem PDF/Word or problem statement text and needs to quickly determine the model/method that should be used for each question and formulate an experimental validation plan.
  • When you are unsure about the interpretation of the problem statement, uncertain about the modeling approach, or need suggestions for aligning the paper structure with the scoring points.

Input

  • Problem statement document path or full problem statement text (supports PDF, DOCX, TXT).
  • Optional: attachment data file paths, highlights you want to emphasize, or limitations.

Output

  • A One-page problem alignment: for each question, provide input/output, evaluation metrics, key constraints, and verifiable methods.
  • B Paper outline: abstract, problem restatement, assumptions, notation, data description, model, solution, results, validation, conclusion, limitations, references.
  • C Scoring point alignment table: scoring point → evidence form (figures/tables/experiments/validation) → paper location.
  • D Model selection and approach: for each question, task type, minimum viable baseline, improvement path, validation plan, risks, and alternatives.
  • E Data requirement configuration (optional): if the problem is found to require external data (such as population, meteorological, or economic data), automatically generate or update the file in the root directory data_requirements.json, so that authoritative-data-harvester can automatically obtain it.
  • Machine-readable contract:paper_output/step1/problem_analysis.json, including documents、data_files、questions、recommended_models、validation_plan、figure_suggestions and other fields, for the modeling approach, evidence audit, formal writing, and overall orchestrator to continue reading.

Directory conventions (aligned with the project globally)

  • Place the problem statement and attachments together in problem_files/。
  • It is recommended to archive the four types of outputs of this skill to paper_output/step1/(for example, paper_output/step1/A_题意对齐.md , etc.), for reference by subsequent skills.
  • Also generate paper_output/step1/D_模型路线.json, used to retain the modeling approach, validation method, and suggested figures for each question.

Script entry point (recommended)

This skill has a built-in structured analysis script:

python .claude/skills/problem-doc-model-selector/scripts/analyze_problem.py

This script will scan problem_files/, read TXT/Markdown/DOCX/PDF problem statement text, and perform lightweight field profiling on CSV/XLSX/XLS attachments. After success, it will write paper_output/step1/problem_analysis.json, and subsequent modeling approaches, evidence gates, and formal outlines will all use it as the upstream contract.

Upstream and downstream connections

  • Subsequent work usually starts with:data-cleaning-and-visualization(data cleaning and visualization).
  • To continue to the paper draft: return to paper-workflow-orchestrator。

Constraints (must be followed)

  • Memory Interaction (required):
    • Before starting, check whether memoryskill.md contains external literature/data indexes (such as references provided by g-sci), and incorporate them into the basis for model selection.
    • After completing the analysis, you must call context-memory-keeper, and update the "core task type," "data conditions," and "model selection conclusion" to memoryskill.md 's Short-term Workbench . This is the key for subsequent paper-generation skills to obtain context.
  • External data check (required):
    • If the analysis finds that the problem depends on external public data (such as "collect relevant data" or "insufficient attachment data"), you must generate data_requirements.json and write it to the root directory.
    • The configuration content should include a clear url(if known) or manual_search prompt, and set active to true。
  • The problem alignment and modeling approach output by this skill must be able to be referenced by subsequent writing positioning; it is recommended to archive them fixedly to paper_output/step1/。
  • If the user's goal is "the final paper is submittable," then after this skill is completed, you must not directly enter the paper-generation stage; you must first ensure the data scope is usable: enter data-cleaning-and-visualization or supplement authoritative-data-harvester。
  • If the user does not want to proceed step by step, it is necessary to return to paper-workflow-orchestrator to execute the complete workflow, avoiding the gap of "parsing completed but no body text generated".

Workflow

  1. Document Reading
    • PDF: prefer PyMuPDF, otherwise pdfplumber; preserve figure and table captions and section numbering.
    • Word: python-docx; preserve paragraph and table structure.
    • Cleaning: remove headers and footers, merge broken lines, standardize units (cm⁻¹, %, etc.).
  2. Problem Statement Parsing
    • Rule-based extraction of "Problem 1/Problem 2/Problem 3..." and "attachment description/units/key parameters".
    • Identify task type: prediction/classification/evaluation/optimization/clustering/simulation/mechanistic modeling.
    • Extract constraints and boundaries: incidence angle, hierarchical relationships, unit conventions, feasible region.
  3. Data Condition Parsing
    • Attachment file names and fields: column names, units, sample size, range, missing value ratio.
    • Result specifications: requires reflectance, thickness, error, ranking, or resource allocation, etc.
  4. Model Selection Engine (rules first, combined with prompt-based decision-making)
    • Prediction: moving average/exponential smoothing/regression/ARIMA → tree models/LSTM.
    • Classification: logistic regression/naive Bayes → random forest/gradient boosting; use cost-sensitive methods for imbalance.
    • Evaluation and ranking: normalization + weighted sum → entropy weight/CRITIC/AHP/TOPSIS/VIKOR.
    • Optimization and scheduling: linear/integer programming → multi-objective and heuristics (genetic/annealing).
    • Clustering: K-means/hierarchical → GMM/DBSCAN (noise and non-convex shapes).
    • Mechanistic/simulation: differential/difference/system dynamics; compare with data-driven approaches.
    • Physical/engineering modeling: establish equations based on domain knowledge (such as heat conduction, fluid mechanics, circuit analysis, optical propagation), and use least squares or optimization algorithms for parameter inversion and model correction.
  5. Validation and Robustness
    • Metrics: RMSE/MAE/AUC/F1/MAPE/silhouette coefficient/constraint satisfaction rate.
    • Cross-validation/rolling backtest/hold-out method; ablation experiments and sensitivity analysis.
    • Extreme/boundary scenarios and consistency checks of unit conventions.

Quick Reference for Discrimination Logic

  • If "prediction/estimate the future/trend/parameter estimation" appears → prediction category.
  • If "classification/whether/risk level/identification" appears → classification category.
  • If "comprehensive evaluation/ranking/weight/scoring" appears → evaluation and ranking.
  • If "resource allocation/path/site selection/minimum cost/maximum profit" appears → optimization and scheduling.
  • If "grouping/profiling/similarity/pattern discovery" appears → clustering.
  • If "mechanism/simulation/dynamics/differential equations" appears → mechanistic/simulation.
  • If "physical processes/chemical reactions/signal transmission/mechanical structures" appears → physical/engineering modeling.

Output Template

  • A Problem Alignment: input, output, metrics, constraints, validation for each question.
  • B Outline: list chapters and sections in a scoring-friendly order.
  • C Scoring Alignment: mapping table of scoring points and evidence.
  • D Model Roadmap: task type/baseline/improvement/validation/risks and alternatives.

Usage Example

  • Input: competition problem file path c:\path\to\赛题.pdf or the full problem statement text.
  • Behavior: Read the document → extract each question → identify the task type and data conditions → output four categories of results A/B/C/D and the recommended model.
  • Automatic suggestions:
    • Baseline: Choose the simplest classical model (such as linear regression, K-means, shortest path algorithm).
    • Improvement: Higher-order models introduced to address baseline shortcomings (such as nonlinearity, noise, multi-objective) (such as XGBoost, improved genetic algorithms, hybrid models).
    • Validation: Metric calculation, residual analysis, cross-validation, sensitivity analysis.

Deviation prevention check

  • Each question must provide quantifiable outputs and verifiable metrics.
  • Symbols and units are unified, and metric definitions are consistent.
  • At least one baseline comparison and improvement evidence (improvement or more reasonable).
  • Conclusions and figures correspond question by question, not "doing a lot but not answering the question".

When not to use this skill

  • When it is already clear that only a specific algorithm needs to be implemented or a single code snippet needs to be modified (direct implementation is faster).