ワンクリックでManusで任意のスキルを実行

ask

スター1

フォーク2

更新日2026年6月9日 18:32

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>"`.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

waitdeadai

waitdeadai/claudemax

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

/ask — describe your goal, achieve it

The user-facing entry point. You describe what you want; the pipeline produces it.

CLI equivalent: cmax ask "<your goal>" — same engine as /cmax and cmax run.

What runs (auto, no flags)

Taste check — read taste.md + taste.vision if present. Suggest cmax taste init if absent and the repo has signal.
/deepresearch — web-current research with source ledger persisted to memory.research_sources. 2-bis. verify-research (default ON) — decomposed per-claim verification: parallel citation-support checks on cached excerpts, network escalation only on doubt, harness-owned timeouts (timeout = unverified, never pass). Contradicted findings stripped before decompose; failed briefs re-researched once.
multispec decompose — Fable 5 (while included →2026-06-22; Opus after) authors a MultiSpec: N sub-Specs + DAG + rollup completion conditions + per-sub-Spec writeSet.
/specqa (parallel per sub-Spec) — gate spec quality (every verifyHint mechanically checkable).
/introspect (parallel per sub-Spec) — confidence/assumption gate. Blocks at confidence < 6.
Mode selection — Mode A (SDK subagents in one query()) for ≤ 5 sub-Specs / short runs; Mode B (Claude Code Agent Teams with shared task list + worktree isolation) for big swarms or write-set overlap.
Parallel /goal per DAG leaf — Sonnet by default; Opus on router escalations (security, novelty, complexity ≥ 7).
Per-sub-Spec /verify (parallel, blind Opus) — re-reads repo, runs verifyHints.
Rollup /verify — blind Opus checks integration conditions across all sub-Spec outputs.
Memory record + state snapshot. ntfy.sh push to phone if NTFY_TOPIC is set.

Bundled dark-patterns hooks block vibes, fake citations, aggregator hallucination, and credential leaks throughout.

Variants (when you need to deviate)

/ask runs /opussonnet semantics by default (Opus plan/judge/verify + Sonnet exec). For other shapes, use the explicit skill:

/opusolo <goal> — all-Opus exec for novel/security/payments/auth (~3× cost, max effectiveness).
/cmax <goal> — same as /ask; the brand umbrella.
/workflow <goal> — v1 muscle-memory alias.
/opussonnet <goal> — explicit v1 muscle-memory invocation.

CLI overrides on cmax run:

cmax run "<goal>" --variant opusolo
cmax run "<goal>" --mode teams
cmax run "<goal>" --no-research
cmax overnight SPEC.md --budget-credits 50

When NOT to invoke /ask

Trivial one-line changes — just edit.
A single SPEC that fits in one /goal loop — invoke /goal directly on the existing SPEC.md.
Pure research with no implementation — invoke /deepresearch directly.

このリポジトリの他の Skills

同じリポジトリ

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

verify

waitdeadai/claudemax

Independent Opus supervisor pass that re-reads the repo blind and re-checks every SPEC completion condition. The source of truth for whether a run actually succeeded. Never skip.

2026-06-021

/ask — describe your goal, achieve it

The user-facing entry point. You describe what you want; the pipeline produces it.

CLI equivalent: cmax ask "<your goal>" — same engine as /cmax and cmax run.

What runs (auto, no flags)

Taste check — read taste.md + taste.vision if present. Suggest cmax taste init if absent and the repo has signal.

/deepresearch — web-current research with source ledger persisted to memory.research_sources. 2-bis. verify-research (default ON) — decomposed per-claim verification: parallel citation-support checks on cached excerpts, network escalation only on doubt, harness-owned timeouts (timeout = unverified, never pass). Contradicted findings stripped before decompose; failed briefs re-researched once.

multispec decompose — Fable 5 (while included →2026-06-22; Opus after) authors a MultiSpec: N sub-Specs + DAG + rollup completion conditions + per-sub-Spec writeSet.

/specqa (parallel per sub-Spec) — gate spec quality (every verifyHint mechanically checkable).

/introspect (parallel per sub-Spec) — confidence/assumption gate. Blocks at confidence < 6.

Mode selection — Mode A (SDK subagents in one query()) for ≤ 5 sub-Specs / short runs; Mode B (Claude Code Agent Teams with shared task list + worktree isolation) for big swarms or write-set overlap.

Parallel /goal per DAG leaf — Sonnet by default; Opus on router escalations (security, novelty, complexity ≥ 7).

Per-sub-Spec /verify (parallel, blind Opus) — re-reads repo, runs verifyHints.

Rollup /verify — blind Opus checks integration conditions across all sub-Spec outputs.

Memory record + state snapshot. ntfy.sh push to phone if NTFY_TOPIC is set.

Bundled dark-patterns hooks block vibes, fake citations, aggregator hallucination, and credential leaks throughout.

Variants (when you need to deviate)

/ask runs /opussonnet semantics by default (Opus plan/judge/verify + Sonnet exec). For other shapes, use the explicit skill:

/opusolo <goal> — all-Opus exec for novel/security/payments/auth (~3× cost, max effectiveness).

/cmax <goal> — same as /ask; the brand umbrella.

/workflow <goal> — v1 muscle-memory alias.

/opussonnet <goal> — explicit v1 muscle-memory invocation.

CLI overrides on cmax run:

cmax run "<goal>" --variant opusolo cmax run "<goal>" --mode teams cmax run "<goal>" --no-research cmax overnight SPEC.md --budget-credits 50

When NOT to invoke /ask

Trivial one-line changes — just edit.

A single SPEC that fits in one /goal loop — invoke /goal directly on the existing SPEC.md.

Pure research with no implementation — invoke /deepresearch directly.

name	ask
description	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>"`.