agentleFS
pgnzbl-uxpgnzbl-ux/crucible/.claude/skills/smoke/SKILL.md

smoke

Skill4 starsChanged 3 months agoMITView on GitHub

全链路端到端冒烟(创建任务 → 沙箱 → Agent → 报告)

5 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions5 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 5

    1. nightly-labs/openbot★ 7.9ksame name
    2. assaio/assaio★ 63same name
    3. lfrodrigues/packt-claude-code-course-auth★ 9same name
    4. VoxTechnologies/transmute-framework★ 5same name
    5. thalissonbarbosas/hangar★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

Files
SKILL.md

Smoke (E2E)

任意 P0 改动后必须跑一次。

步骤

  1. 环境就绪:deploy skill 跑通,/health 200
  2. 注册 + 登录

    TOKEN=$(curl -sX POST http://localhost:8010/api/v1/auth/register \
      -H 'Content-Type: application/json' \
      -d '{"username":"smoke","password":"Smoke123!"}' | jq -r .id)  # 仅取 ID;下面有登录
    TOKEN=$(curl -sX POST http://localhost:8010/api/v1/auth/login \
      -H 'Content-Type: application/json' \
      -d '{"username":"smoke","password":"Smoke123!"}' | jq -r .access_token)
  3. 创建任务(CLAUDE_AGENT_SDK_ENABLED=false 时仍走模式化子图编排,不拉真实 LLM)

    TASK_ID=$(curl -sX POST http://localhost:8010/api/v1/tasks \
      -H "Authorization: Bearer $TOKEN" \
      -H 'Content-Type: application/json' \
      -d '{"repo_url":"https://github.com/octocat/Hello-World","description":"smoke test","priority":"P2"}' \
      | jq -r .id)
  4. 轮询直到完成(timeout 60s)

    for i in {1..30}; do
      curl -s "http://localhost:8010/api/v1/tasks/$TASK_ID" \
        -H "Authorization: Bearer $TOKEN" | jq .status
      sleep 2
    done
  5. 看事件流

    curl -s "http://localhost:8010/api/v1/tasks/$TASK_ID/events" \
      -H "Authorization: Bearer $TOKEN" | jq '.items[] | {type, ts: .timestamp}'
  6. 确认报告

    REPORT_ID=$(curl -s "http://localhost:8010/api/v1/tasks/$TASK_ID" \
      -H "Authorization: Bearer $TOKEN" | jq -r .report_id)
    curl -s "http://localhost:8010/api/v1/reports/$REPORT_ID" \
      -H "Authorization: Bearer $TOKEN" | jq '{status, has_content: (.content != null)}'

通过标准

  • 任务最终 status = completed 或 failed(不允许 running 滞留)
  • 事件流非空
  • 报告 status = completed 且有内容

失败处理

  • 看 Celery worker 日志
  • 看任务 events 找首个 error
  • 看沙箱:docker ps -a --filter "label=crucible"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.