AbstractSkill¶
AbstractSkill is the shared Python library for Agent Skills (SKILL.md) in the
AbstractFramework ecosystem.
It provides a small, dependency-light foundation for:
- parsing and validating
SKILL.mdfrontmatter and instructions - discovering skills on disk (progressive disclosure: metadata first)
- computing stable content hashes for skill evolution and replay safety
- formatting compact
<available_skills>prompt blocks for hosts and agents - composing a skill's tool declarations with an operator grant (never widening)
- classifying skill trust: validated skills, do-not-use advisories, and a fail-closed verdict (trust model)
Flows run; skills activate. AbstractSkill owns the portable skill contract so
abstractruntime, abstractgateway, and thin clients can share identical semantics
without duplicating parsers.
Install¶
pip install abstractskill
Next steps¶
- Getting started — parse, discover, compose tools, evaluate trust
- Architecture — components and data flow
- API reference — public functions and types
- Curated skills catalog — the reviewed shelf under
registry/skills/