dokimi catalog

usage: dokimi catalog [-h] {scan,trigger-set} ...

positional arguments:
  {scan,trigger-set}
    scan              Report which skills/tasks under --root load cleanly
    trigger-set       Build a skill-selection query set (labels + leakage/framing lint) from
                      question sets

options:
  -h, --help          show this help message and exit

dokimi catalog scan

usage: dokimi catalog scan [-h] --root ROOT [--kind {skills,tasks,all}]
                           [--tasks-subdir TASKS_SUBDIR]

options:
  -h, --help            show this help message and exit
  --root ROOT           Local checkout to scan
  --kind {skills,tasks,all}
                        Restrict the scan to skills, tasks, or both (default: all)
  --tasks-subdir TASKS_SUBDIR
                        Task directory relative to --root (default: evaluation/harbor/tasks, the
                        uxlfoundation/skills convention)

dokimi catalog trigger-set

usage: dokimi catalog trigger-set [-h] --catalog CATALOG --questions PATH=LABEL
                                  [--format {reach,skill-creator,questions}] [--target TARGET]
                                  [--rewrite] [--model MODEL] [--provider PROVIDER] [--strict]
                                  --out OUT

options:
  -h, --help            show this help message and exit
  --catalog CATALOG     Directory of the skills the agent will see
  --questions PATH=LABEL
                        Question file and its label: a skill name, 'none' (no skill should load),
                        or '@field.path' read per question (e.g. @metadata.skill_under_test).
                        Repeatable.
  --format {reach,skill-creator,questions}
                        reach: google/skill-reach QuerySet; skill-creator: one target's eval set;
                        questions: a questions artifact for the skill-catalog: arm
  --target TARGET       Target skill for --format skill-creator
  --rewrite             Rewrite each question into first-person user voice (model sees only the
                        question)
  --model MODEL         Model for --rewrite
  --provider PROVIDER   Provider for --rewrite (default: openai)
  --strict              Exit 1 if any query names a skill, keeps exam framing, or has an
                        unresolved @field label
  --out OUT             Output JSON path