📦

idea-refine

Name: idea-refine
Author: addyosmani

コンテンツリビジョン r1 安全 ⚙️ 外部コマンド

Refine Ideas Into Actionable Concepts

Vague ideas often hide weak assumptions and unclear priorities. This skill expands options, tests directions, and produces a focused one-page brief for action.

対応: Claude Codex Code(CC)

📊 76 十分

自分のエージェントでインストール

このリクエストをエージェントにコピーしてください。正規の Skill ページとマニフェストが含まれています。

エージェントリクエスト

Review the Skillstore skill "idea-refine" from https://skillstore.io/skills/addyosmani-idea-refine.md and its manifest at https://skillstore.io/api/skills/addyosmani-idea-refine/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

エージェントは引き続き計画を提示し、セキュリティポリシーで必要な確認を求める必要があります。

エージェントが読めるリソース

AI エージェント、クローラー、スクリプトがページ全体ではなく整理されたコンテキストを必要とする場合は、これらのリンクを使ってください。

Markdown詳細 GET /skills/addyosmani-idea-refine.md 署名済み manifest GET /api/skills/addyosmani-idea-refine/manifest 署名済み lockfile GET /api/skills/addyosmani-idea-refine/lockfile

テストする

「idea-refine」を使用しています。 Refine a tool that helps independent restaurants reduce delivery platform fees.

期待される結果:

Problem: Restaurants pay high fees to reach customers they already know.
Direction: Build a simple direct reordering service for repeat customers.
Core test: Measure whether regular customers switch to direct ordering.

「idea-refine」を使用しています。 Stress-test real-time collaboration for our block-based editor.

期待される結果:

Recommended MVP: Lock individual blocks while showing active collaborators.
Main assumption: Block-level editing satisfies customer expectations.
Not doing: Character-level merging, offline sync, or advanced presence features.

「idea-refine」を使用しています。 Improve weekly retrospectives that produce no completed actions.

期待される結果:

Experiment: Select one action with an owner and deadline.
Success measure: Review completion at the next retrospective.
Not doing: New tools, more meetings, or complex facilitation methods.

セキュリティ監査

安全

v1 • 2026/9/19 バージョン別レポートを開く

All 19 static findings are false positives caused by ordinary prose, Markdown backticks, code fences, or a benign shell shebang. The script only creates the fixed local directory docs/ideas, and the skill requires user confirmation before saving output.

スキャンされたファイル

648

解析済み行数

レビュー項目

誤検知を無視

リスク要因

⚙️ 外部コマンド (12)

scripts/idea-refine.sh:1 SKILL.md:20-23 SKILL.md:23-32 SKILL.md:32-54 SKILL.md:54-69 SKILL.md:69-82 SKILL.md:82 SKILL.md:84-97 SKILL.md:97-112 SKILL.md:112-136 SKILL.md:136-140 SKILL.md:140-156

最新の完了済み静的・セマンティック監査では、確認済みのセキュリティ検出事項は見つかりませんでした。これは、スキルに副作用がないことを証明するものではありません。

監査者: codex

このレポートを共有・引用

バージョン付き評価レポート、中立的なバッジ、埋め込みカード、引用を共有できます。Skillstore は証拠を報告しますが、この Skill が安全かどうかは判断しません。

バージョン別レポートを開く

レポートリンクをコピー

https://skillstore.io/skills/addyosmani-idea-refine/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdownバッジ

[![Skillstore security assessment](https://skillstore.io/badges/skills/addyosmani-idea-refine/security.svg)](https://skillstore.io/skills/addyosmani-idea-refine?utm_source=security_passport_badge)

HTMLバッジ

<a href="https://skillstore.io/skills/addyosmani-idea-refine?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/addyosmani-idea-refine/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

埋め込みカード

<iframe src="https://skillstore.io/embed/skills/addyosmani-idea-refine.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

学術引用 (APA · BibTeX · CFF)

APA形式の引用

addyosmani. (2026). idea-refine security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/addyosmani-idea-refine/audits/1

BibTeX形式の引用

@techreport{addyosmani-addyosmani-idea-refine-2026,
  author = {addyosmani},
  title = {idea-refine security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/addyosmani-idea-refine/audits/1},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "idea-refine security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "addyosmani"
date-released: "2026-09-19"
url: "https://skillstore.io/skills/addyosmani-idea-refine/audits/1"
identifiers:
  - type: other
    value: "skillstore:addyosmani-idea-refine:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore スコア

このスコアの理由証拠の信頼度: 中

アーキテクチャ

保守性

コンテンツ

コミュニティ

仕様準拠

作成できるもの

Shape an early product concept

Turn a broad concept into distinct directions, explicit assumptions, and a testable MVP.

Evaluate a feature proposal

Compare feature approaches against user value, technical constraints, and existing architecture.

Improve a team process

Reframe a recurring workflow problem and design a focused experiment with measurable results.

これらのプロンプトを試す

Clarify a rough idea

Help me refine this idea: [idea]. Identify the target user and desired outcome, then ask up to five questions.

Explore alternative directions

Expand [idea] into six distinct approaches. Explain the lens behind each approach and the specific user value.

Stress-test a preferred direction

Stress-test [direction] for [target user]. Compare value, feasibility, and differentiation, then identify dealbreaker assumptions and practical validation tests.

Refine within a codebase

Review [idea] against this codebase. Identify relevant architecture, compare three feasible directions, and draft an MVP brief after my selection.

ベストプラクティス

Provide a specific target user, desired outcome, and relevant constraints.
React to early variations before requesting a final recommendation.
Validate the riskiest assumption before expanding the MVP.

回避

Do not request many shallow ideas without evaluation criteria.
Do not select a direction before defining its target user.
Do not treat the generated brief as verified market evidence.

よくある質問

What input should I provide?

Provide the idea, target user, desired outcome, known constraints, and previous attempts.

Does the skill choose one direction?

It recommends a direction after you respond to alternatives and tradeoffs.

Can it work with an existing codebase?

Yes. It can inspect relevant project files and adapt options to existing architecture and patterns.

What does the final brief contain?

It contains a problem statement, recommendation, assumptions, MVP scope, exclusions, and open questions.

Does it save files automatically?

No. It asks for confirmation before saving a Markdown brief.

Does it replace user research?

No. It structures assumptions and validation plans, but real users and evidence must test them.

開発者情報

作成者

addyosmani

ライセンス

MIT

Skillstore リビジョン

バージョンに関する注意

作者はバージョンを宣言していません。

リポジトリ

https://github.com/addyosmani/agent-skills/tree/c004a74784a08295d52749b04cda634125b9a581/skills/idea-refine

参照

5d5054f8a23586f9b500fece1cb613a9dffc787b

メンテナンスの新しさ

2026/9/19

利用状況

0 ダウンロード · 0 閲覧

ファイル構成

📄 examples.md

📄 frameworks.md

📄 refinement-criteria.md

📁 scripts/

📄 idea-refine.sh

📄 SKILL.md

addyosmani のその他のスキル

すべて表示

📦

code-review-and-quality

5つの品質軸でコードをレビュー

コード変更には、正確性、セキュリティ、アーキテクチャ、可読性、パフォーマンスに関する問題が潜んでいる可能性があります。このスキルは、体系的なレビュープロセスを適用し、優先順位が明確で実行可能なフィードバックを提供します。

コーディング＆開発表示

📦

interview-me

Clarify User Intent Before You Build

Underspecified requests cause teams to build the wrong outcome and discover misalignment late. This skill runs a focused, one-question interview that turns ambiguity into confirmed intent.

コミュニケーション表示

📦

planning-and-task-breakdown

Plan Work Into Verifiable Tasks

Large or vague software work can hide dependencies, missing acceptance criteria, and verification gaps. This skill converts a specification into ordered task slices with checkpoints, scope guidance, and clear completion conditions.

生産性表示

📦

documentation-and-adrs

Document Decisions and Architecture Clearly

Teams lose context when important technical decisions remain in chat, code comments, or individual memory. This skill turns architectural reasoning, API guidance, project instructions, and release changes into structured documentation.

ドキュメント表示

📦

frontend-ui-engineering

Build Accessible, Production-Ready Frontends

Frontend work can become inconsistent, inaccessible, or difficult to maintain. This skill guides component architecture, responsive layouts, state handling, and polished user experiences.

デザイン＆クリエイティブ表示

📦

debugging-and-error-recovery

Debug Errors with a Root-Cause Workflow

Debugging failures by guesswork wastes time and can hide the real cause. This skill provides a repeatable process for reproducing, isolating, fixing, and verifying problems.

コーディング＆開発表示

すべて表示

📦