search-first

Solid

Research existing solutions before writing custom code

AI & Automation 17 stars 4 forks Updated today MIT

Install

View on GitHub

Quality Score: 86/100

Stars 20%
42
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Search First Mandatory research before writing any new code. Reuse beats reinvention. ## When to Use - Before implementing any new feature - Before writing a utility function - Before adding a new dependency - Before building infrastructure (CI, deploy, tooling) ## Procedure ### Step 1: GitHub Code Search ```bash # Search for existing implementations gh search repos "{feature keywords}" --limit 5 gh search code "{function signature or pattern}" --limit 10 ``` Look for: - Battle-tested implementations with stars and activity - Patterns that solve 80%+ of the problem - Forkable/portable code with compatible licenses ### Step 2: Package Registry Search Check the relevant registry: - **npm**: `npm search {keywords}` - **PyPI**: `pip index versions {package}` or web search - **crates.io**: `cargo search {keywords}` - **Go**: `pkg.go.dev` search Evaluate packages on: - Download count and trend - Last publish date (stale = risk) - Dependency count (fewer = better) - License compatibility ### Step 3: Library Documentation - Read official docs for candidate libraries - Check API matches the use case - Verify version compatibility with project ### Step 4: Decision Output one of: ``` REUSE: {package/repo} - {why it fits} ADAPT: {package/repo} - {what needs modification} BUILD: No suitable existing solution - {why} ``` ## Output Format ``` Search: {what was needed} GitHub: 3 repos found, 1 strong match - gi...

Details

Author
mshadmanrahman
Repository
mshadmanrahman/pm-pilot
Created
5 months ago
Last Updated
today
Language
TypeScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category