antonbabenko
UserAsk Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures the models' usefulness, too.
Categories
Indexed Skills (9)
architect
System design, tradeoffs, and complex technical decisions.
code-reviewer
Find bugs, security holes, and maintainability issues in a diff or file.
debugger
Rank root-cause hypotheses and propose the smallest safe fix.
deliberation
When and how to delegate to GPT, Gemini, Grok, and OpenRouter expert subagents via the deliberation MCP tools.
plan-reviewer
Validate that a work plan is executable before work starts.
researcher
Research external libraries, APIs, and best practices, with evidence.
scope-analyst
Catch ambiguities and hidden requirements before planning.
security-analyst
Threat-model and find vulnerabilities, with practical remediation.
code-intelligence
Use when navigating or refactoring code with a language server - choosing between semantic (LSP), exact-text (rg), and fuzzy/semantic search; anchoring LSP calls by position; gating degraded results; and disclosing tool substitutions, in any language.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.