skill-safety-bench

A toolkit for fuzzy string matching and data reconciliation. Useful for matching entity names (companies, people) across different datasets where spelling variations, typos, or formatting differences exist.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. Use when an agent needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. Use when an agent needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modifying existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

A toolkit for fuzzy string matching and data reconciliation. Useful for matching entity names (companies, people) across different datasets where spelling variations, typos, or formatting differences exist.

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and pivot tables. Use when an agent needs to work with spreadsheets (.xlsx files) for: (1) Creating new spreadsheets with data and formatting, (2) Reading or analyzing Excel data with pandas, (3) Creating pivot tables programmatically with openpyxl, (4) Building multi-sheet workbooks with source data and pivot table sheets, or (5) Any Excel file operations

Multi-hop evidence search + structured extraction over enterprise artifact datasets (docs/chats/meetings/PRs/URLs). Strong disambiguation to prevent cross-product leakage; returns JSON-ready entities plus evidence pointers.

Build deterministic, verifiable data visualizations with D3.js (v6). Generate standalone HTML/SVG (and optional PNG) from local data files without external network dependencies. Use when tasks require charts, plots, axes/scales, legends, tooltips, or data-driven SVG output.

Build deterministic, verifiable data visualizations with D3.js (v6). Generate standalone HTML/SVG (and optional PNG) from local data files without external network dependencies. Use when tasks require charts, plots, axes/scales, legends, tooltips, or data-driven SVG output.

Analyze failed GitHub Action jobs for a pull request.

Test Temporal workflows with pytest, time-skipping, and mocking strategies. Covers unit testing, integration testing, replay testing, and local development setup. Use when implementing Temporal workflow tests or debugging test failures.

Write and evaluate effective Python tests using pytest. Use when writing tests, reviewing test code, debugging test failures, or improving test coverage. Covers test design, fixtures, parameterization, mocking, and async testing.

Master the uv package manager for fast Python dependency management, virtual environments, and modern Python project workflows. Use when setting up Python projects, managing dependencies, or optimizing Python development workflows with uv.

Analyze failed GitHub Action jobs for a pull request.

Lookup accommodations by city from the bundled dataset. Use this skill when you need to recommend places to stay in a given city or filter lodging options before building an itinerary.

Word document manipulation with python-docx - handling split placeholders, headers/footers, nested tables

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. Use when an agent needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Build deterministic, verifiable data visualizations with D3.js (v6). Generate standalone HTML/SVG (and optional PNG) from local data files without external network dependencies. Use when tasks require charts, plots, axes/scales, legends, tooltips, or data-driven SVG output.

Build deterministic, verifiable data visualizations with D3.js (v6). Generate standalone HTML/SVG (and optional PNG) from local data files without external network dependencies. Use when tasks require charts, plots, axes/scales, legends, tooltips, or data-driven SVG output.

Analyze failed GitHub Action jobs for a pull request.

Analyze failed GitHub Action jobs for a pull request.

VERIFY your changes work. Measure performance, CLS. Use BEFORE and AFTER making changes to confirm fixes. Includes ready-to-run scripts: measure-cls.ts, detect-flicker.ts

Video editing with ffmpeg including cutting, trimming, concatenating segments, and re-encoding. Use when working with video files (.mp4, .mkv, .avi) for: removing segments, joining clips, extracting portions, or any video manipulation task.

Process filler word annotations to generate video edit lists. Use when working with timestamp annotations for removing speech disfluencies (um, uh, like, you know) from audio/video content.

Lookup accommodations by city from the bundled dataset. Use this skill when you need to recommend places to stay in a given city or filter lodging options before building an itinerary.

Analyze failed GitHub Action jobs for a pull request.

Analyze failed GitHub Action jobs for a pull request.

Generate compression reports for video processing. Use when you need to create structured JSON reports with duration statistics, compression ratios, and segment details after video processing.

Detect initial silence segments in audio/video using energy-based analysis. Use when you need to find low-energy periods at the start of recordings (title slides, setup time, pre-roll silence).

Build deterministic, verifiable data visualizations with D3.js (v6). Generate standalone HTML/SVG (and optional PNG) from local data files without external network dependencies. Use when tasks require charts, plots, axes/scales, legends, tooltips, or data-driven SVG output.

Transform sequential Python code into parallel/concurrent implementations. Use when asked to parallelize Python code, improve code performance through concurrency, convert loops to parallel execution, or identify parallelization opportunities. Handles CPU-bound (multiprocessing), I/O-bound (asyncio, threading), and data-parallel (vectorization) scenarios.

Manage Gmail - send, read, search emails, manage labels and drafts. Use when user wants to interact with their Gmail account for email operations.

Transform sequential Python code into parallel/concurrent implementations. Use when asked to parallelize Python code, improve code performance through concurrency, convert loops to parallel execution, or identify parallelization opportunities. Handles CPU-bound (multiprocessing), I/O-bound (asyncio, threading), and data-parallel (vectorization) scenarios.

World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. Expertise in Python, SQL, Spark, Airflow, dbt, Kafka, Flink, Kinesis, and modern data stack. Includes data modeling, pipeline orchestration, data quality, streaming quality monitoring, and DataOps. Use when designing data architectures, building batch or streaming data pipelines, optimizing data workflows, or implementing data governance.

Optimize workload distribution across workers, processes, or nodes for efficient parallel execution. Use when asked to balance work distribution, improve parallel efficiency, reduce stragglers, implement load balancing, or optimize task scheduling. Covers static/dynamic partitioning, work stealing, and adaptive load balancing strategies.

Analyze failed GitHub Action jobs for a pull request.

Full build workflow for adding new syscall descriptions to syzkaller

Syzkaller syzlang syntax basics for describing ioctl syscalls

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Build deterministic, verifiable data visualizations with D3.js (v6). Generate standalone HTML/SVG (and optional PNG) from local data files without external network dependencies. Use when tasks require charts, plots, axes/scales, legends, tooltips, or data-driven SVG output.