test(work-items): run the new work-loop and attend-queue evals and a live C3 check
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 4/5
- 预计耗时
- 3-5 天
- 新手友好度
- 35/100
- Issue 类型
- 缺陷
- 描述清晰度
- 基本清楚
- 活跃度
- 活跃
- 技术栈
- github, shell
- 领域
- testing-qa
调研方向
Read plugins/work-items/skills/work-loop/AGENTS.md and the named evals.json files for work-loop and attend-queue. Start by checking the eval runner’s no-plugin baseline workflow and how it records pass rates; then determine how the C3 check can use a throwaway issue or local-markdown binding. Done means the named eval cases have recorded results, the C3 check runs without posting to public issues, and any failures are fixed.
由索引模型根据 Issue 内容生成。
描述
Follow-up to #7159, #7204 and #7208.
Those PRs added or changed eval cases that have only passed the static checks (check-changed-skills, the evals.json schema). None has been run against a model:
plugins/work-items/skills/work-loop/evals/evals.json: case 6 (changed); cases 16, 17 and 18 (truncated snapshot: escalate at once, then stop a headless lane); the first-drain-ratification cases from #7204.plugins/work-items/skills/attend-queue/evals/evals.json: case 9 (a ratify-first-drain proposal on a telemetry issue lists as a[ratify]row, and other telemetry markers stay hidden).
The manual C3 ratification check in plugins/work-items/skills/work-loop/AGENTS.md was also done on paper by a fresh-context agent, not against real tracker items, because a live run posts to public issues.
Do
- Run these suites with
/evals:plugin-evalagainst a no-plugin baseline, and record pass rates. - Run the AGENTS.md C3 check live against a throwaway test issue, or a local-markdown binding, so nothing posts to real public issues.
- Fix any case or skill text that fails.
- 主要语言
- Shell
- 星标
- 22
- 派生
- 2
- 平均合并
- 7 小时 23 分钟
- 30 天内合并 PR
- 950
环境准备
- 没有 Dockerfile 或 Docker Compose 文件
- 没有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue，再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库，在一个分支上完成修改。
- 提交 Pull Request，并在描述里引用这个 Issue 编号。
melodic-software/claude-code-plugins 的其他 Issue
-
fix(session-flow): redact.py misses bare sk-ant-oat01- tokens and stateless ghs_ tokens with dots未关闭needs-human
难度 2/5 1-3 小时 新手友好度 82/100
melodic-software/claude-code-plugins#9026 · 1 条评论 ·
维护者通常 1 天内回复
-
needs-human
难度 2/5 1-3 小时 新手友好度 76/100
melodic-software/claude-code-plugins#9013 · 1 条评论 ·
维护者通常 1 天内回复
-
needs-triage
难度 2/5 1-3 小时 新手友好度 68/100
melodic-software/claude-code-plugins#9000 · 3 条评论 ·
维护者通常 1 天内回复
-
needs-human
难度 2/5 1-3 小时 新手友好度 73/100
melodic-software/claude-code-plugins#8998 ·
维护者通常 1 天内回复
-
fix(source-control): ready hold check treats hyphenated identifiers containing wip as a WIP marker未关闭priority: medium
难度 2/5 1-3 小时 新手友好度 77/100
melodic-software/claude-code-plugins#8977 · 1 条评论 ·
维护者通常 1 天内回复
查看 melodic-software/claude-code-plugins 的全部 Issue
相似的 Issue
-
难度 1/5 1 小时以内 新手友好度 88/100
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 72/100
koalaman/shellcheck#3593 ·
-
automated issue report
难度 1/5 1 小时以内 新手友好度 78/100
a2aproject/A2A#2381 ·
维护者通常 3 天内回复
-
e2e-failure ready-to-code
难度 1/5 1 小时以内 新手友好度 82/100
redhat-developer/rhdh-plugin-export-overlays#4485 · 1 条评论 ·
维护者通常 1 天内回复
-
DSH /pwf-status reports no plan when PLAN_ID is required可能已有人在做 @kuei51307-hub 今天认领。 未关闭
难度 2/5 1-3 小时 新手友好度 78/100
OthmanAdi/planning-with-files#332 · 1 个 reaction ·
维护者通常 1 天内回复