skillfed

Agent-skills research didn't exist before 2023 — and its fastest-growing direction today is security

Field report · Mike Arbuzov · SkillFed Research ·

AI-assisted notes · reviewed by SkillFed

A SkillFed field map of 364 agent-skills papers, 2016–2026: none of this work existed before 2023, and skill security went from nothing to the second-fastest-growing direction in about three quarters.

We harvested, classified, and mapped 364 research papers on agent skills — the reusable, shareable instruction files that let AI agents do specialized work — reaching back to October 2016. The first thing the map shows is an absence: before 2023, essentially none of this literature existed. Not one paper in our corpus framed skills the way today's agent builders do until 2023, when the first handful appeared and, by that year's third quarter, first outnumbered the older robotics-and-reinforcement-learning work they grew out of — a thin 3-to-2 crossing.

From there the field bloomed. Today it resolves into five recognizable directions. Three are accelerating fast: skill evolution — agents that generate and govern their own skill libraries — leads at +5.1 papers per quarter; skill retrieval climbs at +1.7; and the breakout is skill security, which went from nothing before mid-2025 to the second-fastest-growing direction, +2.8 papers per quarter, in about three quarters. A fourth direction, robotic skill learning, has grown steadily since 2016 (+1.0 per quarter); a fifth, agentic benchmarks, is only months old. And the field still remembers where it came from: of the in-corpus citations we could resolve from agent-skills papers, 55% still point back to the robotics and RL roots.

2026 Feb Mar Apr May Jun Jul pre-2026 · 116 MalSkillBench: A Runtime-Verified Benchmark of Malicious Agent Skills Beware of Agentic Botnets: Scalable Untargeted Promptware Attacks via Universal and Transferable Adversarial HalluSquatting Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills SLBench: Evaluating How LLM Agents Follow Logical Relations in Skills Sealing the Audit-Runtime Gap for LLM Skills SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces When Skills Lie: Hidden-Comment Injection in LLM Agents Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis Clawdrain: Exploiting Tool-Calling Chains for Stealthy Token Exhaustion in OpenClaw Agents Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks Behavioral Integrity Verification for AI Agent Skills Methods for Formal Verification of Agent Skills: Three Layers Toward a Mechanically Checkable Capability-Containment Proof "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild When Agents Talk: Discourse, Manipulation, and Risk in an Agentic Social Network Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections POISE: Position-Aware Undetectable Skill Injection on LLM Agents SkillClone: Multi-Modal Clone Detection and Clone Propagation Analysis in the Agent Skill Ecosystem Malicious Or Not: Adding Repository Context to Agent Skill Classification How Your Credentials Are Leaked by LLM Agent Skills: An Empirical Study SkillMutator: Benchmarking and Defending Language-and-Code Cross-modal Attacks on LLM Agent Skills SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation SkillGuard: A Permission-Centric Framework for Agent Skill Security FORTIS: Benchmarking Over-Privilege in Agent Skills Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis Structured Security Auditing and Robustness Enhancement for Untrusted Agent Skills Under the Hood of SKILL.md: Semantic Supply-chain Attacks on AI Agent Skill Registry ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree Formal Analysis and Supply Chain Security for Agentic AI Skills HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents? SkillProbe: Security Auditing for Emerging Agent Skill Marketplaces via Multi-Agent Collaboration Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills SkillTester: Benchmarking Utility and Security of Agent Skills Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces Skill security born 2025-Q3 ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement Learning Reinforcement Learning for Self-Improving Agent with Skill Library Skill-R1: Agent Skill Evolution via Reinforcement Learning Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents Co-Evolving Skill Generation and Policy Optimization SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems Evolving Programmatic Skill Networks SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills SkillOS: Learning Skill Curation for Self-Evolving Agents SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System SkillX: Automatically Constructing Skill Knowledge Bases for Agents SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks SkillMaster: Toward Autonomous Skill Mastery in LLM Agents MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO SkillAudit: From Fixed-Suite Benchmarking to Skill-Centered Assessment SkillCenter: A Large-Scale Source-Grounded Skill Library for Autonomous AI Agents SkillComposer: Learning to Evolve Agent Skills for Specification and Generalization Skill Coverage: A Test Adequacy Metric for Agent Skills SkillGen: Verified Inference-Time Agent Skill Synthesis SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents SkillGrad: Optimizing Agent Skills Like Gradient Descent SkillClaw: Let Skills Evolve Collectively with Agentic Evolver SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills SkillNet: Create, Evaluate, and Connect AI Skills CUA-Skill: Develop Skills for Computer Using Agent A Framework for Evaluating Agentic Skills at Scale Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale CODESKILL: Learning Self-Evolving Skills for Coding Agents OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents Automating Skill Acquisition through Large-Scale Mining of Open-Source Agentic Repositories: A Framework for Multi-Agent Procedural Knowledge Extraction OpenSkill: Open-World Self-Evolution for LLM Agents MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality SkillOpt: Executive Strategy for Self-Evolving Agent Skills CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification EvoSkill: Automated Skill Discovery for Multi-Agent Systems An Empirical Study of Downstream Adaptation for Agent Skills A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications Agent Skill Evaluation and Evolution: Frameworks and Benchmarks SkillEvolver: Skill Learning as a Meta-Skill SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution SkillAudit: Ground-Truth-Free Skill Evolution via Paired Trajectory Auditing Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills Inside the Skill Market: From Software Engineering Activities to Reusable Agent Skills SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe Dynamic Agent Skills: A Lifecycle Survey and Taxonomy of Evolving Skill Libraries SkillWiki: A Living Knowledge Infrastructure for Agent Skills Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents Skillware: A Software Ontology and Engineering Lifecycle for Persistent Behavioral Artifacts Skill evolution born 2025-Q2 Do LLM-Generated Skills Make Better AI Data Scientists? A Component Ablation Across Data-Science Workflows Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents SkillReducer: Optimizing LLM Agent Skills for Token Efficiency SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents Graph of Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills Skill Is Not Document: A Query-Conditional Benchmark and Two-Stage Retriever for LLM Agent Skill Routing Skill Retrieval Augmentation for Agentic AI SkillSelect-Serve: QoS-Aware Budgeted Skill Service Recommendation for LLM Agents SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale SkillRouter: Skill Routing for LLM Agents at Scale Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents SkillResolve-Bench: Measuring and Resolving Same-Capability Ambiguity in Agent Skill Retrieval Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose SkillFlow: Scalable and Efficient Agent Skill Retrieval System Task Decomposition-Guided Reranking for Adaptive Agent Skill Retrieval Group of Skills: Group-Structured Skill Retrieval for Agent Skill Libraries How Well Do Agentic Skills Work in the Wild: Benchmarking LLM Skill Usage in Realistic Settings Generative Skill Composition for LLM Agents SkillsInjector: Dynamic Skill Context Construction for LLM Agents Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-Refinement Skill retrieval born 2025-Q2 SciVisAgentSkills: Design and Evaluation of Agent Skills for Scientific Data Analysis and Visualization ColPackAgent: Agent-Skill-Guided Hard-Particle Monte Carlo Workflows for Colloidal Packing NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation Notes2Skills: From Lab Notebooks to Certainty-Aware Scientific Agent Skills Agentic Publication Protocol: An Attempt to Modernize Scientific Publication Decoding ML Decision: An Agentic Reasoning Framework for Large-Scale Ranking System From Agent-Only Social Networks to Autonomous Scientific Research: Lessons from OpenClaw and Moltbook, and the Architecture of ClawdLab and Beach.Science EpochX: Building the Infrastructure for an Emergent Agent Civilization STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systems KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill AgentClick: A Skill-Based Human-in-the-Loop Review Layer for Terminal AI Agents MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop HighTide: An Agent-Curated Open-Source VLSI Benchmark Suite NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs StructureClaw: Traceable LLM Agents and an Executable Benchmark for Structural Engineering Workflows RigorBench: Benchmarking Engineering Process Discipline in Autonomous AI Coding Agents TDAD: Test-Driven Agentic Development - Reducing Code Regressions in AI Coding Agents via Graph-Based Impact Analysis LEGO: An LLM Skill-Based Front-End Design Generation Platform Pomona: Continuous Code Quality Improvement via Small, Agentic Pull Requests at Bloomberg EffiSkill: Agent Skill Based Automated Code Efficiency Optimization How Agent Skills Fail under Long Contexts: A White-Box Study in Code Auditing Agentic benchmarks born 2026-Q1 DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedback OpenAssistant Conversations - Democratizing Large Language Model Alignment Analyzing Modular Approaches for Visual Question Decomposition On Data Engineering for Scaling LLM Terminal Capabilities Automated Educational Question Generation at Different Bloom's Skill Levels Using Large Language Models: Strategies and Evaluation R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training Agent Skill Acquisition for Large Language Models via CycleQD Cerbero-7B: A Leap Forward in Language-Specific LLMs Through Enhanced Chat Corpus Generation and Evaluation A Comparative Study of Code Generation using ChatGPT 3.5 across 10 Programming Languages Rescue: Ranking LLM Responses with Partial Ordering to Improve Response Generation Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data Skill-Mix: a Flexible and Expandable Family of Evaluations for AI models Skill-it! A Data-Driven Skills Framework for Understanding and Training Language Models Compute Optimal Scaling of Skills: Knowledge vs Reasoning LLM skill training born 2023-Q1 Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft Odyssey : Empowering Minecraft Agents with Open-World Skills Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems in Minecraft MindAgent: Emergent Gaming Interaction Voyager: An Open-Ended Embodied Agent with Large Language Models Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery Learning Communication Skills in Multi-task Multi-agent Deep Reinforcement Learning STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models Scalable Multi-agent Covering Option Discovery based on Kronecker Graphs MetaAgents: Large Language Model Based Agents for Decision-Making on Teaming Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation On Multi-Agent Learning in Team Sports Games OSExpert: Computer-Use Agents Learning Professional Skills via Exploration Exploration Based Language Learning for Text-Based Games Curiosity-Driven Exploration via Latent Bayesian Surprise Offline Multi-agent Continual Cooperation via Skill Partition and Reuse Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning Improving Agent Interactions in Virtual Environments with Language Models Unsupervised Skill-Discovery and Skill-Learning in Minecraft Self-Supervised Exploration via Disagreement Curiosity-Driven Exploration by Self-Supervised Prediction Playful Agentic Robot Learning ALAN: Autonomously Exploring Robotic Agents in the Real World See and Think: Embodied Agent in Virtual Environment A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals Closed-Loop Vision-Language Planning for Multi-Agent Coordination Augmenting Autotelic Agents with Large Language Models SIMA 2: A Generalist Embodied Agent for Virtual Worlds Social Structure Matters in 3D Human-Human Interaction Generation The Information Geometry of Unsupervised Reinforcement Learning Learning with AMIGo: Adversarially Motivated Intrinsic Goals Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learning Latent Skill Planning for Exploration and Transfer Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents Lipschitz-constrained Unsupervised Skill Discovery ELSIM: End-to-end learning of reusable skills through intrinsic motivation Visual Reinforcement Learning with Imagined Goals SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning DexHoldem: Playing Texas Hold'em with Dexterous Embodied System Learning agile soccer skills for a bipedal robot with deep reinforcement learning RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents Goal-Conditioned Reinforcement Learning with Imagined Subgoals Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning MoCapAct: A Multi-Task Dataset for Simulated Humanoid Control WildLMa: Long Horizon Loco-Manipulation in the Wild Choreographer: Learning and Adapting Skills in Imagination Unsupervised Perceptual Rewards for Imitation Learning Deep visual foresight for planning robot motion Accelerating Reinforcement Learning with Learned Skill Priors PI-QT-Opt: Predictive Information Improves Multi-Task Robotic Reinforcement Learning at Scale Continual Quadruped Robots Coordination via Semantic Skill Discovery Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills Learning Predictive Models From Observation and Interaction Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds Learning Latent Plans from Play MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation Meta-learning Parameterized Skills Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents Composing Task-Agnostic Policies with Deep Reinforcement Learning AgentVLN: Towards Agentic Vision-and-Language Navigation Skill-based Model-based Reinforcement Learning GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks Inner Monologue: Embodied Reasoning through Planning with Language Models Chat with the Environment: Interactive Multimodal Perception Using Large Language Models Ag2Manip: Learning Novel Manipulation Skills with Agent-Agnostic Visual and Action Representations GEMS: Agent-Native Multimodal Generation with Memory and Skills CLIPort: What and Where Pathways for Robotic Manipulation MolmoWeb: Open Visual Web Agent and Open Data for the Open Web Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning PANDO: Efficient Multimodal AI Agents via Online Skill Distillation Do As I Can, Not As I Say: Grounding Language in Robotic Affordances Developmental Scaffolding with Large Language Models SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling Language Conditioned Imitation Learning Over Unstructured Data Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills Agentic Skill Discovery Agent Skills Should Go Beyond Text: The Case for Visual Skills Language to Rewards for Robotic Skill Synthesis Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition Skill-CMIB: Multimodal Agent Skill for Consistent Action via Conditional Multimodal Information Bottleneck MMSkills: Towards Multimodal Skills for General Visual Agents XSkill: Continual Learning from Experience and Skills in Multimodal Agents Robotic skill learning born 2016-Q4 The shape of agent-skills research radius = publication month (pre-2026 compressed to the core; 2026 by month to the rim) · wedge = direction · arrow length = drift speed · outer dots = undifferentiated core (105) llm-agent-skillsrobotics-skillsrl-skill-theoryother / reject
How to read it. Each dot is one paper; it fades in when it was published, so the whole field blooms outward through 2026 on its own. Radius is publication date — everything before 2026 is packed into the inner core, and 2026 fans out month by month to the rim. Angle marks the research direction, and each wedge's arrow shows how that direction's center of mass has drifted. Violet dots are agent-skills work; coral is robotics; blue is RL theory; grey is the undifferentiated core.

The five directions

Clustering the 364 embedded papers yields six directions; we name and chart the five that sit on the agent-skills spine. Growth is new papers per quarter, from a linear fit over the direction's most recent quarters.

DirectionBornPapersGrowth /qTrajectory
Skill evolutionAgents that generate, evolve, and govern their own skill libraries.2025-Q265+5.1accelerating
Skill securityAttacks on, and defenses for, agent skill files — malicious skills, injection, threat taxonomies.2025-Q340+2.8accelerating
Skill retrievalFinding and routing the right skill from a large library at inference time.2025-Q222+1.7accelerating
Robotic skill learningThe pre-LLM roots: goal-conditioned RL, self-supervised exploration, imitation, manipulation.2016-Q495+1.0enduring
Agentic benchmarksA 2026-born cluster of autonomous-agent benchmarks and evaluation harnesses.2026-Q121—too new

Agentic benchmarks is only three quarters old — too young for a meaningful growth slope, so we leave it blank. A sixth cluster, an older and now-dormant strand of general LLM-training work, sits off the agent-skills spine; we fold it into the field's undifferentiated core rather than call it a direction. One more caution when comparing against the rest of this site: the SkillFed research directory tags each of its 191 notes with a direction from a separate per-paper classification (evolution, security, retrieval, benchmarks); this map's clusters are computed independently over the full 364-paper corpus, so the names overlap but the counts differ.

Key numbers

Agent-skills papers before 20230
When LLM-skills work first outpaced robotics2023-Q3
Papers in the field map364
Steepest-growing direction (skill evolution)+5.1/q
Skill security, from a standing start+2.8/q
Share of papers mapped into clear directions71.2%

How we made this — and what it can't tell you

We built the map in four steps. Starting from two 2026 survey papers, we crawled outward through citations to assemble 364 papers; classified each as core, adjacent, or off-topic (191 / 123 / 50) and tagged its domain (251 agent-skills, 44 robotics, 19 RL theory, 50 other); embedded every abstract; then clustered the embeddings into six directions, with 71.2% of papers falling into a clear cluster and the rest left as an undifferentiated core. Three limits matter, and we want them in plain view.

  • This is a map of when work was published, not of influence. A paper's distance from the center is its publication date, not citations it has gathered over time. A 2026 paper sits near the rim because it is new — not because it is unproven or overlooked.
  • The 2026 surge is over-sampled. Because our crawl began at two 2026 surveys and followed citations, recent work is over-represented: 2026 is 68% of the corpus (248 of 364), and 2025–2026 together are 76%, versus under 10% (36 papers) before 2023. The shape of the story — 2016 robotics roots, 2023 ignition, 2026 surge — is robust, because it rests on publication dates and domain tags rather than on the crawl. The magnitude of 2026 is not a census. We could not run the intended cross-check either: the corpus's citation graph is too sparse to trace papers back to the seed surveys, so we bound the bias with the year skew above and report it openly.
  • Small samples make fine detail noisy. Several directions have only a few papers per quarter, so quarter-to-quarter wiggles are not meaningful. Growth measured over several quarters is the signal we trust; anything finer, we don't.
  1. Insight · Any AI chat can now run skill search — and you approve every request

    No install, no account, no connector. Your chat writes an abstract wish, you paste the link back, and it reads five security-swept skills. The whole request is a URL in plain English — the privacy boundary is something you check, not something you're asked to trust.

  2. Field report · 61 findings on a site we built for SEO

    A site with build-blocking structured-data lints, machine-readable mirrors and an enforced internal-linking floor still failed 61 checks drawn from the SEO skills our own editorial recommends — including FAQPage markup that same post called retired. 19% of the skills' criteria were stale too.

  3. Insight · 60,611 skills in the wild — what a full census of the public SKILL.md corpus shows

    SkillFed walked all 6,177 repositories in its discovery queue end to end: 2.5× more unique skills than listings claimed, 13,122 per-agent variant files merged, and 86,956 vendored aggregator copies excluded — more copies than originals.

  4. Insight · The largest direction in agent-skill research is spreading outward, not settling down

    Papers on agents that write their own skills land steadily farther from the direction's own semantic center month over month — the only trend in our analysis that survives multiple-comparison correction (BH p = 0.0016) — with no single axis carrying the drift.

  5. Insight · Zero of 184 recent papers connect skill self-authoring with skill security

    Five of the six research-direction pairs in the recent agent-skill literature are bridged by dual-topic papers. The pair formed by its two largest directions — agents authoring their own skills, and securing skill files — is empty, and three null models say that is not chance.