few-shot-examples
Curated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved LLM performance.
npx skills add majiayu000/claude-skill-registry --skill few-shot-examples --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Maps to a collection of construction-domain few-shot examples intended to improve LLM performance on classification, extraction, and analysis tasks. It defines data structures and helper methods to manage examples, format them for prompts, and retrieve subsets by difficulty or randomness. It includes ready-made example sets for CSI classification, RFI classification, cost analysis, and schedule analysis, each with inputs, outputs, explanations, and metadata such as difficulty and tags.
How it works
- Declares an ExampleSet data structure containing name, description, task_type, a list of FewShotExample items, and a version.
- Each FewShotExample holds input, output, optional explanation, tags, difficulty, and source.
- ExampleSet methods:
- get_examples(n, difficulty) filters by difficulty and returns up to n examples.
- get_random_examples(n) returns n random examples from the set.
- format_for_prompt(n) formats a sequence of up to n examples for inclusion in a prompt, including Example i, Input, Output, and optional Explanation.
- ConstructionExampleLibrary registers and retrieves named ExampleSet instances, with a _register_defaults step loading defaults from DEFAULT_EXAMPLE_SETS.
- Provides concrete data blocks for CSI Classification, RFI Classification, Cost Analysis, and Schedule Analysis, each as an ExampleSet with multiple FewShotExample entries.
When to use it
Use when you want to supply structured, domain-specific few-shot examples in prompts to an AI model performing construction-related classification, extraction, or analysis tasks.
What it can touch
- References to data structures and example sets (ExampleSet, FewShotExample, CSI_CLASSIFICATION_EXAMPLES, RFI_CLASSIFICATION_EXAMPLES, COST_ANALYSIS_EXAMPLES, SCHEDULE_ANALYSIS_EXAMPLES).
- Formatting methods to prepare prompts (format_for_prompt) and retrieval methods (get_examples, get_random_examples).
Caveats
- The material is example data intended for prompt composition; there is no guarantee of model performance or outcomes.
- No licensing or usage terms beyond the overall repository license (MIT) are stated within the skill content itself.
# Few-Shot Examples for Construction AI ## Overview Curated few-shot examples for construction industry AI tasks. These examples improve LLM performance by providing domain-specific context for classification, extraction, and analysis tasks. ## Few-Shot Framework ### Example Manager ```python from dataclasses import dataclass, field from typing import List, Dict, Any, Optional import json import random @dataclass class FewShotExample: input: str output: str explanation: Optional[str] = None tags: List[str] = field(default_factory=list) difficulty: str = "medium" # easy, medium, hard source: str = "" @dataclass class ExampleSet: name: str description: str task_type: str examples: List[FewShotExample] version: str = "1.0" def get_examples(self, n: int = 3, difficulty: str = None) -> List[FewShotExample]: """Get n examples, optionally filtered by difficulty.""" filtered = self.examples if difficulty: filtered = [e for e in self.examples if e.difficulty == difficulty] return filtered[:n] def get_random_examples(self, n: int = 3) -> List[FewShotExample]: """Get n random examples for variety.""" return random.sample(self.examples, min(n, len(self.examples))) def format_for_prompt(self, n
- Overview
- Few-Shot Framework
- Example Manager
- CSI Classification Examples
- RFI Classification Examples
- Cost Analysis Examples
- Schedule Analysis Examples
- BIM Data Examples
- Using Examples in Prompts
- Adding Custom Examples
- Best Practices
- Resources
What does the few-shot-examples skill do?
Curated few-shot examples for construction AI tasks: classification, extraction, analysis. Domain-specific examples for improved LLM performance.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill few-shot-examples --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.