All categories
Tools & Automation
CLI tools, utilities, converters, workflow automation, and productivity helpers
- 49,210
- 2,051
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse tools & automation skills
Showing 19,441–19,464 of 49,210 skills
- Arxiv 2607 21503 Agentic Context Management Solving Agent Memory AnAgentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architec (arXiv: 2607.21503)Votes: 0GitHub stars: 3
- Arxiv 2607 21495 Toward Continuous Assurance For The DemocratizatioToward Continuous Assurance for the Democratization of AI Agent Creation in Industry (arXiv: 2607.21495)Votes: 0GitHub stars: 3
- Arxiv 2607 21273 The Dark Room In The Reward Channel Dense PredictiThe Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- an (arXiv: 2607.21273)Votes: 0GitHub stars: 3
- Arxiv 2607 21217 Icae Bench Evaluating Coding Agents As InteractiveICAE-Bench: Evaluating Coding Agents as Interactive Project Builders (arXiv: 2607.21217)Votes: 0GitHub stars: 3
- Arxiv 2607 21106 Attrimem Attribution Guided Process Feedback For AAttriMem: Attribution-Guided Process Feedback for Agent Memory Learning (arXiv: 2607.21106)Votes: 0GitHub stars: 3
- Arxiv 2607 20982 Guardianagentbench Where Agents Fail And How To GuGuardianAgentBench: Where Agents Fail and How to Guard Them (arXiv: 2607.20982)Votes: 0GitHub stars: 3
- Arxiv 2607 20972 Delivery Not Storage Cue Anchored Working Memory ADelivery, Not Storage: Cue-Anchored Working Memory as a Harness Property for Coding Agents (arXiv: 2607.20972)Votes: 0GitHub stars: 3
- Arxiv 2607 20908 Multi Turn Rl With Structural And Performance AwarMulti-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation (arXiv: 2607.20908)Votes: 0GitHub stars: 3
- Arxiv 2606 29806 Accelerating Q Learning Through Efficient Value ShAccelerating Q-learning through Efficient Value-Sharing across Actions (arXiv: 2606.29806)Votes: 0GitHub stars: 3
- Arxiv 2606 21140 Matching Matters A Fair Quality Efficiency BenchmaMatching Matters: A Fair Quality-Efficiency Benchmark for Command-Line Agents (arXiv: 2606.21140)Votes: 0GitHub stars: 3
- Arxiv 2606 19380 Claybuddy A Framework Evaluation Mitigation Of CodClayBuddy: A Framework, Evaluation, & Mitigation of Coding Agent Failures (arXiv: 2606.19380)Votes: 0GitHub stars: 3
- Arxiv 2606 00152 Privacypeek Auditing What Llm Based Agents AcquirePrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They Say (arXiv: 2606.00152)Votes: 0GitHub stars: 3
- Arxiv 2605 25815 Behind Evomap Characterizing A Self Evolving AgentBehind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network (arXiv: 2605.25815)Votes: 0GitHub stars: 3
- Arxiv 2604 02721 Grandcode Achieving Grandmaster Level In CompetitiGrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning (arXiv: 2604.02721)Votes: 0GitHub stars: 3
- Arxiv 2601 03895 All Quadrant Bounded Clipping Grpo Closing The UnbAll-Quadrant Bounded Clipping GRPO: Closing the Unbounded Blind Spot for Stable and Generalizable Training (arXiv: 2601.03895)Votes: 0GitHub stars: 3
- Arxiv 2511 04949 Deepforgeseal Latent Space Driven Semi Fragile WatDeepForgeSeal: Latent Space-Driven Semi-Fragile Watermarking for Deepfake Detection Using Adversarial Reinforcement Learning (arXiv: 2511.04949)Votes: 0GitHub stars: 3
- Arxiv 2510 06277 Dynamic Object Masks As Goal Representations For VDynamic Object Masks as Goal Representations for Visual Goal-Conditioned Reinforcement Learning (arXiv: 2510.06277)Votes: 0GitHub stars: 3
- Arxiv 2510 03699 Dissecting Larval Zebrafish Hunting Using Deep ReiDissecting Larval Zebrafish Hunting using Deep Reinforcement Learning Trained RNN Agents (arXiv: 2510.03699)Votes: 0GitHub stars: 3
- Arxiv 2307 12022 Latent Utility Q Learning For Preference AdaptiveLatent Utility Q-Learning for Preference-Adaptive Dynamic Treatment Regimes (arXiv: 2307.12022)Votes: 0GitHub stars: 3
- Artificial Intellgence Application In Life Sciences And Beyond The Upper Rhine Artificial Intelligence Symposium Urai 2021**arXiv ID:** 2112.05657 **Authors:** Karl-Herbert Schäfer, Franz Quint **Published:** 2021-12-10T16:43:01Z **Abstract:** The TriRhenaTech alliance presents the accepted papers of the 'Upper-Rhine Artificial Intelligence Symposium' held on October 27th 2021 in Kaiserslautern, Germany. Topics of the conference are applications of Artificial Intellgence in life sciences, intelligent systems, industry 4.0, mobility and others. The TriRhenaTech alliance is a network of universities in the Upper-R...Votes: 0GitHub stars: 3
- Agentic Data EnvironmentsAutonomous agents promise substantial gains in speed, scale, and labor efficiency, but their failures can impose abrupt and often irreversible costs. The central challenge for agentic automation is th. Based on arXiv:2607.07397.Votes: 0GitHub stars: 3
- Agent Autonomous Dreaming基于神经科学研究的 Agent 自主梦境系统,模拟人类睡眠中的记忆巩固过程。适用于 AI Agent 的记忆管理、知识整理、自动学习场景。触发词:自主梦境、记忆重塑、agent dreaming、memory consolidation、每日做梦Votes: 0GitHub stars: 3
- Actrce Augmenting Experience Via Teachers Advice For Multigoal Reinforcement Learning**arXiv ID:** 1902.04546 **Authors:** Harris Chan, Yuhuai Wu, Jamie Kiros, Sanja Fidler, Jimmy Ba **Published:** 2019-02-12T18:43:56Z **Abstract:** Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling the goals. Despite its effectiveness, HER has limited applicability because it lacks a compact and universal goal representation. ...Votes: 0GitHub stars: 3
- A Symbolic Neural Cpu For Quantizationsimulated Writeback And Interpretable Program Execution**arXiv ID:** 2607.10021 **Authors:** Jose Luis Lima de Jesus Silva **Published:** 2026-07-10T22:55:23Z **Abstract:** Neural networks can learn algorithmic input-output mappings, but trusting a learned executor requires more than a correct final answer because the state transitions that produce it are usually hidden. To make those transitions visible, we introduce a trace-supervised symbolic neural CPU, a factorized learned execution architecture that combines recurrent control, an explicit o...Votes: 0GitHub stars: 3