菜单
Confidence/assumption hard-gate before /goal handoff. Outputs confidence 0-10, assumptions, unknowns. **Blocks /goal if confidence < 6.** Cheap (Opus, ~5 turns); catches false-confidence wrong turns.
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
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.
| name | introspect |
| description | Confidence/assumption hard-gate before /goal handoff. Outputs confidence 0-10, assumptions, unknowns. **Blocks /goal if confidence < 6.** Cheap (Opus, ~5 turns); catches false-confidence wrong turns. |
A hard-gate before autonomous /goal handoff. The fastest way to catch a wrong turn is to ask the model to introspect on its own plan before executing.
confidence: 0-10
assumptions:
- <thing treated as given>
- ...
unknowns:
- <thing the model doesn't know>
- ...
recommendation: proceed | clarify | research-more
Opus is generally calibrated on confidence. Forcing it to enumerate assumptions and unknowns surfaces the things that would make it fail mid-/goal. Cheaper to catch them here (5 turns Opus) than mid-/goal (50+ turns).
Auto-invoked by every umbrella between /spec(qa) and /goal. Manually invoke when you want a confidence check before a big autonomous run.