confirm-intent
Verifies understanding of change requests to align expectations before coding.
Install
mkdir -p .claude/skills/confirm-intent && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13120" && unzip -o skill.zip -d .claude/skills/confirm-intent && rm skill.zipInstalls to .claude/skills/confirm-intent
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
変更要望の意図を粗く確認する。詳細な要件定義の前段として使う。コード変更はしない。Key capabilities
- →Read change requests and surrounding information
- →Survey relevant existing code and documentation
- →Summarize the change request in own words
- →Detect discrepancies or multiple interpretations
- →Ask clarifying questions about ambiguous points
How it works
The skill reads the change request and codebase, summarizes its understanding, identifies ambiguities, and asks targeted questions to confirm intent.
Inputs & outputs
When to use confirm-intent
- →Clarifying feature requests
- →Identifying ambiguous requirements
- →Early-stage scope validation
About this skill
要望確認
変更要望を受け取り、意図を正しく理解しているか粗く確認する。 重い仕様書は書かない。認識のズレを早期に潰すことが目的。 コード変更は行わない。
処理フロー
- 要望把握: 与えられた変更要望や、Issue / PR などの周辺情報を読む
- コードベース調査: 関連する既存コード、ドキュメントをざっと確認し、要望が現状のどこに影響するかを把握する
- 理解の要約: 要望を自分の言葉で短く言い換える
- ズレの検出: 要望の中で複数の解釈ができる点、前提が食い違いそうな点を洗い出す
- 確認: ズレがありそうな点だけ質問する。ズレがなければ要約だけ提示する
質問の原則
- read-only。コードベースの調査のみ行い変更しない
- 短く済ませる。仕様書を書き始めない
- repo を見れば分かる質問はしない。先に調べる
- 自明なことは確認しない。解釈が割れそうな点だけ聞く
- 各質問になぜ聞くのか、選択肢、選択肢記号、推奨を付け、答えやすくする
- 可逆で低リスクな曖昧さは推奨デフォルトを採用し、仮定として明記する。質問しない
確認すべき観点
以下の観点で認識のズレがないか確認する。全て質問する必要はなく、解釈が割れそうな観点のみ質問する。
- 背景と目的
- 利用者
- 対象範囲と対象外
- 制約
- 既存との互換性
出力形式
以下の形式で報告する。
## 要望確認
### 理解した内容
要望を自分の言葉で箇条書きにする。
### 確認事項
解釈が割れそうな点を質問する。該当なしなら「なし」と書く。
### 未確定事項
この段階では判断できない事項を記載する。該当なしなら「なし」と書く。
文章規範
- 必ず文章を書く直前に
japanese-tech-writingスキルを実行する
When not to use it
- →When the user wants code changes
- →When the user wants a heavy specification document
- →When the user wants to ask questions discoverable by looking at the repo
Limitations
- →The skill does not perform code changes
- →The skill does not write heavy specification documents
- →The skill only asks questions about points where interpretation might differ
How it compares
This skill focuses on early-stage intent confirmation through targeted questioning and summarization without writing heavy specifications or code, unlike direct implementation or detailed documentation.
Compared to similar skills
confirm-intent side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| confirm-intent (this skill) | 0 | 1mo | No flags | Beginner |
| marketing-psychology | 12 | 6mo | No flags | Intermediate |
| ai-prompting | 1 | 7mo | No flags | Beginner |
| it-role-expert | 0 | 5mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
marketing-psychology
davila7
When the user wants to apply psychological principles, mental models, or behavioral science to marketing. Also use when the user mentions 'psychology,' 'mental models,' 'cognitive bias,' 'persuasion,' 'behavioral science,' 'why people buy,' 'decision-making,' or 'consumer behavior.' This skill provides 70+ mental models organized for marketing application.
ai-prompting
jasonkneen
Effective communication strategies for AI-assisted development. Learn context-first prompting, phased interactions, iterative refinement, and validation techniques to get better results from Claude and other AI coding assistants.
it-role-expert
krafton-ai
Provides role-specific expertise for 26+ IT company positions. Use when responding from a specific role's perspective, providing role-based advice, or when specialized knowledge is needed for engineering, product, design, data, marketing, sales, operations, HR, legal, finance, leadership, or academic functions.
meeting-insights-analyzer
ComposioHQ
Analyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback. Identifies when you avoid conflict, use filler words, dominate conversations, or miss opportunities to listen. Perfect for professionals seeking to improve their communication and leadership skills.
sleap-support
talmolab
Handle SLEAP GitHub support workflow for issues and discussions. Use when the user says "support", provides a GitHub issue/discussion number like "#2512", or asks to investigate a user report from talmolab/sleap. Scaffolds investigation folders, downloads posts with images, analyzes problems, and drafts friendly responses.
difficult-workplace-conversations
davila7
Structured approach to workplace conflicts, performance discussions, and challenging feedback using preparation-delivery-followup framework. Use when preparing for tough conversations, addressing conflicts, giving critical feedback, or navigating sensitive workplace discussions.