agent-skill-generatorlisted

# Agent skill generator Build portable skills by default, bind them to a repository or host only when the task requires it, and spend context only on behavior the target agent cannot reliably infer. ## Route by mode Choose one primary mode and honor its side-effect boundary. | Mode | Use when | Required output | File changes | |---|---|---|---| | `design` | Turn a problem or repeated workflow into an implementation-ready skill design | Contract, portability target, package map, side-effect boundaries, and validation plan | None | | `new` | Build a skill from a defined problem or workflow | Complete skill package and validation summary | Create the agreed package; update only required registration metadata and docs | | `revise` | Improve an existing skill | Focused edits, validation summary, and delta | Edit only authorized scope | | `audit` | Find trigger, structure, portability, or token problems | Prioritized findings with concrete targets | None unless separately requested | | `validate` | Pressure-test an existing skill | Evidence record and residual risk | None unless separately requested | | `optimize-trigger` | Improve activation precision or recall | Revised trigger metadata plus adjacent-case analysis | Trigger-bearing metadata only unless broader edits are requested | If the request mixes modes, keep read-only work read-only and state which changes are authorized before editing. Do not rename stable skill identifiers in `optimize-trigger` mode unless the user e