Expired70% confidenceFactExact time
Skills adopt a Progressive Disclosure mechanism, whereby the Agent only loads the complete instructions into the context window when a user request matches the skill description.
4
Sources
70%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
Andrew Ng Partners with Anthropic to Launch Agent Skills Course: Build Once, Deploy Anywhere
bilibiliClaudeCode教程6/9/2026
Related Claims
UnverifiedIn a multi-skill Agent system, metadata plays the role of a routing label, with the scheduling layer performing semantic matching between user intent and the names and descriptions of registered Skills to activate the appropriate skill.76% similarVerifiedSkills采用渐进式披露设计，平时只向模型提供技能的名称和描述，具体执行规则在需要时才加载73% similarUnverifiedSkills involve encapsulating a capability to be automatically discovered and used by the model, whereas Workflow requires explicit triggering with the ultrawork keyword.72% similarUnverified演示任务完成后系统提示skill created，自动创建了新技能并更新用户信息，体现自动生成Skill特性72% similarUnverifiedThe system provides personalized skill optimization capabilities, allowing users to customize individual skills through prompt adjustments and document uploads.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/49887API
curl https://kongchang.com/api/v1/knowledge/claims/49887MCP
get_claim(id=49887)