Skill
A specialized capability module built into or extended on the ChatGPT platform, functioning similarly to a plugin mechanism. Skills augment the model with domain-specific capabilities such as image generation and document processing.
Core Facts
A Skill is a modular encapsulation that grants an agent specialized capabilities, containing complete workflows, judgment logic, and contextual knowledge, and can combine multiple tools to accomplish complex goals.
A Skill is a modular encapsulation that packages specialized capabilities, domain knowledge, and operational norms into reusable units, enabling Agents to invoke them automatically at the appropriate moment.
An AI Skill is a reusable AI execution unit that encapsulates the logic of a specific task, essentially a combination of structured prompts and code logic
Timeline (last 90 days)
Both MCP and Skill were originally product standards proposed by Claude Code and were later widely cited, and LangChain quickly provided direct support for them in its Deep Agents module.
Skills use a lazy-loading mechanism: at agent startup, only each Skill's name, one-sentence description, and local path are written into the context, and only after the model calls a file-reading tool such as Read does the Skill body get added to the context as tool return content.
When checking whether a Skill takes effect, one must distinguish between two different states: 'a Skill appears in the list' and 'the Skill's body has entered the context.'
The uploader's hands-on test: after installing the Skill, querying the same ticket task returned a result from 12306 in 35 seconds.
The uploader's hands-on test: after connecting MCP, each sentence carries about 2696 extra tokens of context, far higher than the Skill's roughly 28 tokens.
The uploader's recommendation: if the same functionality has a Skill version, install the Skill first to reduce context waste; consider MCP only when a tool needs to be reused across AI software; plugins suit users who deeply customize Harness.
The uploader's hands-on test: when using the Skill, each sentence consumes only about 28 extra tokens of context.
Skill uses an on-demand loading mechanism and does not reside in memory permanently; details are expanded only when a relevant task triggers it, so its context usage is very small.
Skills can be provided officially, shared by the community, or built by users themselves, with the core value lying in reducing the cost of repeated configuration.
As Skill entries increase, prompts get longer and inference slows down, requiring periodic consolidation and deduplication.
40 more timeline events
All Facts (20)
A Skill is a modular encapsulation that grants an agent specialized capabilities, containing complete workflows, judgment logic, and contextual knowledge, and can combine multiple tools to accomplish complex goals.
90%VerifiedA Skill is a modular encapsulation that packages specialized capabilities, domain knowledge, and operational norms into reusable units, enabling Agents to invoke them automatically at the appropriate moment.
90%VerifiedAn AI Skill is a reusable AI execution unit that encapsulates the logic of a specific task, essentially a combination of structured prompts and code logic
90%VerifiedA Skill is the concept of packaging multi-step interaction logic, context management, and output constraints into a callable unit, distinct from a single-interaction prompt template.
80%VerifiedA complete Skill contains a Skill.md main document, a Reference folder, a Script folder, and an Assets folder.
80%VerifiedAfter completing a task, Hermes Agent automatically creates new Skills and updates user information.
80%VerifiedAI Agent基于ReAct（Reasoning + Acting）等框架，能够将复杂任务分解为多个子步骤，自主决定何时调用外部工具
80%VerifiedThe difference between a Skill and an ordinary prompt is that a Skill is a reusable, accumulable structured capability unit.
80%VerifiedSkills本质上是结构化的系统提示词（System Prompt）集合，通过标准化接口注入到AI代理的上下文中
80%VerifiedSkills are not competitors to MCP but rather a layer above MCP: MCP is responsible for connecting tools and standardizing external service interfaces, while Skills are responsible for packaging and encapsulating complete task execution capabilities.
80%VerifiedAgent Skills是Anthropic发布的能力封装标准，定义为一个包含Skill.md文件的目录，可包含说明、脚本和其他资源
80%VerifiedChatGPT Work's configuration layer includes Projects providing brand context, Skills codifying ways of working, and Scheduled Tasks enabling automatic triggering.
75%VerifiedAgents (intelligent agents) can invoke tools on a computer and independently complete an entire set of complex tasks, unlike chatbots that can only conduct one-round-at-a-time conversations.
75%VerifiedSkills are essentially Markdown files stored in the project's .claude/ directory.
75%VerifiedWorkBuddy has a built-in Chinese Skill marketplace where common capabilities can be installed with one click.
70%VerifiedAccording to the presenter's observations, programmers at large tech companies may spend 70%–80% of their AI usage time writing Skills, with relatively little time spent directly writing code.
70%VerifiedAgent 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%VerifiedSkill's progressive loading mechanism has two levels: the first level exposes only name and description to form a minimal skill catalog; the second level reads the full SKILL.md and supporting files only after a hit.
65%VerifiedA Skill is a folder containing a file named skill.md, whose description resides in the agent context at low cost, with the body loaded only when a task matches.
65%VerifiedWhen a skill description is so detailed that it contains all the information needed to complete a task, the model will skip the skill-calling step.
65%