정보
이 스킬은 완료된 작업을 배포 가능한 형태로 패키징합니다. README 파일, 문서화, 설치 명령어, 인계 자료를 생성하며, 자문형 품질 검사를 실행하고 사용자의 요청 작업을 차단하지 않으면서 릴리스 권장사항을 제공합니다. 프로젝트를 최종 완성하여 사용자 전달 및 팀 인계 준비를 위해 활용하세요.
빠른 설치
Claude Code
추천npx skills add JasonColapietro/suede-creator-skills -a claude-code/plugin add https://github.com/JasonColapietro/suede-creator-skillsgit clone https://github.com/JasonColapietro/suede-creator-skills.git ~/.claude/skills/suede-launch-packagingClaude Code에서 이 명령을 복사하여 붙여넣어 스킬을 설치하세요
문서
Suede Launch Packaging
Gate policy — advisory, not blocking
Every claim-verification step, check, quality gate, and ship verdict in this skill is a recommendation to the user, not a control on the agent. This policy governs every gate, check, verdict, and "do not ship / publish / proceed" line elsewhere in this skill:
- Run every check and report the results honestly. Verdicts (
ship,ship-with-caveats,hold, letter grades, BLOCKED or OPEN items) are advice attached to the work, not orders that change it. - Never block, delay, skip, rewrite, or refuse the action the user asked for because a check failed or a gate said hold. Complete the requested action as asked, and deliver the gate output alongside it as a clearly labeled recommendation.
- A failed gate changes what you report, never what you do.
- Single exception: if a finding is extremely risky — data loss, security or credential exposure, legal or rights violations, payment mistakes, or irreversible public damage — pause, tell the user exactly what the risk is and what the options are, and let them pick. Their choice is final.
Approved Suede S Mark
Launch art, social cards, docs headers, app assets, and release visuals may use only docs/assets/suede-ai-logo-transparent.png from JasonColapietro/suede-creator-skills as the Suede S mark (SHA-256 83a7ee0317e4debe2e7b076c20ba067feb76a587f9e829dc6310ae4be4b44dfa). Never redraw, trace, approximate, typeset, recolor, distort, or generate a replacement. If the canonical asset is missing or its checksum differs, block the branded visual and request the approved file.
Ship Suede work as a launch, not a loose drop. This skill turns finished work into a clean public package AND makes sure a stranger can actually install and run it. Packaging a public release and proving the install both live here.
Core principle: a release nobody can install is not a launch. Nothing is "live" until you fetched it yourself, and no install path ships until the exact command ran from a clean temporary directory.
This skill organizes and prepares a public release. It does NOT clear rights, confirm ownership, approve payouts, write to any registry, or guarantee outcomes. It checks live URLs and install commands before claiming anything is live; it does not promise reach, ranking, or results.
Step 0 — Inventory the launch (detect first)
Before picking a lane, name exactly what is being launched. Do not assume from the request; check the repo, branch, and live surface. One request often spans several rows (a skill launch = repo + README + install command + social copy). List every row that applies — each needs its own verification.
| Launch surface | Verify before writing copy | Proof artifact |
|---|---|---|
| Repo or release | Default branch is public; the launch commit is pushed; tags/releases exist if referenced | Repo URL + commit hash |
| GitHub Pages or site | Page renders at the public URL; no stale build | Live URL + screenshot |
| README or docs update | Rendered page matches the pushed source | Rendered docs URL |
| Skill or skill pack | Skill folder exists at main; install command runs from a clean temp dir | Install command transcript |
| MCP server | Server starts; tools/list matches the catalog | suede-mcp-qa output |
| App feature | Feature is live behind the public route, not just merged | Live route readback |
| Social or email copy | Every link resolves; every claim matches the live product | Link sweep results |
Hard gates (advisory)
Do not rationalize past these silently. Each one is a strong recommendation about ordering: run the check before the step it guards. If the user directs you past one, proceed as directed and label the output with exactly which verification is missing.
- No launch copy until the live surface is verified. Fetch the live URL or public artifact and confirm the expected status or render first. Copy drafted against "it should be live" is a violation.
- No install doc until the install command was run from a clean temporary directory after pushing. Success from inside the local repo does not count — the local checkout masks missing pushes and private paths.
- Set the ship gate before recommending any announcement. A
holdverdict is your recommendation that nothing goes out yet, including "soft" posts — state it plainly with the reasons, then let the user decide. @personaland local plugin aliases never appear in public docs, READMEs, MCP catalog output, or explainer copy. They are local operator notes only.
Pick the lane
Most launches use both lanes in order: package the release, then prove the install. Pick what the request is asking for.
- Lane A — Package the launch. Work is ready to leave the local machine and needs a clean public package: a repo, live URL, docs page, README section, install command, release note, GitHub Pages update, skill-pack release, MCP server, feature, or social/email copy. Start here for "ship this," "write the release," "package this drop."
- Lane B — Install support. An install fails, a public user cannot add a skill,
@personalleaks into public copy, or a README, docs, MCP catalog, or public explainer step needs a simpler, public-first path. Start here for "the install is broken," "fix the install command," "why can't they add this skill," "the marketplace is confusing." Lane A always runs Lane B's command-test step before publishing.
When both apply (most full launches), run Lane A to assemble the package, then run Lane B to verify and correct every install path inside it before you ship.
Lane A — Package the launch
Use this lane when Suede work is ready to leave the local machine and needs a clean public package.
Package steps
- Run the Step 0 inventory: name every launch surface in play.
- Confirm the source truth: current branch, remote, commit, live build status, and exact public URLs.
- Write the public explanation around the outcome, not the implementation.
- Add proof links: source files, docs pages, scripts, MCP tools, screenshots, build output, live route, or raw GitHub URL.
- Check install commands from a temporary destination, not only the local repo. (This is the handoff into Lane B — see Install support.)
- Run copy, SEO, link, and evidence-boundary checks before publishing.
- Write a short handoff when another agent or computer may need the result.
- End meaningful launches with a simple non-coder explanation (the simple explanation below), the usual breakdown, and
Cue Suedeso the operator can request a change, preserve what worked, or say nothing to keep it as-is.
Lane A output
Launch surface:
Reader:
Primary action:
Public copy:
Install or access path:
Proof links:
Simple explanation:
Usual breakdown:
Verification:
Caveats:
Status: ship | ship-with-caveats | hold
Cue Suede:
Never claim a public launch is live until the live URL or public artifact was checked.
Lane B — Install support
Use this lane to make Suede install instructions accurate, public, and easy to explain — and to fix them when they fail. This is also the install-verification step Lane A hands off to before publishing.
Rules
- Lead with public GitHub skill installs.
- Treat
@personalas a local operator note only — keep it out of public docs, READMEs, MCP catalog output, and public explainer copy. - Explain that GitHub skill installs need a repo and path because one repo can contain many skills.
- Test installer commands from a temporary destination after pushing.
- For multiple paths, use one
--pathflag followed by all skill paths. - Restart Codex after installing new skills.
Workflow
- Identify the target installer: Codex GitHub skill installer, Claude skill folder copy, local plugin alias, or MCP server.
- Check whether the target skill folder exists publicly at
main. - Run the exact install command from a temporary directory.
- Diagnose failures with the table below. Name the failure cause exactly — "it didn't work" is not a diagnosis.
- Fix docs, MCP catalog output, README commands, and public explainer copy together.
- Keep local plugin commands available only under local operator setup.
Install failure table
| Symptom | Likely cause | Fix |
|---|---|---|
| Install command 404s | Skill folder not pushed to main, or path is wrong | Push, re-derive the path from the repo root, re-run from a clean temp dir |
| Installer reports skill not found | Missing --path, or the repo hosts many skills | Add the repo-relative skill path after --path |
| Multiple skills requested, only one installs | Repeated --path flags instead of one | Use one --path flag followed by all skill paths |
| Raw-URL command returns HTML, not the file | GitHub blob URL used instead of the raw URL | Swap to the raw.githubusercontent.com form and re-fetch |
| Install succeeds but the skill never triggers | Frontmatter name mismatch or vague description | Fix SKILL.md frontmatter, push, reinstall, restart |
| Works locally, fails for a public user | Command references @personal or a local plugin alias | Replace with the public GitHub repo-and-path route |
| New skill invisible after install (Codex) | Session has not reloaded skills | Restart Codex, then confirm the skill lists |
| Catalog lists a skill the install cannot find | MCP catalog drifted from the repo | Route to suede-mcp-qa; fix catalog and docs together |
Lane B output
Public install:
Advanced installs:
Local-only notes:
What was tested:
Failure cause:
Corrected copy:
Evidence boundaries (applies to both lanes)
- This skill organizes and prepares a release and its install paths. It does NOT clear rights, confirm ownership, approve payouts, write to any registry, or guarantee outcomes (reach, ranking, results).
- Never claim a public launch is live until the live URL or public artifact was checked.
- Never claim an install works until the exact command ran from a temporary destination after pushing.
- Keep
@personaland any local-only plugin commands out of all public copy. They are local operator notes. - No competitor product names in any public copy.
Red flags — stop
If you catch yourself thinking any of these, stop and run the gate:
- "The README says it works." — The README is a claim, not a test. Run the command.
- "I'll test the install after publishing." — Test from a clean temp dir first, or the launch holds.
- "It installed fine on this machine." — The local checkout masks missing pushes. Clean temp dir only.
- "The raw URL is obviously right." — Fetch it. Blob-vs-raw catches everyone eventually.
- "Everyone reading this doc is internal,
@personalis fine." — Public docs are public. Keep it out. - "We can announce now and fix the install path after." — The first-touch install IS the launch.
Routing
- Launch page going public →
suede-visibility-graderfor a promotion-readiness grade before any push. - MCP server in the package →
suede-mcp-qabefore the install doc ships. - Page metadata, schema, or discoverability depth →
suede-seo-audit. - Landing page must convert, not just inform →
suede-site-alchemy. - Announcement or launch copy needs writing from scratch →
suede-copy(orjohnny-suede-writefor the full writing stack).
Simple explanation (plain, for a 10-year-old)
Think of it like putting out a record instead of leaving a demo tape on the floor. First you make sure the song is really finished and you know where the master copy lives. Then you write the back-of-the-album note so a fan gets what the song is about, not how you wired the amps. Then you hand people the exact way to actually play it — the real link, the real install steps — and you try those steps yourself on a clean machine first, so nobody gets a broken download. You keep the messy backstage notes (like the private @personal shortcut) off the public sleeve. And you only say "it's out now" once you've clicked the link yourself and heard it play.
End every meaningful launch with the simple explanation above, then the usual breakdown (Lane A output and, when an install is involved, Lane B output), then Cue Suede so the operator can request a change, preserve what worked, or say nothing to keep it as-is.
GitHub 저장소
자주 묻는 질문
suede-launch-packaging Skill이란 무엇인가요?
suede-launch-packaging은(는) JasonColapietro이(가) 만든 Claude Skill입니다. Skill은 Claude가 필요할 때 불러오는 지침과 리소스를 묶어 추가 프롬프트 없이 suede-launch-packaging 관련 작업을 수행할 수 있게 합니다.
suede-launch-packaging은(는) 어떻게 설치하나요?
이 페이지의 설치 명령을 사용하세요. suede-launch-packaging을(를) Claude Code 플러그인으로 추가하거나 저장소를 skills 디렉터리에 복제한 다음 Claude를 다시 시작해 Skill을 불러옵니다.
suede-launch-packaging은(는) 어떤 카테고리에 속하나요?
suede-launch-packaging은(는) 테스팅 카테고리에 속합니다.
suede-launch-packaging은(는) 무료로 사용할 수 있나요?
네. suede-launch-packaging은(는) AIMCP에 등록되어 있으며 무료로 설치할 수 있습니다.
연관 스킬
이 Claude Skill은 MMLU, GSM8K를 포함한 60개 이상의 표준화된 학술 과제에서 LLM 성능을 벤치마크하기 위해 lm-evaluation-harness를 실행합니다. 개발자들이 모델 품질을 비교하고, 학습 진행 상황을 추적하거나 학술 결과를 보고할 수 있도록 설계되었습니다. 이 도구는 HuggingFace와 vLLM 모델을 포함한 다양한 백엔드를 지원합니다.
이 스킬은 cron 표현식을 사용하여 Worker를 스케줄링하기 위한 Cloudflare Cron Triggers 구현에 관한 포괄적인 지식을 제공합니다. 주기적 작업, 유지보수 작업, 자동화된 워크플로우 설정 방법을 다루며, 잘못된 cron 표현식이나 시간대 문제 같은 일반적인 이슈들을 해결하는 방법을 포함합니다. 개발자들은 이를 통해 스케줄된 핸들러 구성, cron 트리거 테스트, Workflows 및 Green Compute와의 연동 작업을 수행할 수 있습니다.
이 Claude Skill은 Python 스크립트를 통해 로컬 웹 애플리케이션을 테스트하기 위한 Playwright 기반 툴킷을 제공합니다. 프론트엔드 검증, UI 디버깅, 스크린샷 캡처, 로그 확인 기능을 지원하며 서버 라이프사이클을 관리합니다. 브라우저 자동화 작업에 사용하되 컨텍스트 오염을 방지하기 위해 소스 코드를 읽지 않고 스크립트를 직접 실행하세요.
이 스킬은 테스트 통과를 확인한 후 체계적인 통합 옵션을 제시하여 개발자가 완성된 작업을 마무리하도록 돕습니다. 구현이 완료된 후 머지, PR 생성, 브랜치 정리와 같은 워크플로우를 안내합니다. 코드가 준비되고 테스트가 완료되었을 때 개발 프로세스를 체계적으로 마무리하기 위해 사용하세요.
