ak skill

What it does: (For catalog browsing - list, install, remove - see ak skills. This command operates on a single per-skill runtime env.) Commands for managing the per-skill Python/Node runtime envs that ak run activates before executing a skill. Each subcommand operates on a single <kit>/<skill> reference.

Who it's for: Power devs scripting env hygiene; non-technical users via the matching dashboard surface.

When to use it: Run ak skill verify after a fresh checkout to confirm all envs are healthy; ak skill install after editing skill.yaml to populate the env; ak skill repair when verify reports corrupt; ak skill upgrade after changing the runtime block.

Examples: ak skill verify marketing/youtube # report health (ok|missing|corrupt|unknown) ak skill install marketing/youtube # create or refresh the env ak skill repair marketing/youtube # rebuild a corrupted env ak skill upgrade marketing/youtube # re-resolve after editing skill.yaml ak skill remove marketing/youtube # tear down the per-skill record

What changes on disk: Read-only at this group level; subcommands document their own effects under ~/.agentkit/skills/<kit>/<skill>/ and ~/.agentkit/cache/<hash>/.

Output modes: pretty default on TTY (colors, ASCII markers) plain auto when stdout piped or --no-interactive json --json (single-object envelope, NDJSON-safe)

Exit codes: 0 success 1 runtime error 2 invalid flags 3 user-cancel (SIGINT, prompt-cancel)

Options

  -h, --help             help for skill
      --json             Emit machine-readable JSON (implies --no-interactive)
      --no-interactive   Disable interactive prompts (CI-safe)
  -q, --quiet            Suppress non-error output on stderr
  -V, --verbose          Extra diagnostic output on stderr (loses to --quiet)
  -y, --yes              Assume yes for all prompts

ak skill

Synopsis

Options

SEE ALSO

On this page