Agent Skill
Core Facts
Agent Skill adopts a lazy-loading mechanism whereby the Agent first reads only the metadata (name and description) of each Skill and loads the full instructions only after matching the user's need, so having multiple Skills coexisting does not increase Token consumption
The assets component is used to manage static resources such as images, audio, video, and other material files.
The scripts component allows Agents to call specific scripting tools when executing a Skill to assist in completing the task.
Timeline (last 90 days)
The Agentel team built a manual, deterministic n8n workflow for reviewing an Agent Skill's registered version, declared permissions, license and evidence support before adoption, and the workflow has been published in the n8n template library.
This workflow installs no Skills, executes no Skill code, and grants no permissions; it ultimately produces only one Skill record and one quota receipt for human review.
The MCPMarkets team scraped 5,945 MCP servers and 6,589 Agent Skill repositories on GitHub, about 92% coverage, totaling 12,534 deduplicated repositories.
The top 1% of MCP server repositories take 47.5% of server-side Stars and 41.7% on the Skill side; the top 10% together account for about 83%.
The Gini coefficient of the MCP server Star distribution is 0.867, and 0.882 on the Agent Skill side.
On the Skill side, 37.1% have fewer than 100 stars and 78.1% fewer than 1,000, with a median of 160.
Skill repositories are hotter than Servers on multiple metrics: median Stars 160 vs 64, total Stars 14.17 million vs 3.21 million, pushes in the last six months 84.6% vs 64.2%, and the 10k-star club 256 Skills vs 54 Servers.
On the server side, 20.4% have been dormant for 1–2 years, while on the Skill side the proportion dormant for 1–2 years is almost zero.
On the server side, 58.4% use the MIT license and 13.5% Apache-2.0, with permissive licenses totaling 73.2% and AGPL plus GPL 5.0%; on the Skill side MIT is 53.5%, permissive licenses total 66.4%, and copyleft is only 2.9%.
Unspecified licenses plus the NOASSERTION status cover 21.8% on the server side and as much as 30.4% on the Skill side.
12 more timeline events
All Facts (20)
Agent Skill adopts a lazy-loading mechanism whereby the Agent first reads only the metadata (name and description) of each Skill and loads the full instructions only after matching the user's need, so having multiple Skills coexisting does not increase Token consumption
70%VerifiedThe assets component is used to manage static resources such as images, audio, video, and other material files.
65%VerifiedThe scripts component allows Agents to call specific scripting tools when executing a Skill to assist in completing the task.
65%VerifiedAn Agent can have multiple Skills, with each Skill responsible for tasks in a specific domain.
65%VerifiedThe Agent Skill pattern has been widely applied in AI frameworks such as LangChain and AutoGPT.
65%Unverified会议总结Agent Skill输出包含会议摘要、核心要点和行动项三个固定模块
90%Unverified该会议总结Agent Skill内置了情感分析模块，能判断会议整体的情感倾向为积极、消极或中性
85%UnverifiedAgent Skill通过System Prompt工程、输出Schema约束和Few-shot示例注入来实现对LLM能力的专业化封装
75%UnverifiedSkill可以被不同的Agent加载和复用，而提示词通常是一次性的
70%Unverified现代Agent Skill体系可以分为三个核心层次：大脑决策层、技能封装层和执行引擎层
70%UnverifiedThe references component provides Agents with background knowledge and implementation details needed when executing tasks, such as API documentation and requirements documents.
60%UnverifiedThis workflow installs no Skills, executes no Skill code, and grants no permissions; it ultimately produces only one Skill record and one quota receipt for human review.
50%UnverifiedThe Agentel team built a manual, deterministic n8n workflow for reviewing an Agent Skill's registered version, declared permissions, license and evidence support before adoption, and the workflow has been published in the n8n template library.
50%UnverifiedOnly 28.7% of MCP servers have an executable install command extractable from the README, and only 34.5% contain a usable mcpServers configuration snippet; on the Skill side the install command extraction rate is 100% (uniformly npx skillfish add owner/repo/path).
50%UnverifiedThe MCPMarkets team scraped 5,945 MCP servers and 6,589 Agent Skill repositories on GitHub, about 92% coverage, totaling 12,534 deduplicated repositories.
50%UnverifiedThe top 1% of MCP server repositories take 47.5% of server-side Stars and 41.7% on the Skill side; the top 10% together account for about 83%.
50%UnverifiedThe Gini coefficient of the MCP server Star distribution is 0.867, and 0.882 on the Agent Skill side.
50%UnverifiedOn the Skill side, 37.1% have fewer than 100 stars and 78.1% fewer than 1,000, with a median of 160.
50%UnverifiedSkill repositories are hotter than Servers on multiple metrics: median Stars 160 vs 64, total Stars 14.17 million vs 3.21 million, pushes in the last six months 84.6% vs 64.2%, and the 10k-star club 256 Skills vs 54 Servers.
50%UnverifiedOn the server side, 20.4% have been dormant for 1–2 years, while on the Skill side the proportion dormant for 1–2 years is almost zero.
50%