warden improve <skill> [options]
Revises an existing generated skill from an improvement brief using the
generated-skill reviewer loop.
| Argument | Purpose |
|---|
skill | Generated skill name or skill root path. |
| Option | Purpose |
|---|
-C, --cwd <path> | Run as if invoked from this directory. |
--config <path> | Path to warden.toml. |
-m, --model <model> | Model fallback when warden.toml does not specify one. See Models and Runtimes. |
--json | Output results as JSON. |
-p, --prompt <value> | Improvement brief. Prefix with @ to read from a file. |
--quiet | Errors and final summary only. |
-v, --verbose | Increase verbosity. Repeat as -vv or combine with --debug. |
--debug | Enable debug output. |
--log | Use log output mode. |
--color / --no-color | Override color detection. |
-h, --help | Show help for this command. |
warden improve security -p "Deepen source provenance and reference routing"
warden improve security -p @feedback.md
warden improve ./skills/security -p @feedback.md