cxcscmu/SkillLearnBench - Page 23

video-frame-extraction

Use ffmpeg to extract keyframes from a video file into a target directory.

Langue du texte source : anglais

data-retrieval-using-index-and-match

Use INDEX combined with MATCH to retrieve data from a source table based on two criteria (row and column headers).

Langue du texte source : anglais

statistical-calculation-and-formatting

Perform descriptive statistical analysis while ensuring results are displayed as percentages rounded to one decimal place.

Langue du texte source : anglais

weighted-mean-using-sumproduct

Calculate the weighted mean by multiplying Net Exports % by the corresponding GDP values and dividing by the total GDP.

Langue du texte source : anglais

modern-mandarin-rhyme-tones

Guidelines for mapping modern Mandarin pronunciation (Pinyin) to traditional Ping (Level) and Ze (Oblique) poetic tones, and identifying modern rhyme families.

Langue du texte source : anglais

qiyan-lvshi-composition

Structural, syntactical, and tonal rules for composing a seven-character regulated verse (七言律诗).

Langue du texte source : anglais

pypdf-form-filling

Inspecting and filling interactive PDF forms (AcroForms) using the pypdf library. Crucial for automating the population of government or legal PDF documents.

Langue du texte source : anglais

dbscan-anisotropic-distance

Efficiently computing DBSCAN with a custom weighted (anisotropic) distance metric using coordinate scaling, avoiding the overhead of slow custom distance functions.

Langue du texte source : anglais

geopandas-spatial-analysis

How to perform spatial filtering (point-in-polygon), combine line boundaries, and accurately calculate metric distances between points and boundaries using GeoPandas.

Langue du texte source : anglais

json-nested-list-formatting

Formats and saves answers to a JSON file where each entry requires a specific nested dictionary structure containing list-type values and positive numeric token counts.

Langue du texte source : anglais

llm-token-tracking

Extracts and tracks the consumed token usage from an LLM API response to monitor API cost and utilization.

Langue du texte source : anglais

parse-key-value-text

Parses a text file containing key-value pairs (like question IDs and question text) into a Python dictionary.

Langue du texte source : anglais

analyze-13f-filings-and-holdings

Guidelines for analyzing 13F filings, finding fund accession numbers, calculating AUM, and counting exact stock holdings by utilizing existing scripts and correctly excluding options.

Langue du texte source : anglais

python-docx-advanced-manipulation

Techniques for replacing text placeholders, safely deleting paragraphs, and handling custom multi-paragraph conditionals (like IF/END_IF markers) in Microsoft Word documents using python-docx.

Langue du texte source : anglais

python-to-scala-idioms

Idiomatic translation of Python constructs to Scala 2.13, including classes, interfaces, enums, and naming conventions.

Langue du texte source : anglais

scala-functional-error-handling

Handling absence of values and errors in Scala using Option, Try, and Either instead of nulls and exceptions.

Langue du texte source : anglais

scala-immutable-builder-pattern

Implementing the Builder pattern idiomatically in Scala using case classes and the copy method for immutability.

Langue du texte source : anglais

scala-regex-processing

Using regular expressions for text tokenization and parsing in Scala using the scala.util.matching.Regex API.

Langue du texte source : anglais

d3-interactivity-and-tooltips

HTML/CSS/JS patterns for creating tooltips, conditional interactions based on data attributes, and cross-highlighting elements across different views (like a chart and a table).

Langue du texte source : anglais

itinerary-generation-and-formatting

Use this skill to construct the final itinerary and strictly format the output as a JSON file, enforcing specific key requirements and keywords.

Langue du texte source : anglais

travel-data-retrieval

Use this skill to query the local databases for distances, cities, accommodations, restaurants, and attractions to gather real-world data for an itinerary.

Langue du texte source : anglais

excel-2d-lookup-formulas

How to perform two-dimensional data lookups in Excel using functions like INDEX & MATCH or VLOOKUP & MATCH based on both row and column criteria.

Langue du texte source : anglais

excel-statistical-and-weighted-mean-formulas

How to calculate statistical summaries (min, max, median, mean, percentiles) and weighted averages using SUMPRODUCT, with specific rules for rounding and avoiding double-scaling of percentages.

Langue du texte source : anglais

generate-anthropic-technical-artifact

Create technical diagrams and posters adhering to Anthropic's official brand guidelines. Use this skill to produce exploded-view hardware visualizations with specific brand color tokens, typography, and minimalist styling.

Langue du texte source : anglais

mandarintonemapping

Rules for determining the Ping (平) or Ze (仄) status of a character based on modern Mandarin Pinyin tones.

Langue du texte source : anglais

sevencharacterregulatedversecomposition

Composing a Chinese Seven-Character Regulated Verse (七言律诗) following strict traditional structural, tonal, and rhyming rules using modern Mandarin.

Langue du texte source : Plusieurs langues

fill-pdf-form

Fills a PDF form with provided data. It maps field keys to their respective pages and applies values. It handles multi-line text areas by assigning specific strings to the identified sequential keys. For checkboxes, it uses the precise export values found…

Langue du texte source : anglais

format-claim-description

Splits a long string of text (like a claim description or reason) into multiple parts that fit into sequential PDF field keys. Use this when the SC-100 form provides multiple lines (e.g., 'Reason_Line1', 'Reason_Line2') for a single explanation.

Langue du texte source : anglais

inspect-pdf-form

Extracts detailed information about form fields in a PDF, including field keys, types, page indices, current values, and allowed export values for checkboxes and radio buttons. Use this to identify how multi-line text is split across different keys (e.g.,…

Langue du texte source : anglais

dbscan-custom-metric-weighting

Implementing a weighted Euclidean distance metric for DBSCAN to account for anisotropic spatial features.

Langue du texte source : anglais

greedy-point-matching-evaluation

Matching predicted cluster centroids to ground truth points using a greedy distance-based approach to calculate F1 score and precision/recall.

Langue du texte source : anglais

grid-search-parallelization

Running a multi-parameter grid search efficiently using parallel processing to find optimal hyperparameters.

Langue du texte source : anglais

mars-cloud-data-grouping

Organizing annotation data by image identifiers to prepare for image-by-image clustering analysis.

Langue du texte source : anglais

pareto-frontier-identification

Identifying the set of non-dominated solutions in a multi-objective optimization problem.

Langue du texte source : anglais

csv-security-report-generation

Formatting security audit findings into a standardized CSV format for reporting and compliance.

Langue du texte source : anglais

npm-audit-security-analysis

Identifying vulnerabilities in Node.js dependencies using the npm audit tool to filter for high and critical severities.

Langue du texte source : anglais

vulnerability-json-parsing

Extracting specific security metadata (CVE, CVSS, Fix versions) from structured vulnerability reports like npm audit JSON or OSV.

Langue du texte source : anglais

geopandas-spatial-filtering

Use GeoPandas to filter points within a specific polygon, such as finding earthquakes within a specific tectonic plate.

Langue du texte source : anglais

geospatial-metric-projections

Transform GeoPandas objects to metric projections (like World Equidistant Cylindrical) to calculate distances in meters or kilometers rather than degrees.

Langue du texte source : anglais

plate-tectonics-pb2002-parsing

Specific knowledge of the PB2002 (Bird, 2002) dataset structure for identifying the Pacific plate.

Langue du texte source : anglais