メニュー
Interactive skill creation workflow for project-local skills. Triggers: skill-create, create skill
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/popup-studio-ai/bkit-claude-code --skill skill-create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-create |
| classification | workflow |
| classification-reason | Interactive skill creation workflow with user prompts, file generation, and eval scaffolding. Multi-step process requiring user decisions. |
| deprecation-risk | none |
| effort | low |
| description | Interactive skill creation workflow for project-local skills. Triggers: skill-create, create skill |
| argument-hint | /skill-create [name] | /skill-create from-btw {btw-id} |
| user-invocable | true |
| allowed-tools | ["Read","Write","Edit","Glob","Grep","Bash"] |
프로젝트 컨텍스트를 분석하여 project-local 스킬을 생성하는 워크플로우.
If /skill-create (no args):
If /skill-create {name}:
If /skill-create from-btw {btw-id}:
.bkit/btw-suggestions.jsonCLAUDE.md for project conventionsCreate .claude/skills/project/{name}/SKILL.md with:
---
name: {name}
classification: {workflow|capability}
classification-reason: "{reason based on analysis}"
deprecation-risk: none
effort: low
description: |
{Generated description}
Triggers: {trigger commands}
Keywords: {keywords in Korean and English}
argument-hint: "{usage hint}"
user-invocable: true
allowed-tools:
- Read
Body content includes:
Create evals/{name}/ directory with:
evals/{name}/
eval.yaml - Test configuration
prompt.txt - Test prompt
expected.txt - Expected behavior description
eval.yaml format:
name: "{name} skill eval"
skill: ".claude/skills/project/{name}/SKILL.md"
tests:
- name: "basic trigger"
prompt: "{trigger command}"
expected:
- "{expected behavior 1}"
- "{expected behavior 2}"
- name: "edge case"
prompt: "{edge case prompt}"
expected:
- "{expected behavior}"
/{name} or review at .claude/skills/project/{name}/SKILL.md"All generated skills go to: .claude/skills/project/{name}/SKILL.md
This location:
| Pattern | Example | Use When |
|---|---|---|
{project}-{domain} | hunikflow-model | Domain-specific capability |
{action}-{target} | validate-entity | Action-oriented workflow |
{tool}-{purpose} | proxy-guide | Tool/pattern guide |
When creating from a /btw suggestion:
context.file to understand what code was being worked oncontext.feature to understand the PDCA feature contextpromotedTo field with the new skill namebkend.ai authentication — email/social login, JWT tokens, RBAC, session management. Triggers: bkend auth, bkend login, bkend signup, bkend JWT, bkend RBAC
bkend.ai project tutorials (todo to SaaS) and common error troubleshooting. Triggers: bkend tutorial, bkend cookbook, bkend troubleshooting
bkend.ai database — CRUD, column types, filtering, sorting, relations, indexing. Triggers: bkend table, bkend CRUD, bkend column, bkend relation, bkend data