Install any skill in seconds. Free to start, no credit card required.
Get Started Free →qdhenry/setup-agent-tail
Configure agent-tail log aggregation for the current project. Auto-detects framework (Vite, Next.js, plain Node, monorepo) and sets up CLI runner, browser log plugins, and output destinations.
Passed 16 of 20 test cases with the skill, and 7 of 20 without it.
and 12 more in the full report
12 fixed6 passed either way3 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
In a repository containing only `pnpm-lock.yaml` and `package.json`, show the command to install the logging tools.
| Checked | Without skill | With skill |
|---|---|---|
| Uses pnpm add -D as the package installation command. | Missed | Passed |
| Includes agent-tail-core in the package installation arguments. | Missed | Passed |
The instructions your model reads when the skill loads.
<quick_start> Run the auto-detect workflow below. The skill will:
<essential_principles>
tmp/logs/latest/ — this is agent-tail's standard output directorytmp/ directory must be gitignoredagent-tail-core init at root and agent-tail-core wrap in each packageRead these files to determine the project setup:
package.json — check for framework dependencies (vite, next, react, etc.) and existing scriptsvite.config.ts / vite.config.js — Vite project indicatornext.config.ts / next.config.js / next.config.mjs — Next.js project indicatorturbo.json / nx.json / pnpm-workspace.yaml / lerna.json — monorepo indicators.gitignore — check if tmp/ is already ignoredClassify the project as one of:
Step 2: Gather user preferences
test cases passed, vs 7 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.