This is the execution half of a two-step modernization pipeline. It takes the audit output from ln-645, which identifies custom modules that could be replaced with OSS packages, and does the actual swap with atomic keep/discard verification. For each candidate it installs the package, rewrites imports using the provided API mapping, runs tests, and either commits or fully reverts based on whether tests pass. The safety model is conservative: one module at a time, three consecutive failures stops the run, and LOW confidence candidates get skipped entirely. It's designed for managed coordinator runs but works standalone. Good for teams migrating legacy utility code to standard libraries without gambling on bulk replacements.

skills.sh installs
220
GitHub stars
591
last updated
Aug 21, 2026

Install

$ npx -y skills add levnikolaevich/claude-code-skills --skill ln-831-oss-replacer --agent claude-code

Installs into .claude/skills of the current project.

Files

This is the execution half of a two-step modernization pipeline. It takes the audit output from ln-645, which identifies custom modules that could be replaced with OSS packages, and does the actual swap with atomic keep/discard verification. For each candidate it installs the package, rewrites imports using the provided API mapping, runs tests, and either commits or fully reverts based on whether tests pass. The safety model is conservative: one module at a time, three consecutive failures stops the run, and LOW confidence candidates get skipped entirely. It's designed for managed coordinator runs but works standalone. Good for teams migrating legacy utility code to standard libraries without gambling on bulk replacements.

Browse the repository on GitHub

Sponsors

Details

Repository
github.com/levnikolaevich/claude-code-skills
Category
Testing & QA
First seen
Jun 3, 2026

More from levnikolaevich/claude-code-skills

All 128
1manic-trade avatarmanic-trading-benchmark-skillmanic-trade/manic-trading-benchmark-skillRun a standardized benchmark to evaluate AI trading agent capabilities on the Manic Trade platform. Use this skill when a user wants to benchmark their trading 220skills.sh installs
2sendaifun avatarsurfpoolsendaifun/skillsComplete Surfpool development environment for Solana - drop-in replacement for solana-test-validator with mainnet forking, cheatcodes, Infrastructure as Code, a220skills.sh installs
3guia-matthieu avatarlean-canvasguia-matthieu/clawfu-skillsDocument your business model on one page and systematically de-risk it. Master Ash Maurya's adaptation of Business Model Canvas optimized for startups and uncer218skills.sh installs
4travisjneuman avatarstatistics-verifiertravisjneuman/.claudeVerify statistics from raw data with methodology checking, significance testing, claim validation, and bias detection. Use when fact-checking statistical claims218skills.sh installs
5guia-matthieu avatarad-spend-optimizerguia-matthieu/clawfu-skillsAnalyze paid advertising performance across channels and recommend budget reallocation to maximize ROAS and minimize CAC. Use when: planning quarterly ad budget217skills.sh installs
6yonatangross avatarreview-pryonatangross/orchestkitPR review using parallel specialized agents for code quality, security, testing, architecture, and performance analysis. Synthesizes findings into a review repo217skills.sh installs