Skill collection
benchflow-ai/skillsbench agent skills
- skills
- 178
- GitHub stars
- 1.8k
GitHub description: “SkillsBench evaluates how well skills work and how effective agents are at using them.”
- Stars
- 1,832 (370 forks)
- Licence
- Apache-2.0
- Last push
- Jul 2026
- Created
- Dec 2025
- Homepage
- skillsbench.ai
- benchmark
- skillsbench
Install all skills
npx skills add benchflow-ai/skillsbenchAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in benchflow-ai/skillsbench, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | This skill should be used when working on Lean 4 formalization projects to maintain persistent memory of successful proof patterns, failed approaches, project conventions, and user preferences… | benchflow-ai/ | 1.8k | — | ~3.2k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 2 | World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure. | benchflow-ai/ | 1.8k | — | ~5.9k | Automated safety check: Pass | MIT | 2 mo ago |
| 3 | AC branch pi-model power flow equations (P/Q and |S|) with transformer tap ratio and phase shift, matching acopf-math-model.md and MATPOWER branch fields. | benchflow-ai/ | 1.8k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 4 | 4.Civ6lib Civilization 6 district mechanics library. An agent skill from benchflow-ai/skillsbench. | benchflow-ai/ | 1.8k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 5 | Build deterministic, verifiable data visualizations with D3.js (v6). | benchflow-ai/ | 1.8k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 6 | DC power flow analysis for power systems. An agent skill from benchflow-ai/skillsbench. | benchflow-ai/ | 1.8k | — | ~717 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 7 | Calculate per-second RMS energy from audio files. An agent skill from benchflow-ai/skillsbench. | benchflow-ai/ | 1.8k | — | ~437 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 8 | Manage Gmail - send, read, search emails, manage labels and drafts. | benchflow-ai/ | 1.8k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 9 | Hex grid spatial utilities for offset coordinate systems. An agent skill from benchflow-ai/skillsbench. | benchflow-ai/ | 1.8k | — | ~690 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 10 | Analyzes 3D mesh files (STL) to calculate geometric properties (volume, components) and extract attribute data. | benchflow-ai/ | 1.8k | — | ~557 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 11 | Detect pauses and silence in audio using local dynamic thresholds. | benchflow-ai/ | 1.8k | — | ~642 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 12 | A skill your agent uses when erlang's concurrency model including lightweight processes, message passing, process links and monitors, error handling patterns, selective receive, and building… | benchflow-ai/ | 1.8k | 1 repo | ~2.1k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 13 | A skill your agent uses when erlang distributed systems including node connectivity, distributed processes, global name registration, distributed supervision, network partitions, and building… | benchflow-ai/ | 1.8k | 1 repo | ~3.3k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 14 | A skill your agent uses when oTP behaviors including genserver for stateful processes, genstatem for state machines, supervisors for fault tolerance, genevent for event handling, and building… | benchflow-ai/ | 1.8k | 1 repo | ~4.5k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 15 | Generate compression reports for video processing. An agent skill from benchflow-ai/skillsbench. | benchflow-ai/ | 1.8k | — | ~449 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 16 | 16.Senior Java World-class Java and Spring Boot development skill for enterprise applications, microservices, and cloud-native systems. | benchflow-ai/ | 1.8k | — | ~5k | Automated safety check: Pass | MIT | 2 mo ago |
| 17 | Detect initial silence segments in audio/video using energy-based analysis. | benchflow-ai/ | 1.8k | — | ~599 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 18 | Process videos by removing segments and concatenating remaining parts. | benchflow-ai/ | 1.8k | — | ~802 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 19 | Generator economic dispatch and cost optimization for power systems. | benchflow-ai/ | 1.8k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 20 | 20.Grpo Reference for the GRPO (Group Relative Policy Optimization) algorithm. | benchflow-ai/ | 1.8k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 21 | Optimize Python code for reduced memory usage and improved memory efficiency. | benchflow-ai/ | 1.8k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 22 | Implement mHC (Manifold-Constrained Hyper-Connections) for stabilizing deep network training. | benchflow-ai/ | 1.8k | — | ~1k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 23 | Transform sequential Python code into parallel/concurrent implementations. | benchflow-ai/ | 1.8k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 24 | Parse raw radar I/Q captures (CW or FMCW mmWave) and produce a cleaned 1-D slow-time signal ready for motion or vital-signs analysis. | benchflow-ai/ | 1.8k | — | ~586 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 25 | End-to-end pipeline for extracting heart rate (HR) and breathing rate (BR) from raw short-range radar I/Q captures — both continuous-wave (CW, 24 GHz clinical boards) and FMCW mmWave (60/77 GHz, TI… | benchflow-ai/ | 1.8k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 26 | Diagnostic guide for RL-based post-training of language models (GRPO, PPO, REINFORCE, DPO). | benchflow-ai/ | 1.8k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 27 | 27.Threejs Three.js scene-graph parsing and export workflows: mesh baking, InstancedMesh expansion, part partitioning, per-link OBJ export, and URDF articulation. | benchflow-ai/ | 1.8k | — | ~807 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 28 | Provides database transaction concurrency-control background. | benchflow-ai/ | 1.8k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 29 | Teaches how to reason from a transaction protocol’s rules to a working model. | benchflow-ai/ | 1.8k | — | ~1k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 30 | Teaches evidence-based analysis of transaction logs and traces. | benchflow-ai/ | 1.8k | — | ~845 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 31 | Estimate heart rate (HR) and breathing rate (BR) in bpm from a cleaned 1-D physiological time series such as radar phase, WiFi CSI amplitude, PPG, or a chest-motion signal. | benchflow-ai/ | 1.8k | — | ~925 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 32 | Optimize workload distribution across workers, processes, or nodes for efficient parallel execution. | benchflow-ai/ | 1.8k | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 33 | Extract audio from video files to WAV format. An agent skill from benchflow-ai/skillsbench. | benchflow-ai/ | 1.8k | — | ~359 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 34 | Combine multiple segment detection results into a unified list. | benchflow-ai/ | 1.8k | — | ~411 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 35 | A skill your agent uses when implementing the inner control loop for a quadrotor — attitude (roll/pitch/yaw) PID control and attitude planning (converting desired acceleration to desired Euler… | benchflow-ai/ | 1.8k | — | ~709 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 36 | Compare and implement eviction policies (LRU, LFU, FIFO, S3FIFO, ARC) for bounded-capacity caches. | benchflow-ai/ | 1.8k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 37 | Nonlinear optimization with CasADi and IPOPT solver. An agent skill from benchflow-ai/skillsbench. | benchflow-ai/ | 1.8k | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 38 | 38.Conditioning Data conditioning techniques for gravitational wave detector data. | benchflow-ai/ | 1.8k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 39 | Calculate the relative contribution of different factors to a response variable using R² decomposition. | benchflow-ai/ | 1.8k | — | ~738 | Automated safety check: Pass | MIT | 2 mo ago |
| 40 | A skill your agent uses when reading sensor data from CSV files, writing simulation results to CSV, processing time-series data with pandas, or handling missing values in datasets. | benchflow-ai/ | 1.8k | — | ~455 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 41 | Define custom distance/similarity metrics for clustering and ML algorithms. | benchflow-ai/ | 1.8k | — | ~674 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 42 | Video editing with ffmpeg including cutting, trimming, concatenating segments, and re-encoding. | benchflow-ai/ | 1.8k | — | ~952 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 43 | Process filler word annotations to generate video edit lists. | benchflow-ai/ | 1.8k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 44 | A skill your agent uses when converting natural language flight commands into waypoints and timing for a drone simulator. | benchflow-ai/ | 1.8k | — | ~770 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 45 | Detect flood events by comparing water levels to thresholds. | benchflow-ai/ | 1.8k | — | ~922 | Automated safety check: Pass | MIT | 2 mo ago |
| 46 | Choose placements that preserve useful residual capacity. An agent skill from benchflow-ai/skillsbench. | benchflow-ai/ | 1.8k | — | ~983 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 47 | 47.Gh CLI The gh CLI is GitHub's official command line tool for interacting with GitHub repositories, issues, pull requests, and more. | benchflow-ai/ | 1.8k | — | ~1.6k | Automated safety check: Pass | Proprietary | 2 mo ago |
| 48 | 48.Glm Basics Basic usage of the General Lake Model (GLM) for lake temperature simulation. | benchflow-ai/ | 1.8k | — | ~540 | Automated safety check: Pass | MIT | 2 mo ago |
Questions, answered from the data.
What is the best skill in benchflow-ai/skillsbench?
Lean4 Memories from benchflow-ai/skillsbench ranks first of the 178 skills in benchflow-ai/skillsbench listed here, with the highest score: its repository has 1.8k GitHub stars, its SKILL.md loads about 3.2k tokens and it passes the automated safety check with no findings. Next come Senior Data Engineer and Ac Branch Pi Model.
Are the skills in benchflow-ai/skillsbench official?
None yet. All 178 skills in benchflow-ai/skillsbench listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from benchflow-ai/skillsbench?
Run npx skills add benchflow-ai/skillsbench in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.