cxcscmu/SkillLearnBench - 29ページ

cvss-report-generation

How to generate security audit reports in CSV format. Use this skill whenever you need to produce a `/root/security_audit.csv` report.

原文の言語: 英語

dependency-vulnerability-audit

How to perform security audits on package-lock.json. Use this skill whenever you need to identify HIGH or CRITICAL vulnerabilities in project dependencies.

原文の言語: 英語

geopandas-projection-tools

Handles CRS transformations and distance calculations in kilometers. Use this for converting between geographic coordinates (WGS84) and equal-area projections (like Lambert Azimuthal Equal Area centered on the Pacific region) for accurate distance…

原文の言語: 英語

geospatial-earthquake-analysis

Handles loading and processing of earthquake and plate boundary data. Use this for reading, filtering, and joining geospatial datasets related to tectonics (plates, boundaries, earthquake points).

原文の言語: 英語

enterprise-data-retrieval

Retrieve information from enterprise JSON datasets in /root/DATA.

原文の言語: 英語

json-answer-formatter

Format retrieval answers as a dictionary in /root/answer.json.

原文の言語: 英語

13f-analysis-guide

How to analyze 13F filings. Use this skill to process COVERPAGE.tsv, INFOTABLE.tsv, and metadata for hedge fund holdings and AUM.

原文の言語: 英語

druid-maven-build

How to rebuild Apache Druid after applying patches. Use this whenever the codebase has been modified and needs a partial or full rebuild.

原文の言語: 英語

druid-vulnerability-fix

How to fix the Apache Druid JavaScript sampler vulnerability. Use this skill when patching Druid code to block arbitrary JavaScript execution.

原文の言語: 英語

gh-data-gathering

How to gather PR and issue data from a GitHub repository using the gh CLI for monthly reports. Use this skill whenever you need to fetch monthly metrics from a repository.

原文の言語: 英語

report-generator

How to process GitHub API JSON output into a structured report.json for monthly analytics. Use this whenever you have raw JSON data from the gh CLI.

原文の言語: 英語

environment-setup

Procedures for setting up the environment for research projects involving Python, PyTorch, and NLP models. Use whenever environment requirements (environment.yml) are present.

原文の言語: 英語

simpo-loss-implementation

Guidelines for implementing the SimPO (Simple Preference Optimization) loss function for NLP model training. Use this skill when modifying trainers or implementing preference-based loss functions in transformer projects.

原文の言語: 英語

file-classifier

Use this skill to classify PDF, PPTX, or DOCX files into subject categories: LLM, trapped_ion_and_qc, black_hole, DNA, or music_history. Analyze filenames and available content to determine the correct category.

原文の言語: 英語

calendar-parser

Extract appointments from calendar.pdf. Use whenever you need to determine availability from the calendar.

原文の言語: 英語

email-parser

Extract meeting request details from JSON input. Use whenever you process meeting requests.

原文の言語: 英語

meeting-scheduler

Schedule meetings and generate response text files. Use whenever you have a meeting request to process and confirm.

原文の言語: 英語

d3-stock-viz

Use this skill for D3.js (v6) force-directed bubble charts and linked data tables. Always use this when tasked with financial data visualization using D3.js.

原文の言語: 英語

glm-metrics

How to calculate and save GLM performance metrics (RMSE) to metrics.json. Use this whenever the user asks for RMSE checks or final model evaluation.

原文の言語: 英語

glm-simulation

How to run GLM, modify calibration parameters, and manage simulation outputs. Use this whenever the user wants to run, calibrate, or troubleshoot GLM simulations.

原文の言語: 英語

data-querying

How to query CSV datasets in /app/data to extract information like accommodations, attractions, and restaurants. Use this skill whenever you need to look up data from files in the /app/data directory.

原文の言語: 英語

itinerary-planning

How to construct a 7-day, pet-friendly travel itinerary for three Ohio cities starting from Minneapolis without using flights. Use this skill for planning, organizing the itinerary data, and formatting the final JSON output.

原文の言語: 英語

image-processing

Use this skill for image conversion, such as grayscale conversion, to prepare images for analysis.

原文の言語: 英語

object-counting

Use this skill for counting specific objects (coins, enemies, turtles) in images using template matching.

原文の言語: 英語

video-frame-extraction

Use this skill to extract key frames from MP4 video files into a target directory.

原文の言語: 英語

excel-data-processing

How to perform data lookups in Excel using INDEX and MATCH. Use this skill when needing to extract data from a source table based on two conditions (e.g., Row header and Column header).

原文の言語: 英語

weighted-mean-calculation

How to calculate weighted means in Excel using SUMPRODUCT. Use this skill when calculating the weighted average for a group (e.g., GCC Countries) by multiplying values by their corresponding weights (e.g., GDP).

原文の言語: 英語

anthropic-brand-standards

How to apply Anthropic's official brand colors, typography, and design guidelines. Use this skill whenever the user mentions Anthropic styling, corporate colors, brand accents, or visual formatting for Anthropic.

原文の言語: 英語

exploded-view-generator

How to generate 2D isometric or exploded-view technical posters programmatically. Use this skill whenever the user asks for a technical exploded-view, internal hardware layers, or an isometric hardware diagram.

原文の言語: 英語

qiyan-lushi-composition

How to compose a seven-character regulated verse (Qiyan Lushi). Use this skill whenever the user asks to write a seven-character regulated verse or traditional Chinese poetry, even if they don't explicitly mention the rules.

原文の言語: 英語

sc100-form-filler

How to map and fill the California Small Claims Court form SC-100 (Plaintiff's Claim and ORDER to Go to Small Claims Court). Use this skill whenever the user mentions filling an SC-100 form or filing a small claims case in California.

原文の言語: 英語

dbscan-custom-distance

Define custom distance metrics for DBSCAN clustering. Use this skill whenever a task requires clustering points with unequal weighting or application-specific distances.

原文の言語: 英語

joblib-parallel-gridsearch

Perform parallel grid search using joblib. Use this skill whenever a task requires optimizing multiple hyperparameters simultaneously across CPU cores.

原文の言語: 英語

pareto-frontier-optimization

Compute the Pareto frontier for multi-objective optimization. Use this skill whenever a task requires finding optimal trade-offs between conflicting metrics (e.g., maximize F1, minimize distance).

原文の言語: 英語

geospatial-analysis

How to perform geospatial analysis using GeoPandas. Use this skill whenever the user mentions maps, coordinates, geospatial distance, plate boundaries, earthquakes, or spatial data, even if they don't explicitly ask for it.

原文の言語: 英語

enterprise-data-retrieval

How to extract and format enterprise product data for specific queries. Use this skill whenever the user asks to retrieve employee IDs, report authors, competitor URLs, or insights from JSON enterprise product or metadata files.

原文の言語: 英語

druid-jackson-security

Securing Apache Druid's JavaScriptConfig deserialization. Use this skill whenever patching or securing Jackson deserialization in Druid, especially regarding the empty key ("") bypass.

原文の言語: 英語

maven-build-skip

Guide on how to rebuild Druid using Maven while skipping unnecessary checks. Use this skill when asked to compile or build Druid.

原文の言語: 英語

github-metrics

How to calculate GitHub community pulse metrics using the `gh` CLI. Use this skill whenever the user asks for pull request metrics, issue metrics, community pulse, average merge times, top contributors, or bug reports over a specific timeframe.

原文の言語: 英語

pytorch-loss-implementation

How to implement custom loss functions in PyTorch. Use this skill whenever the user asks to implement a loss function, write a custom criterion, or mentions PyTorch tensor operations for backpropagation.

原文の言語: 英語