Skill Codex
Run a read-only capability preflight before adding, installing, comparing, replacing, upgrading, disabling, composing, or building for DeepSeek Harness. Use when a user asks whether DSH already supports something, which plugin fits, whether an option fits the current profile, what risks or duplicates exist, what…
Skill Codex
Design, install, run, and report deterministic DeepSeek Harness tool-failure experiments. Use when a user wants to prove retry or fallback behavior, timeout or cooperative cancellation, policy-denial handling, blocked-result recovery, Code Mode nested-call resilience, or CI evidence for a DSH agent/plugin. Complete…
Skill Claude CodeCodex
Use DeepSeek Harness's built-in tools and capabilities before installing third-party plugins or inventing shell/custom workarounds. Use whenever a task may be handled by native DSH files, search, shell, jobs, LSP, subagents, workflow, Ralph, goals, todo, web, sessions, planning, or other shipped capabilities; also use…
Skill Codex
A recovery guide for common DeepSeek Harness failures, such as missing commands, stale text, unavailable history, or failed installation. It examines the current error and applies a small, matching recovery step.
Skill Codex
Query the current AI mathematics frontier, audit solution claims and verification boundaries, find replay-ready opportunities, compare methods, or export a problem to Low-Hanging Fruit. Use for questions such as what AI solved recently, which claims are only candidates, which results are Lean- or expert-verified, what…
MCP server Claude CodeCodexCursor +2
MCP server "vibemath" as configured in cyanseek/VibeMath. Runs locally from the vibemath npm package.