three.js model, downloadable as OBJ or GLB
日本語の概要は準備中です。原文の説明を表示しています。
asgeirtj/system_prompts_leaks7万2026年10月12日 更新
無料GitHub で公開
requirements-clarification
Clarify a material user-owned product decision before substantive implementation commitments. Use only when request and named/governing evidence still leave a choice that would materially change scope, platform support, user-facing surface, data/API contract, domain values, project placement, or cross-system architecture; also use when a truncated request omits such a choice. On the initial turn, inspect only named or governing requirements evidence, then ask directly without loading: prefer structured input; ask one blocking outcome question or at most three coupled questions; wait. After the answer, load the body before write or delegation. Do not use for implement/build/fix/debug/refactor work when expected behavior is settled, plan/design deliverables owned by Plan, complexity/greenfield/integration alone, agent-owned technical choices, locally discoverable facts, reversible defaults, permission to begin, or stop/no-tool turns. Never re-ask supplied facts or turn clarification into refusal.
含まれるファイル（1）
- SKILL.md2.7 KB
SKILL.md（原文）
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Requirements Clarification
Resolve only a remaining user-owned product decision. Do not turn normal implementation uncertainty into a question.
- Read the request and any explicitly named or governing requirements source. Do not scan broadly for hypothetical ambiguity. If this evidence settles the outcome, proceed without asking.
- Separate user-owned outcomes and authoritative inputs from agent-owned implementation choices. Research discoverable facts yourself. Never ask the user to choose a library, framework, or method the agent can determine.
- If a narrow reversible default safely satisfies the request, state it and proceed. Complexity, greenfield status, file count, or integration work alone never requires clarification.
- Otherwise ask before substantive commitment. Reads, notes, or one small branch-neutral probe are allowed; a scaffold, public contract, embedded domain values, or cross-system architecture is a commitment.
- Prefer
request_user_inputwhen available. Ask one blocking outcome question; group at most three tightly coupled questions. Offer concrete outcome options and a recommendation. Never ask merely for permission to begin. - After the answer, do not ask again unless later evidence reveals a distinct material fork. Apply the answer and continue.
plan owns standalone plan and design deliverables. This skill does not create
an approval gate or stop a specified implementation merely because planning
would be useful. Never re-ask facts already supplied by the request or governing
evidence, and never turn clarification into a refusal.
レビュー
まだレビューはありません。使ってみた感想をお寄せください。
同じリポジトリのスキル
概要と使いどころ
Manage your private to-do list for the user. Use to add or update tasks, record what they are waiting on, track blockers, mark tasks complete or canceled, and clean up the list. Not for Dreamers or external task trackers.
日本語の概要は準備中です。原文の説明を表示しています。
asgeirtj/system_prompts_leaks7万2026年10月12日 更新
agents
無料Run a goal as a project: you coordinate. Use for "agents <task>", "take this to done", "work on this in parallel", "what are my threads doing", "pick up <slug>", "resume <slug>", "keep going until it is merged". Under `/agents` you do the work yourself unless it needs several lanes or a long wait — you judge; the plan line says why. No target you could verify (a file, API, number or measure) → the grill interview first, not threads. Read this skill before proposing anything for `/agents`: without it a proposal is in-session subagents.
日本語の概要は準備中です。原文の説明を表示しています。
asgeirtj/system_prompts_leaks7万2026年10月12日 更新
Timeline-based motion design
日本語の概要は準備中です。原文の説明を表示しています。
asgeirtj/system_prompts_leaks7万2026年10月12日 更新
The user's synced Apple Health (HealthKit) data: daily metrics (steps, distance, calories, heart rate, HRV, VO2max), sleep sessions (stages, quality, efficiency), and workouts.
日本語の概要は準備中です。原文の説明を表示しています。
asgeirtj/system_prompts_leaks7万2026年10月12日 更新
Create, read, edit, or manipulate Word documents (.docx) and Word templates (.dotx). Use whenever a build task's artifact kind is document with the default docx output, or the task mentions a Word doc, .docx, or .dotx, extracts or reorganizes content from one, inserts or replaces images, does find-and-replace in one, or works with tracked changes (redlines) or comments. Covers python-docx generation, raw OOXML editing of existing files, document structure and formatting, and render verification. Not for PDFs, spreadsheets, or Google Docs.
日本語の概要は準備中です。原文の説明を表示しています。
asgeirtj/system_prompts_leaks7万2026年10月12日 更新