code-review-and-quality
785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。
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.
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。
Review the Skillstore skill "planning-and-task-breakdown" from https://skillstore.io/skills/addyosmani-planning-and-task-breakdown.md and its manifest at https://skillstore.io/api/skills/addyosmani-planning-and-task-breakdown/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。
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。
「planning-and-task-breakdown」を使用しています。 Add email notifications when a user receives a comment.
期待される結果:
「planning-and-task-breakdown」を使用しています。 We need to add search with filters to an existing application.
期待される結果:
The plan separates indexing, the search API, one complete filtered user flow, and later performance work. Each task includes dependencies, acceptance criteria, verification, likely files, and a scope estimate.
All 28 static findings are false positives. The flagged backticks, paths, and checklist text are Markdown documentation examples, not executable commands, reconnaissance, or path traversal. No semantic security findings or prompt injection attempts were identified.
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。
https://skillstore.io/skills/addyosmani-planning-and-task-breakdown/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/addyosmani-planning-and-task-breakdown?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/addyosmani-planning-and-task-breakdown?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/addyosmani-planning-and-task-breakdown/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/addyosmani-planning-and-task-breakdown.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>addyosmani. (2026). planning-and-task-breakdown security audit report (audit version 2) [Author version unspecified]. Skillstore. https://skillstore.io/skills/addyosmani-planning-and-task-breakdown/audits/2@techreport{addyosmani-addyosmani-planning-and-task-breakdown-2026,
author = {addyosmani},
title = {planning-and-task-breakdown security audit report (audit version 2)},
institution = {Skillstore},
year = {2026},
number = {2},
url = {https://skillstore.io/skills/addyosmani-planning-and-task-breakdown/audits/2},
note = {Author version unspecified}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "planning-and-task-breakdown security audit report (audit version 2)"
version: "unspecified"
type: report
authors:
- name: "addyosmani"
date-released: "2026-09-19"
url: "https://skillstore.io/skills/addyosmani-planning-and-task-breakdown/audits/2"
identifiers:
- type: other
value: "skillstore:addyosmani-planning-and-task-breakdown:audit:2"
description: "Skillstore immutable audit report identifier"
Convert a feature brief into ordered tasks with dependencies, acceptance criteria, verification steps, and review checkpoints.
Break a large engineering request into focused vertical slices that an AI coding agent can implement and verify independently.
Identify parallel work, shared contracts, sequencing constraints, risks, and the task-list location for a multi-person project.
Break this request into ordered tasks. For each task, include a short description, acceptance criteria, verification step, dependency, and estimated scope: [paste request].
Analyze this specification and map the dependency graph. Then propose a bottom-up task order with one checkpoint after each major phase: [paste specification].
Use vertical slicing to plan this feature. Separate foundation work from complete user flows, identify likely files, define testable acceptance criteria, and flag tasks that are too large: [describe feature and repository context].
Audit the following implementation plan for missing dependencies, unclear acceptance criteria, oversized tasks, weak verification, unsafe parallelization, and missing checkpoints. Return a corrected ordered plan with open questions: [paste plan].
作成者
addyosmaniライセンス
MIT
Skillstore リビジョン
r2
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。
参照
5d5054f8a23586f9b500fece1cb613a9dffc787b
メンテナンスの新しさ
2026/9/19
利用状況
5 ダウンロード · 0 閲覧
ファイル構成
📄 SKILL.md
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。
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.
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.
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.
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.
Structure Better Context for Coding Agents
Coding agents lose accuracy when context is incomplete, stale, or excessive. This skill provides practical structures for focused sessions, durable rules, and reliable handoffs.
Convert Plans into Executable Tasks
作成者 getpaperclipai
Plans often fail when tasks lack owners, dependencies, or clear starting conditions. This skill turns accepted Paperclip plans into a verified task graph that supports focused and parallel execution.
ガイド付き計画で機能を設計する
作成者 notedit
機能アイデアには、明確な要件、トレードオフ、実装手順が不足していることがよくあります。このスキルは、構造化された対話を通じて、発見、設計検証、ドキュメント作成、タスク計画を支援します。
Track Long Tasks With a Portable State Ledger
作成者 glenskii
Long technical tasks lose decisions, evidence, and next actions across sessions. This skill maintains a concise Markdown state file with reviewed local evidence references.
Verify AI Deliverables with Evidence
作成者 jadeyingwah
AI work can appear complete before the result is opened, tested, or checked against the request. This skill adds staged planning, real-environment verification, and honest completion levels.
あらゆるタスクに適したAIツールを選択
作成者 0xDarkMatter
多数のスキルやエージェントから選択することで、技術作業が遅れる場合があります。このスキルは、簡潔なカタログと選択ルールを使用して、各タスクを目的に特化したツールに割り当てます。
本番環境向けLLMプロンプトを最適化
作成者 wshobson
LLMプロンプトは、指示、例、評価基準が不明確なために失敗することがよくあります。このスキルは、Claude、Codex、Claude Code、および同様のツールでプロンプトを改善するためのテンプレートとワークフローを提供します。