菜单
Auto-bootstrap project taste.md + taste.vision via /deepresearch. NO 10-question wizard. Reads repo signals + researches SOTA at current time → synthesizes taste docs with zero questions (one fallback question only if repo has no signal).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | taste |
| description | Auto-bootstrap project taste.md + taste.vision via /deepresearch. NO 10-question wizard. Reads repo signals + researches SOTA at current time → synthesizes taste docs with zero questions (one fallback question only if repo has no signal). |
Replaces v1's /tastebootstrap (10 kernel questions). v2 auto-derives taste from repo evidence + current-time SOTA research.
taste.md (operating principles, code style, architecture invariants, deps posture) + taste.vision (north star, ICP, success criteria) with zero questions.cmax taste init # auto-bootstrap; writes taste.md + taste.vision
cmax taste init --regenerate # ignore existing; re-derive from scratch
taste.md and injects it into every workflow's system prompt.Ask. Achieve. The canonical user-facing entry to claudemax — describe your goal, the SOTA-2026 pipeline (deepresearch → multispec → parallel /goal → verify) handles the rest. Same engine as /cmax with a friendlier verb. CLI equivalent is `cmax ask "<goal>"`.
The default FAT umbrella. Auto-runs deepresearch + multispec decomposition + parallel /goal + verify. Opus for planning/judgment/verification; Sonnet for sub-Spec execution (escalates per router). Multispec engine selects Mode A (SDK subagents) or Mode B (Claude Code Agent Teams) automatically based on work size. Your default daily-driver.
Max-effectiveness umbrella. Opus for EVERYTHING — planning, decomposition, sub-Spec /goal execution, verification. Use for novel domains, security/auth/payments, or when you want the highest ceiling regardless of cost.
Show the model-routing decision for a task (Fable/Opus/Sonnet/Haiku) with reasoning. Use before launching a packet to sanity-check the tier and to override when you have stronger judgment than the heuristic.
Reviews a proposed diff for correctness, security, style, taste alignment. Distinct from /audit (which reviews existing code, not diffs) and /verify (which checks SPEC completion).
Spec quality gate. Every completion condition must have a mechanically-checkable verifyHint (file path, command, test name, behavior). Blocks /goal handoff if the spec wouldn't be verifiable.