Skill Builder

Build reusable capability from working procedures, domain knowledge, and recurring preferences. Choose instructions, evidence, and tools that make the task succeed.

Quick Path

1. Infer the outcome, trigger, target harness, edit scope, and authority from the request and package. Ask only for consequential missing information.
2. Identify evidence: successful work, a real artifact, documented contract, preference, or correction. Separate the reusable method from private records and incidental details.
3. Choose the useful scope and home: personal, project-local, or shared. Improve an existing skill when it owns the task; create or combine packages only when that clarifies selection and execution.
4. Edit the source and affected references together. Put routine instructions in SKILL.md, optional detail in references, repeatable operations in scripts, and output structures in assets.
5. Validate changed surfaces. Report format, execution, discovery, and behavioral evidence separately.
6. Deliver the usable patch, material decisions, and remaining limitations. Publication and installation follow the requested scope.

Read local layout when resolving repository sources or installed copies. Read source guide when deciding format requirements, target-specific differences, or rule provenance.

Choose What Belongs

Add what the agent cannot reliably infer: a preferred explanation style, private schema, subtle API contract, required artifact, fragile operation, or recurring mistake. Start from real work and user preferences.