Claude skills exhibit inconsistent behavior across bots
billyjhowell · x · 2026-08-30
A user noted that custom Claude skills run with high fidelity in Claude Code, but when used in Codex or @bot, the execution becomes less rigid and more ad-hoc. This highlights a lack of behavioral consistency for the same skills across different agent environments.
More from coding & agent
- Ultra Rapid GPU Shader Dev via Self-Sustaining RL with Claude Code — Amazing-Seesaw-6197 · 2026-08-30
- Data expert builds a conversational ontology editor in one hour, entirely on his phone — juansequeda · 2026-08-30
- workweave/router: open-source model router cuts agentic costs 40-70% in <50ms — workweave · 2026-08-30
- Dev shares AGENTS.md + skills repo: worktrees, evidence-driven testing, Greptile loops — Rasmic · 2026-08-30
- RegexForge: Deterministic Regex Synthesis via MCP Without LLMs — modelcontextprotocol · 2026-08-30
- Salesforce MCP Server: Natural Language Interface for Salesforce Ops — modelcontextprotocol · 2026-08-30