- Home
- Skills
- Productivity
- Fleet Calibration
Fleet Calibration
Measure what a kanban worker fleet can accurately reproduce on a regular basis. Runs a ladder of task types (trivial → deep-build) throug...
Free
Works with the AI Agents you already use
About this skill
Measure what a kanban worker fleet can accurately reproduce on a regular basis. Runs a ladder of task types (trivial → deep-build) through the real gateway dispatch and scores each worker profile by whether it actually produced a verifiable artifact — catching the classic "faked done" failure (status=done but no output). Use when calibrating worker profiles, tuning a fleet, or proving a worker's reliability ceiling.
Measures what a Hermes Agent kanban worker fleet can accurately reproduce, on a repeatable basis. Instead of trusting a worker's self-reported "done", every calibration task must write a deterministic marker file into its workspace; the harness verifies the file bytes on disk — so a worker that claims success but produces nothing (faked completion) is caught and counted. Plus runtime per task, written to a CSV you can diff across runs to track fleet reliability over time.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed 18 days ago
- Free with an Agensi account
Permissions
File Scopes
Runs locally inside your agent environment. No third-party accounts required.