ワンクリックでManusで任意のスキルを実行

best-practice-research

スター3

フォーク0

更新日2026年5月13日 07:11

Use when the user asks for best practices, broader validation, GitHub/open-source comparison, official-doc verification, or warns against one-sided thinking. Also use before implementation when official API, framework, or project-pattern facts are needed to avoid rework.

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

cnw-L

cnw-L/agent-router

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

Best Practice Research Adapter

Research exists to reduce total delivery cost, not to collect sources.

Decision Research

Use before finalizing a plan. Prefer official docs, maintained GitHub repos, mature examples, security guidance, and benchmark/eval evidence. Summarize consensus, disagreements, applicability, and recommendation.

Implementation Research

Use after the plan is confirmed but before edits when code correctness depends on project patterns or external APIs. Prefer project-local same-pattern code, related tests, Context7 or official docs, and version notes.

Stop Rule

Stop once the evidence is enough to choose or implement a path. Do not keep researching after the marginal value is low.

このリポジトリの他の Skills

同じリポジトリ

code-review

cnw-L/agent-router

Use for review, PR review, audit, self-review, and regression-risk work. Prioritizes bugs, regressions, missing tests, architecture drift, redundancy, security risk, and verification gaps.

2026-05-133

codebase-impact

cnw-L/agent-router

Use before multi-file, unfamiliar, public-contract, or shared-behavior code changes to build a bounded impact set without reading the whole repository or editing from a single file view.

2026-05-133

coding-workflow

cnw-L/agent-router

Route non-trivial coding work across target-state implementation, codebase impact, Superpowers, Context7, security review, PR workflow, and verification. Skip for tiny edits or simple reads.

2026-05-133

critical-thinking

cnw-L/agent-router

Use before finalizing non-trivial design, architecture, configuration, or implementation decisions. Reduces sycophancy bias by independently evaluating proposals, surfacing risks, and presenting alternatives. Auto-triggers on design_or_config and complex_feature routes.

2026-05-133

decision-alignment

cnw-L/agent-router

Use before architecture, configuration, workflow, dependency, or high-impact implementation decisions to align goals, constraints, options, tradeoffs, recommendation, acceptance criteria, and user confirmation. Skip for tiny obvious tasks.

2026-05-133

implementation-quality

cnw-L/agent-router

Use for non-trivial code changes after the plan is confirmed. Enforces target-state implementation: minimal necessary scope, existing patterns, no avoidable MVP residue, no duplicate logic, synchronized callers/tests/types/errors/config, and verification.

2026-05-133

name	best-practice-research
description	Use when the user asks for best practices, broader validation, GitHub/open-source comparison, official-doc verification, or warns against one-sided thinking. Also use before implementation when official API, framework, or project-pattern facts are needed to avoid rework.

Best Practice Research Adapter

Research exists to reduce total delivery cost, not to collect sources.

Decision Research

Implementation Research

Stop Rule

Stop once the evidence is enough to choose or implement a path. Do not keep researching after the marginal value is low.