Agents & tools · Glossary term
What is Skill Discovery?
A runtime pipeline that searches configured roots, identifies candidate skill directories, validates their package contract, attaches scope and provenance, resolves collisions, and publishes eligible catalog entries.
Why does Skill Discovery matter?
Deterministic discovery makes missing, malformed, shadowed, and unsafe packages diagnosable before model routing begins.
Skill Discovery in practice
Declare search scopes and duplicate behavior, decide how symlinks are handled, reject resource escapes, and log why each candidate was accepted or rejected.
What is the common confusion about Skill Discovery?
Skill discovery is not an unrestricted recursive search for filenames called `SKILL.md`; installation locations and precedence are runtime policy.
Learn Skill Discovery in the course
Start with
- Skill Discovery and Progressive Disclosure
A skill becomes useful before its body is loaded. Its name and description earn a place in the catalog; its deeper files earn context only when the task reaches them.
Taught in Phase 13: Tools & Protocols.
Related terms
- Skill CatalogThe compact model-visible inventory of eligible skills, usually containing routing metadata such as name, description, and an internal…
- Skill BundleThe complete installable skill directory, including `SKILL.md` and every reference, script, asset, fixture, or companion file required by…
- Progressive DisclosureSupplying a person or model with the minimum useful context first, then revealing deeper detail when the task or evidence requires it.
- Trust BoundaryAn interface where data, instructions, identity, or authority crosses between components or principals that operate under different trust…
Sources
More terms in Agents & tools
- Agent
- Agent Harness
- Agent Memory
- Agent State
- Agent Skill
- Approval Gate
- Checkpoint
- Compensating Action
- Delegation
- Durable Execution
- Function Calling
- Human-in-the-Loop (HITL)
- MCP (Model Context Protocol)
- Multi Round-Trip Request (MRTR)
- Orchestration
- Planning
- ReAct
- Sandbox
- Skill Bundle
- Skill Catalog
- Skill Invocation
- Stateless MCP
- Structured Output
- Swarm
- Termination Condition
- Tool Contract
This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.