Skills and MCP tagged “benchmarks”

golang-testing affaan-m skill A skill that gives your agent Go testing patterns: table-driven cases, subtests, benchmarks, fuzzing and coverage. Useful when you write tests and want idiomatic Go. Claude Code CX Codex Cursor +1 5,000installs harness-creator walkinglabs skill Builds, audits, and fixes scaffolding for coding agents. It generates agent instructions, state files, and verification gates to stop task drift. Claude Code CX Codex Cursor +1 2,300installs evaluation-methodology Seth Hobson skill Reference guide for the PluginEval quality framework. Explains scoring formulas, anti-pattern penalties, and multi-layer checks for agent skills. Claude Code CX Codex Cursor 7,200installs checkpoint-promotion Seth Hobson skill Gates a trained checkpoint before release by checking data quality, capability drift, forgetting, and paired results against the base model. Claude Code CX Codex Cursor 2,600installs social-media-analyzer Alireza Rezvani skill Analyzes social media campaign performance, computes engagement rates, and calculates marketing ROI. Compares post metrics against benchmarks across Instagram, TikTok, LinkedIn, and Facebook. Claude Code 1,558installs