Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
13f-analyzer
Perform various data analysis on SEC 13-F and obtain some insights of fund activities such as number of holdings, AUM, and change of holdings between two quarters.
benchflow-ai/skillsbench 897
-
lab-unit-harmonization
Comprehensive clinical laboratory data harmonization for multi-source healthcare analytics. Convert between US conventional and SI units, standardize numeric formats, and clean data quality issues. This skill should be used when you need to harmonize lab values from different sources, convert units for clinical analysis, fix formatting inconsistencies (scientific notation, decimal separators, whitespace), or prepare lab panels for research.
benchflow-ai/skillsbench 897
-
enterprise-artifact-search
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.
benchflow-ai/skillsbench 897
-
mhc-algorithm
Implement mHC (Manifold-Constrained Hyper-Connections) for stabilizing deep network training. Use when implementing residual connection improvements with doubly stochastic matrices via Sinkhorn-Knopp algorithm. Based on DeepSeek's 2025 paper (arXiv:2512.24880).
benchflow-ai/skillsbench 897
-
modal-gpu
Run Python code on cloud GPUs using Modal serverless platform. Use when you need A100/T4/A10G GPU access for training ML models. Covers Modal app setup, GPU selection, data downloading inside functions, and result handling.
benchflow-ai/skillsbench 897
-
nanogpt-training
Train GPT-2 scale models (~124M parameters) efficiently on a single GPU. Covers GPT-124M architecture, tokenized dataset loading (e.g., HuggingFace Hub shards), modern optimizers (Muon, AdamW), mixed precision training, and training loop implementation.
benchflow-ai/skillsbench 897
-
syzkaller-build-loop
Full build workflow for adding new syscall descriptions to syzkaller
benchflow-ai/skillsbench 897
-
syz-extract-constants
Defining and extracting kernel constants for syzkaller syzlang descriptions
benchflow-ai/skillsbench 897
-
syzlang-ioctl-basics
Syzkaller syzlang syntax basics for describing ioctl syscalls
benchflow-ai/skillsbench 897
-
glm-output
Read and process GLM output files. Use when you need to extract temperature data from NetCDF output, convert depth coordinates, or calculate RMSE against observations.
benchflow-ai/skillsbench 897
-
glm-calibration
Calibrate GLM parameters for water temperature simulation. Use when you need to adjust model parameters to minimize RMSE between simulated and observed temperatures.
benchflow-ai/skillsbench 897
-
glm-basics
Basic usage of the General Lake Model (GLM) for lake temperature simulation. Use when you need to run GLM, understand input files, or modify configuration parameters.
benchflow-ai/skillsbench 897
-
hierarchical-taxonomy-clustering
Build unified multi-level category taxonomy from hierarchical product category paths from any e-commerce companies using embedding-based recursive clustering with intelligent category naming via weighted word frequency analysis.
benchflow-ai/skillsbench 897
-
d3js-visualization
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.
benchflow-ai/skillsbench 897
-
search-restaurants
Retrieve restaurants by city from the bundled dataset. Use this skill when recommending places to eat or validating dining options for a destination.
benchflow-ai/skillsbench 897
-
search-flights
Search flights by origin, destination, and departure date using the bundled flights dataset. Use this skill when proposing flight options or checking whether a route/date combination exists.
benchflow-ai/skillsbench 897
-
search-cities
List cities for a given state using the bundled background data. Use this skill to validate state inputs or expand destination choices before flight/restaurant/attraction/driving/accommodation lookups.
benchflow-ai/skillsbench 897
-
search-driving-distance
Estimate driving/taxi duration, distance, and rough cost between two cities using the bundled distance matrix CSV. Use this skill when comparing ground travel options or validating itinerary legs.
benchflow-ai/skillsbench 897
-
search-accommodations
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.
benchflow-ai/skillsbench 897
-
search-attractions
Retrieve attractions by city from the bundled dataset. Use this skill when surfacing points of interest or building sightseeing suggestions for a destination.
benchflow-ai/skillsbench 897
-
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
benchflow-ai/skillsbench 897
-
pddl-skills
Automated Planning utilities for loading PDDL domains and problems, generating plans using classical planners, validating plans, and saving plan outputs. Supports standard PDDL parsing, plan synthesis, and correctness verification.
benchflow-ai/skillsbench 897
-
filler-word-processing
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.
benchflow-ai/skillsbench 897
-
whisper-transcription
Transcribe audio/video to text with word-level timestamps using OpenAI Whisper. Use when you need speech-to-text with accurate timing information for each word.
benchflow-ai/skillsbench 897