Stats
Actions
Tags
From laconic
Run the laconic benchmark and print results in the CLI. Use when the user invokes /laconic benchmark or asks to benchmark token savings.
How this skill is triggered — by the user, by Claude, or both
Slash command
/laconic:benchmarkThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Run the laconic benchmark from anywhere — locate the script in the installed plugin and execute it.
Run the laconic benchmark from anywhere — locate the script in the installed plugin and execute it.
Locate the plugin install path. Try in order:
$CLAUDE_PLUGIN_ROOT (set when this skill runs)~/.claude/plugins/cache/laconic/laconic/* (newest match)pwd is the laconic repo
Fail with a clear message if benchmark/run.sh cannot be found.Check prerequisites: claude and jq on PATH. If missing, tell the user how to install.
Run the benchmark via Bash. Honor an optional RUNS argument from the user (default 3). Stream stderr so the user sees per-prompt progress. The script writes benchmark/results.md inside the plugin path.
Print results to chat: read benchmark/results.md and show the full markdown table. Include the total saved % on the first line of the reply.
claude CLI, no jq, no prompts file), stop and report — don't fake numbers.RUNS × number of prompts × 2 modes will take more than a couple of minutes.results.md — that's the user's call.npx claudepluginhub brillcp/laconic --plugin laconicCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.