Run iterative optimization loops for code and AI models.
npx skills add https://github.com/danielmiessler/LifeOS --skill optimize-danielmiessler
Please help me install this Agent Skill. Skill: Optimize Source: https://github.com/danielmiessler/LifeOS/tree/main/LifeOS/install/skills/Optimize Command: npx skills add https://github.com/danielmiessler/LifeOS --skill optimize-danielmiessler
This Skill automates the process of optimizing code and AI models, saving time and effort in the iterative improvement process.
Run the optimize skill to start an optimization loop for your target, using the following command:
/optimize --metric "lighthouse_score" --higher-is-better --measure "npx lighthouse http://localhost:3000 --output=json" --extract "jq '.categories.performance.score * 100' lighthouse.json" --files "src/**/*.tsx,src/**/*.css" --budget 120
High-intent search queries and answers about installing and using this skill.
You can automate code optimization by running an iterative loop that modifies target files, measures the result using a specified shell command, and repeats until improvements stop. This metric mode optimizes targets that produce a number, like bundle size or latency.
Yes, you can optimize AI prompts automatically using eval mode. This mode runs an iterative process that modifies prompts or agents and measures success using LLM-as-judge binary evaluations, repeating until no further improvements are found.
An autonomous optimization loop for AI models automatically modifies a target, measures the result against an evaluation metric, and repeats the process iteratively. It halts the loop when successive modifications no longer yield measurable improvements.
Yes, you need specific shell commands to measure success when optimizing code. The optimization loop requires a defined shell command to execute the target and a jq extraction command to pull the numerical metric from the output.
You can stop an automated optimization loop from running indefinitely by setting a budget parameter. The loop naturally terminates when iterative modifications no longer produce measurable improvements or when the defined budget is exhausted.
sakamoto-family-smileRun a bounded optimization loop to improve target operation performance.
lvzhengbinCreate and refine AI skills with SKILL.md files and evaluation loops.
ylxaiIteratively adjust code or AI models using metrics or LLM-as-judge evaluations.
InverterNetworkReview git diffs and apply safe refactors across code quality and architecture.