This skill covers configuring score boosting to prioritize relevant code paths and deprioritize tests, docs, and vendor code.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versiongrepai-search-boostingExecute the skills CLI command in your project's root directory to begin installation:
Fetches grepai-search-boosting from yoanbernabeu/grepai-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate grepai-search-boosting. Access via /grepai-search-boosting in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
16
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
16
stars
This skill covers configuring score boosting to prioritize relevant code paths and deprioritize tests, docs, and vendor code.
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.
# .grepai/config.yaml
search:
boost:
enabled: true
penalties:
- pattern: /tests/
factor: 0.5
bonuses:
- pattern: /src/
factor: 1.1
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
# Documentation
- pattern: /docs/
factor: 0.6
- pattern: /documentation/
factor: 0.6
# Vendor/third-party
- pattern: /vendor/
factor: 0.3
- pattern: /node_modules/
factor: 0.3
- pattern: /third_party/
factor: 0.3
# Generated code
- pattern: /generated/
factor: 0.4
- pattern: .gen.
factor: 0.4
- pattern: .pb.go
factor: 0.4
# Examples and samples
- pattern: /examples/
factor: 0.7
- pattern: /samples/
factor: 0.7
# Increase scores (factor > 1.0)
bonuses:
# Core source code
- pattern: /src/
factor: 1.1
- pattern: /lib/
factor: 1.1
- pattern: /app/
factor: 1.1
- pattern: /core/
factor: 1.2
- pattern: /internal/
factor: 1.1
# Important directories
- pattern: /services/
factor: 1.1
- pattern: /handlers/
factor: 1.1
- pattern: /controllers/
factor: 1.1
| Factor | Effect | Use Case |
|---|---|---|
| 0.3 | 70% reduction | Strong penalty (vendor) |
| 0.5 | 50% reduction | Moderate penalty (tests) |
| 0.7 | 30% reduction | Mild penalty (examples) |
| 1.0 | No change | Neutral |
| 1.1 | 10% increase | Mild boost (src) |
| 1.2 | 20% increase | Moderate boost (core) |
| 1.5 | 50% increase | Strong boost |
Patterns match against the full file path:
/project/src/auth/middleware.go
^^^^
Matches "/src/" pattern
| Pattern | Matches | Doesn't Match |
|---|---|---|
/tests/ |
src/tests/auth.go |
tests.go |
_test. |
auth_test.go |
test_auth.go |
.spec. |
auth.spec.ts |
spec/auth.ts |
/src/ |
project/src/main.go |
resource/file.go |
Score: 0.85 | tests/auth_test.go:10-30
Score: 0.82 | src/auth/middleware.go:15-45
Score: 0.80 | src/auth/jwt.go:23-55
penalties:
- pattern: /tests/
factor: 0.5
bonuses:
- pattern: /src/
factor: 1.1
Score: 0.90 | src/auth/middleware.go:15-45 (0.82 × 1.1)
Score: 0.88 | src/auth/jwt.go:23-55 (0.80 × 1.1)
Score: 0.43 | tests/auth_test.go:10-30 (0.85 × 0.5)
search:
boost:
enabled: true
penalties:
- pattern: /tests/
factor: 0.5
- pattern: _test.
factor: 0.5
- pattern: .spec.
factor: 0.5
- pattern: /vendor/
factor: 0.3
- pattern: /docs/
factor: 0.6
bonuses:
- pattern: /src/
factor: 1.1
- pattern: /lib/
factor: 1.1
search:
boost:
enabled: true
penalties:
- pattern: /__tests__/
factor: 0.5
- pattern: .test.
factor: 0.5
- pattern: .spec.
factor: 0.5
- pattern: /node_modules/
factor: 0.3
- pattern: .stories.
factor: 0.6
- pattern: /storybook/
factor: 0.6
bonuses:
- pattern: /src/
factor: 1.1
- pattern: /components/
factor: 1.1
- pattern: /hooks/
factor: 1.1
search:
boost:
enabled: true
penalties:
- pattern: _test.go
factor: 0.5
- pattern: _mock.go
factor: 0.5
- pattern: /testdata/
factor: 0.5
- pattern: /vendor/
Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
kostja94/marketing-skills
aaaaqwq/claude-code-skills
agentbay-ai/agentbay-skills
glebis/claude-skills
shopmeskills/mcp
wuchubuzai2018/expert-skills-hub
grepai-search-boosting is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
grepai-search-boosting is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
grepai-search-boosting reduced setup friction for our internal harness; good balance of opinion and flexibility.
Keeps context tight: grepai-search-boosting is the kind of skill you can hand to a new teammate without a long onboarding doc.
Registry listing for grepai-search-boosting matched our evaluation — installs cleanly and behaves as described in the markdown.
We added grepai-search-boosting from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
Useful defaults in grepai-search-boosting — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Keeps context tight: grepai-search-boosting is the kind of skill you can hand to a new teammate without a long onboarding doc.
Useful defaults in grepai-search-boosting — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
We added grepai-search-boosting from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
showing 1-10 of 65