メニュー
[UDS] Identify repeated processes and build Skills with the right development depth
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/AsiaOstrich/universal-dev-standards --skill skill-builderコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
SKILL.md を表示中
| name | skill-builder |
| scope | universal |
| description | [UDS] Identify repeated processes and build Skills with the right development depth |
| allowed-tools | Read, Glob, Grep, Write, Edit, Bash |
| argument-hint | [process description | 流程描述] |
Guides you from "I keep doing this manually" to a properly built Skill, with the right amount of process along the way.
A Skill records process knowledge. Memory records historical facts. When you notice yourself executing the same steps repeatedly, that's a Skill candidate.
New Skill needed?
├── Modifying existing Skill?
│ → Delta path: append ## MODIFIED / ## ADDED to existing SKILL.md
│ update version field → done
│
├── Answer these 4 questions (any "yes" → Complex):
│ 1. More than 7 steps?
│ 2. Branching logic between steps (if/else)?
│ 3. Requires knowledge from 3+ separate standards/decisions?
│ 4. Output directly affects sub-project source code?
│
├── All "no" → Simple path
│ → Fill Skill Brief (templates/SKILL-BRIEF-TEMPLATE.md)
│ → Create SKILL.md directly (no XSPEC needed)
│
└── Any "yes" → Complex path
→ Create XSPEC first → run /sdd
→ Return here after XSPEC Approved
Deprecating a Skill?
→ Add to SKILL.md frontmatter:
status: deprecated
deprecated_at: YYYY-MM-DD
deprecated_reason: "..."
superseded_by: "/new-skill" (if applicable)
→ Mark archived in SKILL-CANDIDATES.md
Before creating SKILL.md, decide where it belongs:
| Condition | Placement |
|---|---|
| Steps reference project-specific paths (e.g. TECH-RADAR.md, DEC-*.md) | Project: {project}/.claude/skills/ |
| Steps are universal (no project-specific paths) | UDS: skills/{name}/ + zh-TW locale |
Capture the repeated sequence:
Open your project's SKILL-CANDIDATES.md (copy from templates/SKILL-CANDIDATES.md if first time):
Answer the 4 judgment questions. Determine: Simple, Complex, or Delta.
Use templates/SKILL-BRIEF-TEMPLATE.md:
Run /sdd to create XSPEC. Return to Step 5 after XSPEC is Approved.
Identify which sections of the existing SKILL.md change.
Add ## MODIFIED Requirements or ## ADDED Requirements at the end.
Generate SKILL.md from the Brief or XSPEC:
name, scope, description, allowed-tools{project}/.claude/skills/{name}/SKILL.mdMark the candidate row: trigger ✅, Skill column filled.
feat(skills): Add /{skill-name} skill. 新增 /{skill-name} Skill。
{English description, 1-2 lines}
{Chinese description, 1-2 lines}
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
After completing all steps, verify:
SKILL-CANDIDATES.md updated (trigger ✅, Skill name filled)SKILL.md created with complete frontmatter (name/scope/description/allowed-tools)status: deprecated in frontmatterSOC 職業分類に基づく
[UDS] 以 Claude 原生 Agent tool 编排多任务执行计划（DAG-based，无外部引擎）。 Use when: executing a plan.json file with parallel/sequential task dependencies. Keywords: orchestrate, plan, execute, DAG, task plan, 编排, 执行计划, 并行.
[UDS] 从 Spec 文档、OpenSpec 变更或自由文本需求生成 plan.json。 Use when: converting specifications into executable task plans for /orchestrate. Keywords: plan, spec, task plan, 计划, 规格, 任务, plan.json, DAG.
[UDS] AI 辅助 git push 安全层：质量门禁 + 协作护栏。 Use when: pushing commits, force pushing, pushing to protected branches, pushing feature branches. Keywords: git push, force push, protected branch, quality gate, push receipt, PR automation, 推送, 保护分支, 质量门禁.