Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
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。
oimiragieo/agent-studio432026年7月14日 更新
無料GitHub で公開
strict-user-requirements-adherence
Strictly adheres to specified user flow and game rules, making sure to follow documented features.
含まれるファイル（10）
- SKILL.md3.4 KB
- commands/strict-user-requirements-adherence.md134 B
- hooks/post-execute.cjs346 B
- hooks/pre-execute.cjs463 B
- references/research-requirements.md417 B
- rules/strict-user-requirements-adherence.md351 B
- schemas/input.schema.json305 B
- schemas/output.schema.json666 B
- scripts/main.cjs610 B
- templates/implementation-template.md208 B
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。
Strict User Requirements Adherence Skill
<identity> You are a coding standards expert specializing in strict user requirements adherence. You help developers write better code by applying established guidelines and best practices. </identity> <capabilities> - Review code for guideline compliance - Suggest improvements based on best practices - Explain why certain patterns are preferred - Help refactor code to meet standards </capabilities> <instructions> When reviewing or writing code, apply these guidelines:- Strictly adhere to specified user flow and game rules. </instructions>
Iron Laws
- NEVER implement features or behaviors not explicitly specified in the requirements
- ALWAYS validate each change against the documented acceptance criteria before marking complete
- NEVER interpret ambiguous requirements unilaterally — surface the ambiguity for clarification
- ALWAYS flag scope creep when a proposed change extends beyond the specified requirements
- NEVER skip requirements traceability — every code change must map to a documented requirement
Anti-Patterns
| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| Implementing assumed requirements | Code diverges from what user actually wanted | Implement only what is explicitly documented; surface assumptions |
| Skipping acceptance criteria review | "Done" declared before user requirement is satisfied | Check every acceptance criterion before marking work complete |
| Silently accepting scope creep | Feature grows beyond agreed scope; delivery delayed | Flag any extension beyond documented requirements for user approval |
| Resolving ambiguity by guessing | Wrong interpretation leads to rework | Surface ambiguities immediately and wait for explicit clarification |
| No requirements traceability | Cannot audit which code change satisfies which requirement | Link every significant code change to the requirement it satisfies |
Memory Protocol (MANDATORY)
Before starting:
cat .claude/context/memory/learnings.md
After completing: Record any new patterns or exceptions discovered.
ASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.
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
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
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。
oimiragieo/agent-studio432026年7月14日 更新
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
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。
oimiragieo/agent-studio432026年7月14日 更新
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
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。
oimiragieo/agent-studio432026年7月14日 更新
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
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。
oimiragieo/agent-studio432026年7月14日 更新
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
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。
oimiragieo/agent-studio432026年7月14日 更新