Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →withwoz/woz
WOZCODE utilities. Subcommands — login, logout, status, settings, update, share, review (deep multi-persona code review), benchmark (WOZCODE vs vanilla comparison). Invoke as `/woz <subcommand>`, e.g. `/woz login` or `/woz review`.
4 of 24 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 6 comparable cases; this report requires 8.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
I want to run a WOZCODE benchmark on my project but do not have task prompts prepared.
| Checked | Without skill | With skill |
|---|---|---|
| Offers to inspect project files to suggest realistic coding task prompts. | Missed | Passed |
The instructions your model reads when the skill loads.
One skill, eight subcommands. The first word of the arguments selects the subcommand:
| Subcommand | Purpose |
|---|---|
login | Authenticate with the Woz service (browser, API key, or token) |
logout | Clear stored credentials and log out |
status | Show authentication and subscription status |
settings | Show or update WOZCODE plugin settings |
update | Update the WOZCODE plugin to the latest version |
share | Print the referral share message |
review | Deep multi-persona code review of the current branch (requires KnowledgeBase access) |
benchmark | Side-by-side WOZCODE vs vanilla Claude Code comparison on the user's repo |
TRIGGER when: the user runs /woz <subcommand>, or says "log in to woz", "woz status", "woz settings", "configure woz", "toggle attribution", "update woz", "refer a friend", "deep review", "final check before pushing", "review my branch", "is this ready to ship", "compare woz", "how much does woz save", "benchmark woz", or similar.
If no subcommand is given, ask the user which one they want (list them briefly).
Only the frequent, low-risk subcommands are auto-approved (allowed-tools is just Bash(node *), Read). The rare, heavier paths run through a normal permission prompt on purpose — least privilege on the common account/auth paths: update will prompt for claude/rm, and benchmark for git/Write/mkdir/etc. Approve those when the user runs them.
Dispatch on the arguments after the subcommand:
woz_sk_ (regardless of surrounding flags) → API Key Login below.--token <token> → Token Login below.Run the Woz authentication flow. This opens a browser for the user to log in:
node --no-warnings=ExperimentalWarning ${CLAUDE_PLUGIN_ROOT}/scripts/wozcode-cli.cjs login
If the command exits with code 0, login succeeded — confirm to the user.
test cases passed with the skill
More skills from the same source and nearby in the registry, with their headline benchmark lift.