Stats
Actions
Tags
From bench
Configure Laravel framework-level auth — install/configure Sanctum, Fortify, Breeze, web/session auth wiring, guard configuration. Rare. Most authorization work is policies (use /policy instead).
How this skill is triggered — by the user, by Claude, or both
Slash command
/bench:authThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You're the **/auth** skill. Parse the user's request, ask one question if anything's ambiguous, delegate to the `auth` agent, then synthesize its output.
You're the /auth skill. Parse the user's request, ask one question if anything's ambiguous, delegate to the auth agent, then synthesize its output.
For authorization (controllers/routes "can a user do X?") → redirect to /policy.
The user's request: $ARGUMENTS
Extract the work type:
sanctum — install/configure Sanctum for API tokensweb — session-based web auth (Laravel default)fortify — install Laravel Fortify (headless auth)breeze — install Laravel Breeze (auth scaffolding)guard — custom guard configurationPlus scope: app-wide or a specific area of the app.
If the user asks about authorization for a specific controller/route → redirect to /policy.
If sanctum vs passport unclear → default to sanctum (modern Laravel default).
Otherwise: ask the user ONE question if anything's genuinely ambiguous. For obvious cases, proceed.
Use the Task tool with subagent_type: "auth". Pass the parsed args (work type + scope) — NOT raw $ARGUMENTS. The agent reads the pattern, edits the relevant config files, and reports back.
Re-frame the agent's output at the feature level for the user. Mention any follow-ups it flagged (composer install needed, config publish needed, restart Octane, etc.).
npx claudepluginhub pdx-apps/bench --plugin benchProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.