一键在 Manus 中运行任何 Skill

investigate

星标1

分支2

更新时间2026年5月20日 21:02

Multi-source root-cause analysis for a specific bug or failure. Depth-first on one symptom. Use when something is broken and you need the actual cause, not a workaround.

安装

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。

在 Manus 中运行

来源

waitdeadai

waitdeadai/claudemax

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

/investigate — root-cause analysis

Depth-first on one symptom. The investigator's job is to find the actual cause, not patch the symptom.

Process

Reproduce the symptom (run the failing test, hit the failing endpoint, replay the failing input). If you can't reproduce, that's the first finding.
Inventory all code paths that touch the symptom.
Bisect via git, logs, or feature flags to localize the regression.
Hypothesize a cause; design a minimal test that would prove or disprove the hypothesis; run it.
Iterate until the hypothesis holds and the proof is mechanical.
Output: cause statement + evidence path + suggested fix shape (do NOT auto-apply; pass to /goal or /opussonnet for execution).

When to use

A specific test is failing or flaky.
A specific endpoint or page is broken.
A specific user-reported bug needs a definitive cause.

Distinct from

/audit — breadth-first across many holes. Investigate is depth-first on one.
/debug-hard task class — the router escalates debug-hard to Opus automatically; /investigate is the user-invokable skill.

同仓库更多 Skills

同仓库

ask

waitdeadai/claudemax

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>"`.

2026-06-091

cmax

waitdeadai/claudemax

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.

2026-06-091

opusolo

waitdeadai/claudemax

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.

2026-06-091

route

waitdeadai/claudemax

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.

2026-06-091

review

waitdeadai/claudemax

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).

2026-06-091

specqa

waitdeadai/claudemax

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.

2026-06-021

name	investigate
description	Multi-source root-cause analysis for a specific bug or failure. Depth-first on one symptom. Use when something is broken and you need the actual cause, not a workaround.

/investigate — root-cause analysis

Depth-first on one symptom. The investigator's job is to find the actual cause, not patch the symptom.

Process

Reproduce the symptom (run the failing test, hit the failing endpoint, replay the failing input). If you can't reproduce, that's the first finding.
Inventory all code paths that touch the symptom.
Bisect via git, logs, or feature flags to localize the regression.
Hypothesize a cause; design a minimal test that would prove or disprove the hypothesis; run it.
Iterate until the hypothesis holds and the proof is mechanical.
Output: cause statement + evidence path + suggested fix shape (do NOT auto-apply; pass to /goal or /opussonnet for execution).

When to use

A specific test is failing or flaky.
A specific endpoint or page is broken.
A specific user-reported bug needs a definitive cause.

Distinct from

/audit — breadth-first across many holes. Investigate is depth-first on one.
/debug-hard task class — the router escalates debug-hard to Opus automatically; /investigate is the user-invokable skill.