一键导入
marketplace-publish
Package and submit skills to the Crewly marketplace. Validates, archives, and submits for review to both local and remote registries.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Package and submit skills to the Crewly marketplace. Validates, archives, and submits for review to both local and remote registries.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | Marketplace Publish |
| description | Package and submit skills to the Crewly marketplace. Validates, archives, and submits for review to both local and remote registries. |
| version | 1.0.0 |
| category | automation |
| skillType | claude-skill |
| assignableRoles | ["developer","backend-developer","fullstack-dev","architect","generalist"] |
| triggers | ["publish skill","submit skill","marketplace publish","package skill","share skill"] |
| tags | ["marketplace","publish","submit","package","skills"] |
| execution | {"type":"script","script":{"file":"execute.sh","interpreter":"bash","timeoutMs":60000}} |
Package and submit skills to the Crewly marketplace. This skill handles validation, archiving, and submission to both local and remote registries.
validate — Check a skill directory before publishingbash {{AGENT_SKILLS_PATH}}/marketplace/marketplace-publish/execute.sh '{"action":"validate","skillPath":"{{PROJECT_PATH}}/config/skills/agent/my-skill"}'
Returns valid: true/false with any errors and warnings.
publish — Package and submit to local marketplacebash {{AGENT_SKILLS_PATH}}/marketplace/marketplace-publish/execute.sh '{"action":"publish","skillPath":"{{PROJECT_PATH}}/config/skills/agent/my-skill"}'
This creates a tar.gz archive and submits it to the local Crewly backend for review. The skill becomes available in the local marketplace once approved.
publish-remote — Submit to both local and remote registriesbash {{AGENT_SKILLS_PATH}}/marketplace/marketplace-publish/execute.sh '{"action":"publish-remote","skillPath":"{{PROJECT_PATH}}/config/skills/agent/my-skill"}'
Publishes to the local review queue AND to the public marketplace. The public path goes through the authenticated Crewly Cloud flow (crewly publish --cloud) — it requires crewly cloud login, and the cloud opens a PR to the skills repo on your behalf (a maintainer reviews + merges it). It does NOT write the registry directly: that admin endpoint is correctly restricted (returns 401 to unauthenticated callers), and sending an admin token from a user skill would leak it to every machine.
If you are not logged in, the local submission still succeeds; the result includes a cloudError and a hint to run crewly cloud login, then retry.
list-submissions — View submission statusbash {{AGENT_SKILLS_PATH}}/marketplace/marketplace-publish/execute.sh '{"action":"list-submissions"}'
Filter by status:
bash {{AGENT_SKILLS_PATH}}/marketplace/marketplace-publish/execute.sh '{"action":"list-submissions","status":"pending"}'
A valid skill directory must contain:
skill.json — Metadata with id (kebab-case), name, description, version (semver), category, assignableRoles, tagsexecute.sh — Executable bash script (the skill's entry point)instructions.md — Usage documentation for the agentJSON response with publish status, including submission ID for tracking.
Plan and create a NESTED team hierarchy (parent coordination team + per-stream child teams) for a complex multi-stream goal. Use INSTEAD of recommend-team/materialize-team when the goal names 2+ parallel work-streams (e.g. frontend + backend + DevOps). Onboarding-only.
Search the live web for a query and return ranked results (title, URL, snippet) as JSON. Works with no API key (DuckDuckGo HTML fallback) and uses the Brave Search API or SerpAPI automatically when BRAVE_API_KEY / SERPAPI_KEY is set. Any agent can call it for research, competitor analysis, market/trend lookups, fact-checking, finding sources to cite, or grounding a non-software goal (marketing, growth, commerce) in real-world information.
Transcribe a local audio (or video) file to text with timestamps using Whisper. Defaults to local whisper.cpp (free, offline, word/segment-level timestamps) and automatically falls back to the OpenAI Whisper API (whisper-1) when the local engine is not installed. Any agent can call it for meetings, podcasts, voice notes, interviews, or video audio tracks.
Accept and take the next available task from the task queue. Use when an agent is idle and ready to pick up the highest-priority unassigned task. For assigning tasks to specific agents, use assign-task instead.
Register the agent as active with the Crewly backend on startup. Use when an agent first launches and needs to join the team and become visible to the orchestrator. For confirming responsiveness after registration, use heartbeat instead.
Analyze git changes and produce a structured code review with automated checks for missing tests, debug statements, potential secrets, large changes, and dependency modifications. Use when reviewing staged changes, unstaged diffs, recent commits, or branch comparisons before submitting a pull request. For task-level quality gates, use check-quality-gates instead.