Refresh Coder Comparison — AI skill for Claude Code
Re-research the coder capability matrix — re-check benchmark boards, pricing, model rosters, safety evaluations, and each vendor's terms, then write the results back into select-coder's matrix.md — bu.
How to install Refresh Coder Comparison
Installs to ~/.claude/skills/bestdan-workflow-skills-refresh-coder-comparison/SKILL.md
mkdir -p ~/.claude/skills/bestdan-workflow-skills-refresh-coder-comparison && curl -fsSL https://raw.githubusercontent.com/bestdan/workflow-skills/HEAD/commands/refresh-coder-comparison.md -o ~/.claude/skills/bestdan-workflow-skills-refresh-coder-comparison/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Refresh Coder Comparison does
description: Re-research the coder capability matrix — re-check benchmark boards, pricing, model rosters, safety evaluations, and each vendor's terms, then write the results back into select-coder's matrix.md — bumping its cache date only on a full refresh in which every slice was actually checked. The occasional (~2-month) world-state refresh, distinct from /select-coder --refresh, which only re-probes which backends this machine can run allowed-tools: Bash, Glob, Grep, Read, Write, Edit, W
Alternatives in AI
- Qwen Code — A command-line AI workflow tool adapted from Gemini CLI, optimized for Qwen3-Coder models with enhanced parser 20.8k ★
- Rb Setup — First-time setup 1.3k ★
- Sast Skills — Collection of agent skills that turn your AI coder into a SAST scanner 620 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Select Coder
Recommend which coder agent and model should execute a coding task — probes locally available backends (opus,
Artificial Analysis Compare
LLM model comparison skill using Artificial Analysis API - benchmarks, pricing, and performance metrics
Moodtrip Hotel Search
Hotel search, comparison, reviews, pricing, and booking handoff via MoodTrip.ai MCP server. 12 tools including
Model Comparison
Local open-weight models (Qwen3.5-397B, MiniMax M2.5) vs cloud coding agents (Codex 5.3, Claude Code) on six w
Midjourney MCP
RunAPI Midjourney MCP server for image and video generation: create tasks, poll results, and check pricing acr
Persona Portability Benchmark
One persona, one frozen memory, N models: how much of an agent's character survives a model swap? Harness + bl
Related Agents
Lead Consistency
Cross-unit consistency pass and deduction-matrix arbitration for an audit-style evaluation run. Runs ONCE per
Skill
Professional finance research toolkit — backtesting (10 engines + benchmark comparison panel), factor analysis
Eval Auditor
Audits an evaluation setup (benchmark, A/B test, or model comparison) for methodology errors that would invali