원클릭으로 Manus에서 모든 스킬 실행

request-artifacts

스타2

포크0

업데이트2026년 6월 18일 19:05

Request and iteratively publish shareable Claude Code artifacts (live, interactive pages) built from full session context.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

uygnoey

uygnoey/skills-from-claude-blog

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Instructions

Use this skill to turn an in-progress Claude Code session into a live, shareable artifact (an interactive web page) that updates as you work.

When you invoke this skill, follow these steps:

Ask what the artifact is for (PR walkthrough, incident investigation, dashboard, release checklist, architecture explainer) and who will read it.
Propose a page outline (sections and key visuals) that can be kept up-to-date as new findings arrive.
Build and publish the artifact, then republish as the session progresses so the same link stays current.
Ensure the artifact references the session context it was built from (codebase, diffs, connector data, and reasoning from the session) and includes links back to relevant code where possible.
Keep sensitive details private; artifacts are shareable only within the organization and cannot be made public.

Examples

Incident timeline artifact (live updates)
- Prompt: “Turn this incident into an artifact — timeline, suspect commits, error spike from our monitoring — and republish as I work through it.”
PR walkthrough artifact
- Prompt: “Make an artifact walking through this PR — the diff, the reasoning, and what I tested.”
License audit artifact
- Prompt: “Build an artifact listing every third-party dependency and its license, flagging anything copyleft.”

See: examples/role-prompts.md

이 저장소의 다른 Skills

같은 저장소

loops-playbook

uygnoey/skills-from-claude-blog

Choose the simplest loop primitive (turn-based, /goal, /loop, /schedule) and make success criteria explicit and verifiable.

2026-06-302

verify-frontend-change

uygnoey/skills-from-claude-blog

Verify any UI change end-to-end before declaring it done.

2026-06-302

apps-gateway-rollout

uygnoey/skills-from-claude-blog

Plan and roll out Claude Code via a self-hosted apps gateway, using centralized SSO login, managed settings enforcement, and per-user usage attribution when running on Amazon Bedrock or Google Cloud.

2026-06-292

foundry-azure-deployment-choice

uygnoey/skills-from-claude-blog

Decide whether to run Claude via Microsoft Foundry hosted on Azure or hosted on Anthropic, based on Azure-native requirements vs. needing full API feature/model availability.

2026-06-292

human-agent-teams-playbook

uygnoey/skills-from-claude-blog

A practical playbook for designing and operating effective human–agent teams: working in public, defining roles and tools, setting a north star, and building trust through verification and gradual autonomy.

2026-06-242

agent-identity-access-model

uygnoey/skills-from-claude-blog

Configure and roll out workspace-owned “agent identities” for team-wide AI agents with least privilege, strong boundaries, and reliable auditing.

2026-06-232

name	request-artifacts
description	Request and iteratively publish shareable Claude Code artifacts (live, interactive pages) built from full session context.

Instructions

Use this skill to turn an in-progress Claude Code session into a live, shareable artifact (an interactive web page) that updates as you work.

When you invoke this skill, follow these steps:

Ask what the artifact is for (PR walkthrough, incident investigation, dashboard, release checklist, architecture explainer) and who will read it.
Propose a page outline (sections and key visuals) that can be kept up-to-date as new findings arrive.
Build and publish the artifact, then republish as the session progresses so the same link stays current.
Ensure the artifact references the session context it was built from (codebase, diffs, connector data, and reasoning from the session) and includes links back to relevant code where possible.
Keep sensitive details private; artifacts are shareable only within the organization and cannot be made public.

Examples

Incident timeline artifact (live updates)
- Prompt: “Turn this incident into an artifact — timeline, suspect commits, error spike from our monitoring — and republish as I work through it.”
PR walkthrough artifact
- Prompt: “Make an artifact walking through this PR — the diff, the reasoning, and what I tested.”
License audit artifact
- Prompt: “Build an artifact listing every third-party dependency and its license, flagging anything copyleft.”

See: examples/role-prompts.md