Agent Skills › Tracer-Cloud/opensre › onboarding-github-ci

onboarding-github-ci

GitHub

CI/CD入职引导主技能,负责展示工作流菜单、处理用户选择并路由至子技能执行具体任务。

core/agent_harness/prompts/skills/onboarding-github-ci/SKILL.md Tracer-Cloud/opensre

Trigger Scenarios

用户询问OpenSRE能力或请求演示 启动时触发入职流程 调用/demo命令

Install

npx skills add Tracer-Cloud/opensre --skill onboarding-github-ci -g -y
More Options

Non-standard path

npx skills add https://github.com/Tracer-Cloud/opensre/tree/main/core/agent_harness/prompts/skills/onboarding-github-ci -g -y

Use without installing

npx skills use Tracer-Cloud/opensre@onboarding-github-ci

指定 Agent (Claude Code)

npx skills add Tracer-Cloud/opensre --skill onboarding-github-ci -a claude-code -g -y

安装 repo 全部 skill

npx skills add Tracer-Cloud/opensre --all -g -y

预览 repo 内 skill

npx skills add Tracer-Cloud/opensre --list

SKILL.md

Frontmatter
{
    "name": "onboarding-github-ci",
    "metadata": {
        "owner": "Vincent",
        "version": "3.1",
        "requires": [
            "An interactive terminal for the entry picker, or a conversational surface for its text fallback.",
            "At least one available onboarding child skill."
        ],
        "usecases": [
            "For new users selecting an available onboarding workflow at startup or through \/demo.",
            "For users exploring OpenSRE capabilities before choosing a specific workflow."
        ],
        "last_changed_at": 1790899200,
        "last_changed_by": "Jan"
    },
    "description": "Present the available onboarding workflows and follow the selected skill. Use at interactive startup, for \/demo, or when a user asks about OpenSRE capabilities. Direct workflow requests should load the matching specialist."
}

CI/CD onboarding

This master skill owns the onboarding question. The host opens its menu on entry; the result's entry_menu reports whether it opened. If the current message already answers it, continue directly to the selected child. Never ask the onboarding question twice for one request.

Ask User

Read the entry_menu result before deciding what to do:

  • menu: queued: end the turn and wait for the selection. The host owns the menu; do not call ask_user_choice again or repeat its options as text.
  • menu: suppressed: no new menu opened. Continue the current request using the existing answer. If the user explicitly requests the demo menu again, call slash_invoke with /demo; a greeting does not request reopening.
  • menu: unavailable: show Current demo choices as a numbered list and wait for a reply.
  • A hook error without a menu status: explain that the picker could not open and show Current demo choices as a numbered list.

Only a queued menu justifies telling the user to select from an open picker. The menu has no free-text row. Its last option opens the plain shell; the shell handles Skip and Escape without sending an answer to the model.

Follow the selected child

The next message carries the question and the user's answer. A local or cloud repair can also carry a second answer to Create a private demo repository?. That answer is the target decision. Do not ask it again and do not reopen this menu. Call skill_view with the matching name, then follow its returned instructions in the same turn:

Use the generated Current demo choices below to match the answer to its skill. Load that skill before performing its workflow.

For a custom answer, treat that text as the user's request and act on it using the appropriate tools or skill. Do not reopen this menu or force a demo choice. After a child asks its own question, continue that child rather than returning to this master menu. Escape cancels onboarding; wait for a fresh user request.

An explicit /demo starts the selected workflow with the new request. Let its tool resolve an existing active run; completed results do not count as a new run.

When the picker is unavailable, the text fallback must offer the two outcomes first, then the three automation choices, instead of a flat list of four demos. Bump last_changed_by, last_changed_at, and version on each card in that same edit

Version History

  • 88dba66 Current 2026-10-19 05:34

    修复了自动化场景下后续答案记录问题;改进了欢迎横幅测试以匹配新的文案;调整了失败种子报告的HTTP状态码逻辑。

  • 4303874 2026-09-22 10:48

Same Skill Collection

core/agent_harness/prompts/skills/architecture_audit/SKILL.md
core/agent_harness/prompts/skills/delivering-morning-briefings/SKILL.md
core/agent_harness/prompts/skills/fixing-github-merge-conflicts/SKILL.md
core/agent_harness/prompts/skills/fixing-github-security-alerts/SKILL.md
core/agent_harness/prompts/skills/github_ci_fix_onboarding/SKILL.md
core/agent_harness/prompts/skills/github_ci_fix/SKILL.md
core/agent_harness/prompts/skills/github_ci_health/SKILL.md
core/agent_harness/prompts/skills/github_cli/SKILL.md
core/agent_harness/prompts/skills/github_security_fix/SKILL.md
core/agent_harness/prompts/skills/investigating-incidents-with-runbooks/SKILL.md
core/agent_harness/prompts/skills/morning_report/SKILL.md
core/agent_harness/prompts/skills/repair-github-ci/SKILL.md
core/agent_harness/prompts/skills/reporting-github-ci-failures/SKILL.md
integrations/github/tools/ci_fix/SKILL.md
integrations/github/tools/github_cli/SKILL.md
integrations/github/tools/security_fix/SKILL.md
integrations/github/tools/workflow/SKILL.md
integrations/posthog/tools/skills/posthog-summary/SKILL.md
integrations/posthog/tools/skills/summarizing-posthog-analytics/SKILL.md
integrations/sentry/tools/skills/sentry-summary/SKILL.md
integrations/sentry/tools/skills/summarizing-sentry-issues/SKILL.md
integrations/yandex_cloud/tools/SKILL.md
tools/github_cli/SKILL.md
tools/system/python_execution_tool/skills/github-star-velocity/SKILL.md
tools/system/python_execution_tool/skills/measuring-github-star-velocity/SKILL.md
core/agent_harness/prompts/skills/analyzing-local-repositories/SKILL.md
core/agent_harness/prompts/skills/cicd_analytics_demo/SKILL.md

Metadata

Files
0
Version
88dba66
Hash
ac377c93
Indexed
2026-09-22 10:48

ホーム - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-10-21 10:23
浙ICP备14020137号-1