Unverified50% confidenceFactExact time
Skill++'s core method is to rewrite only the name and description of each newly added skill, with no need to train the router or use labeled data, and without modifying the skill body.
1
Sources
50%
Confidence
Long-term
Relevance
11/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSkill++ requires the new description to contain three elements: what the skill body supports, how it differs from its closest predecessor, and which related work it excludes.76% similarUnverifiedWhen modifying a skill, you usually don't need to invoke the skill creator again; just use a normal prompt to have the model modify the corresponding Markdown file.75% similarUnverifiedSkill is a form of externalized memory, unrelated to model parameters, recording structured, readable and editable Markdown steps, and is more controllable than pure vector memory.75% similarUnverifiedSkills 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.73% similarUnverifiedBy default, only a Skill's name and description are sent to the model, not the full Markdown content; the full content is only disclosed to the model when the Skill is invoked.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1129275API
curl https://kongchang.com/api/v1/knowledge/claims/1129275MCP
get_claim(id=1129275)