Unverified50% confidenceDecision RuleExact time
Division of labor between claude.md and skill: claude.md is read every time and stores rules; skill is loaded only when used and stores procedures. Judgment tasks (such as picking segments and writing hooks) are left to humans, while execution tasks (such as how to cut and how to produce images) are left to fixed scripts to ensure reproducible results.
1
Sources
50%
Confidence
Long-term
Relevance
10/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSkill uses a layered loading design: at startup only the names and descriptions of all Skills are loaded; after a task is issued, descriptions are matched and the full content is then loaded, with on-demand reading during execution.76% similarUnverifiedSkill的工作流程为：元数据匹配→Skill加载→数据读取→工具执行→结果输出75% similarUnverifiedSkills consist of two parts—Description and Content; the Description is unconditionally loaded into the context at the start of every conversation, while the Content is only expanded and read when the model decides to use that Skill.75% similarVerifiedA 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.75% similarUnverifiedSkill.md differs from fine-tuning (which changes model weights) and prompt engineering (which relies on the context of a single conversation): it is a reusable asset independent of the model that can be loaded by an agent at runtime and followed step by step.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1110115API
curl https://kongchang.com/api/v1/knowledge/claims/1110115MCP
get_claim(id=1110115)