Optimize your skills and tiles: review SKILL.md quality, generate eval scenarios, run evals, compare across models, diagnose gaps, and re-run until scores improve.
88
94%
Does it follow best practices?
Impact
88%
1.07xAverage score across 24 eval scenarios
Passed
No known issues
A developer advocacy team maintains a library of SKILL.md files and wants to set up a repeatable process for improving them one at a time. Currently the team does this manually and inconsistently — some developers skip the review step, some apply changes without validating syntax, and no one compares scores before and after. The team lead wants to standardize the process with an automated script.
Create a shell script that automates the skill optimization workflow. The script should accept a path to a SKILL.md file and walk through the improvement process programmatically, capturing review output before and after changes, running validations, and producing a summary of the improvement.
Produce the following files:
optimize_skill.sh — the automation scriptREADME.md — brief usage instructions explaining how to run the script and what it does at each stepThe script does not need to make actual edits to the SKILL.md (it can leave that step as a placeholder or interactive step), but it should handle all the evaluation and validation steps programmatically.
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
scenario-19
scenario-20
scenario-21
scenario-22
scenario-23
scenario-24
skills
compare-skill-model-performance
optimize-skill-instructions
references
optimize-skill-performance
optimize-skill-performance-and-instructions