evident-charts: open-source skill teaches coding agents to make honest charts and self-check
randal_olson · x · 2026-10-30
Randal Olson clarified two AA-PersonalityBench dimensions—transparency (truthful, admits uncertainty, flags assumptions) and informativeness (dense, evidence-based, actionable)—and released the companion open-source tool evident-charts (MIT license).
- Teaches coding agents like Claude Code, Codex, and Cursor to make clear, honest charts and critique each one before delivery
- Example fixes: raw counts on a log scale, EU total ranked among its own members, meaningless rainbow colors
- Distributed as an agent skill with Claude Code plugin, Codex plugin, and Gemini extension support
More from coding & agent
- Switch: open-source harness framework lets decision models like Jev drive agent loops — iamrobotbear · 2026-10-30
- Flashy UI memory systems won't survive: 2% retrieval failure is already fatal — StewartalsopIII · 2026-10-30
- Indie dev says Claude Opus 5.5 now reviews his AI game sound effects — TAbrodi · 2026-10-30
- Vercel's zeeg: We Now Spend Over $50k/Month on AI Security Review Tool Warden — zeeg · 2026-10-30
- Dev: An agent that automates expense reports in existing enterprise software beats another booking app — gethackteam · 2026-10-30
- Free scanner checks if AI agents can discover your MCP server — Stripe and GitLab score 68 — ElderElCapitan · 2026-10-30