문서, 테스트, 평가 및 썸네일 이미지를 포함한 완전하고 이식 가능한 Agent Skills를 생성하고 관리형 저장소에 등록합니다.
- GitHub 스타
- 18
- 파일
- 23
- 마지막 커밋
- 2026년 11월 12일
- 라이선스
- MIT
- 허용된 도구
- —
create-skill skill은 무엇을 하나요?
문서, 테스트, 평가 및 썸네일 이미지를 포함한 완전하고 이식 가능한 Agent Skills를 생성하고 관리형 저장소에 등록합니다.
skill의 SKILL.md에서 생성된 요약입니다.
create-skill skill 정보
표준화된 Agent capabilities를 구축하고 배포하려는 개발자는 이 도구를 사용하여 관리형 저장소 내에 완전하고 이식 가능한 SKILL을 스캐폴딩하고 등록할 수 있습니다. SKILL.md, README.md, 라이선스 파일 및 패키지 구성을 포함한 필수 파일 생성을 자동화하며, 결정론적인 테스트와 Vally 평가를 생성합니다. 이 워크플로우를 통해 모든 새로운 SKILL이 marketplace, 플러그인 또는 카탈로그와 같은 기존 등록 인터페이스에 적절히 통합되도록 보장합니다.
에이전트가 저장소에 새로운 기능을 추가해야 할 때, 이 SKILL을 로드하여 전체 파일 구조와 등록 프로세스를 계획합니다. 이 도구는 검색을 위해 skills-repo.config.json 파일을 사용하며, 실수로 인한 쓰기를 방지하기 위해 엄격한 dry-run 및 승인 메커니즘을 사용합니다. 코드 외에도 Azure OpenAI GPT Image 2 또는 OpenAI Images와 같은 프로바이더나 사용자 정의 전달 워크플로우를 통해 썸네일 이미지를 생성합니다. 이를 통해 모든 SKILL이 기능적으로 작동하고 테스트될 뿐만 아니라 저장소 카탈로그에서 시각적으로도 표현되도록 합니다.
agent가 수행할 수 있는 작업
- 1새로운 이식 가능한 SKILL 스캐폴딩단일 명령으로 필요한 모든 문서, 테스트 및 메타데이터를 포함한 완전한 SKILL 디렉토리를 생성합니다.
- 2SKILL 썸네일 이미지 생성AI 프로바이더 또는 사용자 정의 워크플로우를 사용하여 기존 SKILL에 대한 검증된 썸네일 이미지를 생성하거나 가져옵니다.
- 3기존 SKILL 등록로컬 파일을 덮어쓰지 않고 이전에 작성한 SKILL을 저장소의 등록 인터페이스에 추가합니다.
- 4JSON 피스처로부터 SKILL 생성비대화형 모드를 사용하여 제공된 JSON 입력으로부터 검증된 예시 SKILL을 결정론적으로 생성합니다.
skill의 SKILL.md를 기반으로 작성되었습니다. 모든 사용 사례는 해당 문서의 인용구와 대조 확인되었습니다.
create-skill skill 설치 방법
각 명령은 skill 폴더를 클라이언트의 skills 디렉터리에 복사합니다. 클라이언트를 재시작하거나 새 세션을 시작하여 로드하세요.플러그인에 create-skill skill 설치
/plugin marketplace add jongio/skills /plugin install jongio-skills@jongio-skills
Claude Code에 create-skill skill 설치
~/.claude/skills/create-skill/SKILL.md
$ npx degit jongio/skills/skills/create-skill ~/.claude/skills/create-skillClaude Code (project)에 create-skill skill 설치
.claude/skills/create-skill/SKILL.md
$ npx degit jongio/skills/skills/create-skill .claude/skills/create-skillCodex에 create-skill skill 설치
~/.agents/skills/create-skill/SKILL.md
$ npx degit jongio/skills/skills/create-skill ~/.agents/skills/create-skillGemini CLI에 create-skill skill 설치
~/.gemini/skills/create-skill/SKILL.md
$ npx degit jongio/skills/skills/create-skill ~/.gemini/skills/create-skillClaude.ai에 create-skill skill 설치
npx degit jongio/skills/skills/create-skill create-skill && zip -r create-skill.zip create-skill # claude.ai → Customize → Skills → + → Create skill → Upload a skill → create-skill.zip
자동 검사
2026년 11월 14일에 실행됨전체 보고서 →자동 검사를 통과했습니다. 보안 감사는 아닙니다. 에이전트가 실행하기 전에 스크립트를 읽어 보세요. 검사 방식 · 점수를 높이기 위해 수정할 항목
- 소스 저장소 연결 및 접근 가능jongio/skills/skills/create-skill is public and reachablegithub.com/jongio/skills/tree/HEAD/skills/create-skill ↗통과
- 오픈 소스 라이선스 (OSI)MITspdx.org/licenses/MIT.html ↗통과
- 최근 1년 내 커밋 또는 릴리스Last commit 2026-11-12github.com/jongio/skills/commits ↗통과
- 스크립트에 다운로드 후 실행이나 자격 증명 탈취가 없음5 of 9 scripts read; none of them downloads and runs code, the rest were not read결함 발견
- SKILL.md에 숨겨진 지침 없음No override phrases, safeguard switches, credential requests or hidden charactersgithub.com/jongio/skills/blob/HEAD/skills/create-skill/SKILL ↗통과
- 사전 허용 도구가 제한됨No pre-approved tools; the agent asks before using onegithub.com/jongio/skills/blob/HEAD/skills/create-skill/SKILL ↗통과
- SKILL.md가 Agent Skills 형식을 따름Valid name and description; says when to use it; 230 linesgithub.com/jongio/skills/blob/HEAD/skills/create-skill/SKILL ↗통과
SKILL.md
GitHub에서 보기[!CAUTION] Read and follow the shared safety rules before any action. Preview local writes and obtain explicit approval. Git and GitHub writes require their own approval and are outside this skill.
Create Skill
Create one complete skill and register every repository surface without guessing. The workflow plans first, fails closed on ambiguous conventions, and applies one approved change set.
Commands
| Command | Purpose |
|---|---|
create-skill <name> |
Create and register a new skill with deterministic placeholder art. |
create-skill art <name> |
Preview and create or ingest thumbnail art for an existing skill. |
create-skill register <name> |
Preview and register an existing complete skill without replacing its authored files. |
create-skill check <name> |
Validate the skill shape and thumbnail parity without writing. |
create-skill fixture --input <json> --repo-root <path> |
Deterministically create a validated fixture skill without interview prompts. |
Every mutating command starts with --dry-run. Apply the unchanged plan only after the user
approves its single-use hash.
Workflow
1. Resolve the request
Collect only missing values:
- Skill name in lowercase-dash form.
- A one-sentence summary.
- Specific
USE FORphrases that users will type. - Specific
DO NOT USE FORboundaries and the sibling workflow that should win. - Copyright holder, when repository conventions do not identify one.
- Art choice: Azure OpenAI GPT Image 2, OpenAI Images, custom workflow, or placeholder.
Search installed and repository skills for overlapping triggers before creation. If another skill already owns the same job, stop and propose extending it.
2. Discover the repository
Run from the target repository, not this installed skill directory.
- Prefer the nearest
skills-repo.config.json. - Validate managed identity and settings before deriving canonical repository paths.
- Without managed config, discover the existing populated
skills/directory and known registration surfaces. - Stop before any write when multiple skill roots or catalog surfaces are plausible.
See repository discovery for the exact contract.
3. Preview creation
Invoke this script by absolute path while keeping the target repository as the working directory:
node <skill-dir>/scripts/create-skill.mjs <name> \
--summary "<summary>" \
--use-for "<trigger phrases>" \
--do-not-use-for "<boundaries>" \
--author "<holder>" \
--dry-run
Show the complete JSON preview and approval token. The preview includes every skill file and every registration surface. Ask the user to approve that exact hash once.
4. Apply creation
Repeat the same command and replace --dry-run with --approve <hash>. Do not alter any input
between preview and apply. The tool rejects a stale hash, existing skill directory, symlinked
destination, missing locked Vally toolchain, ambiguous registration, or invalid PNG.
Creation includes:
SKILL.mdwithname,description, andmetadata.versionfrontmatter.README.md,LICENSE,package.json, andpackage-lock.json..vally.yaml, deterministic tests, andevals/<name>/eval.yaml.thumbnail.pngas the tracked source for catalog synchronization when a catalog is present.- Marketplace, plugin, README, eval workflow, Dependabot, and catalog registration when present.
- Prompt and non-secret provenance in
docs/thumbnail-prompts.mdwhen present.
5. Choose art
The initial placeholder is deliberate and deterministic. Replace it only when requested.
Built-in providers
Preview the exact action:
node <skill-dir>/scripts/create-skill.mjs art <name> \
--provider azure-openai \
--prompt "<exact prompt>" \
--dry-run
Supported choices:
azure-openai: Azure OpenAI GPT Image 2 at the exact configuredhttps://<resource>.openai.azure.comorigin.openai: OpenAI Images at the exacthttps://api.openai.comorigin.placeholder: deterministic local PNG with no network or billed call.
The placeholder and check commands run on bare Node. Before a network provider, run
npm ci --ignore-scripts in the installed create-skill directory so its locked SDKs are
available.
Show provider, exact endpoint, model, prompt, targets, billing status, one attempt, and no fallback.
Ask for approval of the single-use action hash. Then repeat with --approve <hash>.
Built-in requests disable redirects and SDK retries. Never retry automatically. Never switch providers after a timeout, redirect, rate limit, service error, invalid response, or rejected PNG. Report the failure and ask the user what to do.
Custom provider or delivery workflow
Ask: "Describe any provider and delivery workflow you want me to use for the thumbnail."
The answer is open-ended. It may name an API, MCP tool, browser flow, local application, uploaded attachment, shared storage location, human handoff, or another delivery mechanism. Never reduce the choice to a local command.
Convert the answer into an exact action preview containing:
- Provider and destination.
- Exact prompt and non-secret data sent.
- Exact tool calls, API origin, browser actions, or human handoff steps.
- Billing or external side effects.
- One attempt and no fallback.
- How the final PNG will arrive in the target repository workspace.
- The skill and catalog paths that will receive the validated bytes.
Show that preview and obtain explicit single-use approval before taking the custom action. Execute only the approved steps once. Never place credentials in the preview or provenance.
After delivery, save the result as a repository-relative regular file and ingest it:
node <skill-dir>/scripts/create-skill.mjs art <name> \
--provider custom \
--custom-description "<approved provider and delivery steps>" \
--custom-provider "<provider name>" \
--custom-model "<model or method>" \
--delivery "<delivery method>" \
--input "<repository-relative PNG>" \
--dry-run
Approve the displayed hash, then repeat with --approve <hash>. The CLI never executes a custom
command. It accepts the delivered PNG only after the same strict validation used for built-in art.
See art and provenance.
6. Validate
Run:
node <skill-dir>/scripts/create-skill.mjs check <name>
npm test
npm run eval:lint
Run vally lint <skill-dir>, skill-doctor, and registration parity checks when available in
the target repository. Do not run the full capability eval unless the user accepts
its agent usage.
7. Generate a deterministic fixture
Repository generators may create functional example skills through the stable fixture contract:
node <skill-dir>/scripts/create-skill.mjs fixture \
--input "<fixture.json>" \
--repo-root "<target-repository>" \
--dry-run
Parse the JSON preview, obtain or propagate approval for its hash, then repeat the unchanged
command with --approve <hash>. Fixture mode is always noninteractive. It accepts only the version
1 schema, deterministic built-in placeholder art, and the normal repository registration path.
It never bypasses dry-run, approval, validation, atomic writes, or provenance.
Read fixture mode for the exact payload and exit contract.
Repository generators use create-skill register create-skill --dry-run, followed by the
unchanged command with --approve <hash>, after catalog staging. This registers the bundled
authoring skill through the same atomic path without rewriting its skill files.
Safety
- Dry-run never writes files or calls an image provider.
- Approval binds the exact inputs and target paths. Changed inputs require a new preview.
- Provider requests make one attempt with no retry, redirect, or fallback.
- Custom workflows require an exact preview and approval before any external action.
- Provider output is untrusted until the complete PNG validator accepts it.
- The validated skill thumbnail is the tracked source; catalog builds generate public copies.
- Secrets never enter prompts, previews, logs, generated files, or provenance.
- Existing files are preserved when planning fails. Apply uses staged sibling files and rollback.
- No git staging, commit, push, issue, pull request, or repository setting change is part of this skill.
Exit Criteria
-
New skills declare
metadata.versionas a quoted SemVer string. Preserve existing skill versions during registration; use the repository's version helper to bump a release and synchronize plugin listings when available. -
The skill has every required file and only portable SKILL.md frontmatter keys.
-
Every discovered or configured registration surface includes the skill.
-
The tracked skill thumbnail passes strict PNG validation; catalog builds generate the public copy.
-
Prompt and non-secret provenance are recorded when that repository surface exists.
-
Deterministic tests and Vally lint pass.
-
The final report lists exact changed files, commands, results, and any blocked work.
이 스킬의 파일
23create-skill skill 질문
Claude Code에 create-skill skill을 어떻게 설치하나요?
npx degit jongio/skills/skills/create-skill ~/.claude/skills/create-skill를 실행합니다. Claude Code는 ~/.claude/skills(모든 프로젝트) 또는 .claude/skills(한 프로젝트)에서 skills를 로드하며, 설명이 작업과 일치할 때 skill을 사용합니다.
create-skill skill을 사용할 수 있는 클라이언트는 무엇인가요?
Agent Skills 형식을 읽는 모든 클라이언트(Claude Code, Codex, Gemini CLI, claude.ai(ZIP으로 업로드))가 사용할 수 있습니다. skill 내 스크립트는 클라이언트가 코드 실행을 허용하는 경우에만 실행됩니다.
이 SKILL이 커밋이나 푸시와 같은 Git 작업을 처리하나요?
아니요, 이 SKILL은 git staging, commit, push 또는 기타 저장소 설정 변경을 수행하지 않습니다.