/

/overnight-optimization

by erKamerkamyaman/dhh-p-bloom-agent-skills1 stars

Use when you want an AI agent to improve performance, size or startup time of a project over a long unattended run, with tests as a safety gate.

2 files
2.2 KB
Updated 11 hours ago
GitHub

Ask your Agent

Use this Skill: https://skilld.dev/gh/erkamyaman/dhh-p-bloom-agent-skills/overnight-optimization

This session only. Nothing lands on disk.

referencesrun-log.md

550 B raw

≈138 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Run log format

## Baseline
- metric: <name>, value: <number>, measured with: <command>

## Attempts
| # | Change | Tests | Before | After | Decision |
|---|---|---|---|---|---|
| 1 | Lazy-load charts module | pass | 1.8 MB | 1.5 MB | keep |
| 2 | Replace date library | fail | 1.5 MB | 1.3 MB | revert |

## Summary
- final value: <number>
- changes kept: <count>

Rules for the agent: never edit or delete tests to make them pass, never skip the benchmark, and stop after a fixed number of attempts or when the target is reached.

Source: SKILL.md on GitHub

Third-party checks

No third-party reports yet.

Provenance

Signed by skilld at 57c6daa. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 5 hours ago.

Activeupdated 11 hours ago

/overnight-optimization