Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →loulanyue/search-first
Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.
Passed 18 of 22 test cases with the skill, and 16 of 22 without it.
3 fixed16 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
A developer asks to add a string truncation utility helper to our TypeScript repo. Before searching npm or writing truncateString(), what initial step should be taken inside the existing project codebase?
| Checked | Without skill | With skill |
|---|---|---|
| recommends searching the existing repository first | Passed | Passed |
| mentions using ripgrep to check for existing internal functions | Missed | Passed |
The instructions your model reads when the skill loads.
Systematizes the "search for existing solutions before implementing" workflow.
Use this skill when:
┌─────────────────────────────────────────────┐
│ 1. NEED ANALYSIS │
│ Define what functionality is needed │
│ Identify language/framework constraints │
├─────────────────────────────────────────────┤
│ 2. PARALLEL SEARCH (researcher agent) │
│ ┌──────────┐ ┌──────────┐ ┌──────────┐ │
│ │ npm / │ │ MCP / │ │ GitHub / │ │
│ │ PyPI │ │ Skills │ │ Web │ │
│ └──────────┘ └──────────┘ └──────────┘ │
├─────────────────────────────────────────────┤
│ 3. EVALUATE │
│ Score candidates (functionality, maint, │
│ community, docs, license, deps) │
├─────────────────────────────────────────────┤
│ 4. DECIDE │
│ ┌─────────┐ ┌──────────┐ ┌─────────┐ │
│ │ Adopt │ │ Extend │ │ Build │ │
│ │ as-is │ │ /Wrap │ │ Custom │ │
│ └─────────┘ └──────────┘ └─────────┘ │
├─────────────────────────────────────────────┤
│ 5. IMPLEMENT │
│ Install package / Configure MCP / │
│ Write minimal custom code │
└─────────────────────────────────────────────┘
test cases passed, vs 16 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.