Grepai Search Boosting

This configures search result boosting in GrepAI so you can push production code to the top and bury tests, docs, and vendor files in rankings. You set penalty factors (like 0.5 for tests, 0.3 for node_modules) and bonus factors (1.1 for /src/, 1.2 for /core/) in a YAML config. The math is simple: a 0.85 score on a test file becomes 0.425 with a 0.5 penalty, so actual source code ranks higher even if the raw match is slightly worse. The prebuilt configs for Go, Python, and frontend projects are solid starting points. It's the difference between hunting through test files every search and actually finding the implementation you need first try.

skills.sh installs: 778
GitHub stars: 20
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add yoanbernabeu/grepai-skills --skill grepai-search-boosting --agent claude-code

Installs into .claude/skills of the current project.

Files

GrepAI Search Boosting

This skill covers configuring score boosting to prioritize relevant code paths and deprioritize tests, docs, and vendor code.

When to Use This Skill

Prioritizing source code over tests
Penalizing vendor/third-party code
Boosting important directories
Customizing result ranking

What is Boosting?

Boosting modifies search scores based on file paths:

Original score: 0.85 (src/auth.go)
Bonus (+10%):   0.935

Original score: 0.85 (tests/auth_test.go)
Penalty (-50%): 0.425

This ensures production code ranks higher than tests with similar content.

Configuration

Basic Configuration

# .grepai/config.yaml
search:
  boost:
    enabled: true
    penalties:
      - pattern: /tests/
        factor: 0.5
    bonuses:
      - pattern: /src/
        factor: 1.1

Full Configuration

search:
  boost:
    enabled: true

    # Reduce scores (factor < 1.0)
    penalties:
      # Test files
      - pattern: /tests/
        factor: 0.5
      - pattern: /__tests__/
        factor: 0.5
      - pattern: _test.
        factor: 0.5
      - pattern: .spec.
        factor: 0.5
      - pattern: .test.
        factor: 0.5

SKILL.md on GitHub