Marketplace

4 skills

Each listing spells out exactly what's inside — the steps, the ready-to-run code, and which AI tools it works with — so you know what you're getting before you buy.

Clear filters

Use when a repo's test suite is red and you must drive it to green by patching the code under test within a budget, without masking regressions.

  • 11-step procedure
  • Runnable Python included
  • 8-point quality checklist
code-qualityBest with a strong model (Claude Opus 5)·9 min read·Updated today

Audit code for race conditions, deadlocks, and thread safety issues in async and multi-threaded code.

  • 9-step procedure
  • 7 pitfalls to avoid
  • Installs into 6 tools
code-qualityBest with a strong model (Claude Sonnet 4)·4 min read·Updated today

Use when a failure's cause is unknown: a hypothesis-driven protocol from symptom to confirmed root cause, with evidence trail and regression test.

  • 9-step procedure
  • 1 ready-to-run code block
  • 10-point quality checklist
code-qualityBest with a strong model (Claude Sonnet 4)·7 min read·Updated today

Systematically modernize legacy codebases: strangler fig pattern, incremental rewrites, and risk-minimized migration paths.

  • 9-step procedure
  • 6 pitfalls to avoid
  • Installs into 6 tools
code-qualityBest with a strong model (Claude Sonnet 4)·3 min read·Updated today