원클릭으로 Manus에서 모든 스킬 실행

skills-marketplace-readiness

스타1

포크1

업데이트2026년 7월 17일 00:37

Prepare an agent skills repository for discovery, installation, and marketplace listings. Use when publishing skills to skills.sh, Agent Skills clients, Claude plugins, Codex, Cursor, Copilot, and related skill directories.

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

wakqasahmed

wakqasahmed/agentic-commerce-skills

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Skills Marketplace Readiness

Workflow

Confirm every skill is an independent folder with a matching SKILL.md frontmatter name and a specific activation-focused description.
Keep each skill narrow, executable, and short enough for progressive disclosure. Move long background material to references only when needed.
Add install and discovery surfaces:
- README install command: npx skills@latest add owner/repo
- skills.sh badge: [![skills.sh](https://skills.sh/b/owner/repo)](https://skills.sh/owner/repo)
- .claude-plugin/plugin.json with all published skill paths.
- scripts/list-skills.sh and scripts/link-skills.sh for local fallback.
Validate that all plugin paths resolve and each listed skill has a SKILL.md.
Confirm safety-relevant skills — those that can drive autonomous checkout, payment, support actions, or other agent-executed changes — have a behavioral eval (fixtures plus a pass/fail runner) wired into CI. A skill that only has prose guardrails and no eval coverage is not marketplace-ready.
Position the repo around searchable intent, not internal naming: use words buyers and agents search for, such as ecommerce, agentic commerce, AEO, GEO, SEO, agent readiness, checkout, ACP, UCP, MCP, and AI crawler readiness.
Submit or seed marketplace visibility by installing with the public CLI, sharing the GitHub URL, adding the badge, and linking the repo from website, docs, social profiles, and relevant skill directories.

Guardrails

Do not inflate install claims or marketplace status before the repo appears publicly.
Do not bundle unrelated workflow skills into the domain repo. Keep engineering workflow skills in a separate repo.
Treat marketplace listings as distribution, not validation. Skill quality still depends on real execution and iteration.
Do not call a pack marketplace-ready if a safety-relevant skill lacks behavioral eval or CI coverage.

이 저장소의 다른 Skills

같은 저장소

commerce-protocol-readiness

wakqasahmed/agentic-commerce-skills

Audit an ecommerce storefront for agentic commerce protocols and action readiness. Use when checking ACP, UCP, AP2, x402, MPP, MCP, A2A, OAuth, checkout, order, and payment readiness.

2026-07-171

agent-readiness

wakqasahmed/agentic-commerce-skills

Check whether AI agents can discover, read, cite, and safely act on an ecommerce storefront. Use for agentic commerce readiness reviews.

2026-07-171

custom-agent-remediation-plan

wakqasahmed/agentic-commerce-skills

Convert Agentic Commerce audit findings into a custom-agent implementation checklist. Use after readiness, SEO/AEO/GEO, product knowledge, or policy gaps are known.

2026-07-171

readiness-audit

wakqasahmed/agentic-commerce-skills

Route an ecommerce storefront through an Agentic Commerce readiness audit. Use when assessing whether a store should move to Custom Agent, Verified Audit, Forward Deployed Engineering, or Not Qualified.

2026-07-171

llms-txt-and-crawler-access

wakqasahmed/agentic-commerce-skills

Review crawler and AI-agent access files for ecommerce sites, including robots.txt, sitemap, llms.txt, and AI bot rules.

2026-07-101

ecommerce-policy-readiness

wakqasahmed/agentic-commerce-skills

Assess whether ecommerce policies are clear enough for AI answers, support drafts, and supervised order workflows.

2026-06-151

name	skills-marketplace-readiness
description	Prepare an agent skills repository for discovery, installation, and marketplace listings. Use when publishing skills to skills.sh, Agent Skills clients, Claude plugins, Codex, Cursor, Copilot, and related skill directories.

Skills Marketplace Readiness

Workflow

Confirm every skill is an independent folder with a matching SKILL.md frontmatter name and a specific activation-focused description.
Keep each skill narrow, executable, and short enough for progressive disclosure. Move long background material to references only when needed.
Add install and discovery surfaces:
- README install command: npx skills@latest add owner/repo
- skills.sh badge: [![skills.sh](https://skills.sh/b/owner/repo)](https://skills.sh/owner/repo)
- .claude-plugin/plugin.json with all published skill paths.
- scripts/list-skills.sh and scripts/link-skills.sh for local fallback.
Validate that all plugin paths resolve and each listed skill has a SKILL.md.
Confirm safety-relevant skills — those that can drive autonomous checkout, payment, support actions, or other agent-executed changes — have a behavioral eval (fixtures plus a pass/fail runner) wired into CI. A skill that only has prose guardrails and no eval coverage is not marketplace-ready.
Position the repo around searchable intent, not internal naming: use words buyers and agents search for, such as ecommerce, agentic commerce, AEO, GEO, SEO, agent readiness, checkout, ACP, UCP, MCP, and AI crawler readiness.
Submit or seed marketplace visibility by installing with the public CLI, sharing the GitHub URL, adding the badge, and linking the repo from website, docs, social profiles, and relevant skill directories.

Guardrails

Do not inflate install claims or marketplace status before the repo appears publicly.
Do not bundle unrelated workflow skills into the domain repo. Keep engineering workflow skills in a separate repo.
Treat marketplace listings as distribution, not validation. Skill quality still depends on real execution and iteration.
Do not call a pack marketplace-ready if a safety-relevant skill lacks behavioral eval or CI coverage.