基于 SOC 职业分类
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。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/andreadellacorte/groove --skill groove-work-compound命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | groove-work-compound |
| description | Document lessons, update rules/templates/docs. Use to capture learnings after review. |
| license | MIT |
| allowed-tools | Read Write Edit Glob Grep Bash(git:*) AskUserQuestion |
| metadata | {"author":"andreadellacorte"} |
"This conversation" means the full chat thread (all messages in the same chat where the user invoked compound). Lessons and compound actions come from work done or decided anywhere in that thread.
In scope:
Not in scope unless the user asks: Daily memory, weekly summaries, or other docs (e.g. "compound on the whole day").
If no other work is visible in the context when compound runs (e.g. the turn only shows the compound request): ask which session or work to compound on (e.g. "I only see the compound request. Which session should I compound on — e.g. the PPP run above, or something else?") instead of concluding "no work discussed."
Lessons, root causes, and fixes are documented. Relevant project files are updated (rules, templates, docs, task bodies). A checklist of compound actions with done/pending status is produced.
tasks.backend from .groove/index.md; memory path is always .groove/memory/.groove/.cache/pending-capture.md exists (staged by the session-capture Stop hook), read it first and use its commits/working-changes as ground-truth source material for the lessons and the git context — so a forgotten or compacted session is not lost. After the compound stage is recorded, delete .groove/.cache/pending-capture.md./groove-utilities-memory-mistakes --list:
/groove-utilities-memory-mistakes before moving ontasks.backend != none via /groove-utilities-task-create with a descriptive title so multiple compounds per day are distinct: YYYY-MM-DD, Compound — <brief topic> (topic from the work just closed, e.g. release, feature, or session summary). Do not number stages in task titles.patterns, tools, anti-patterns, hooks)## <YYYY-MM-DD> heading in the file;
create the file with a # <Topic> heading if it does not exist; create the dated heading if absentgroovebook: is set in .groove/index.md: add a one-line suggestion after the checklist: "Learning captured → .groove/memory/learned/<topic>.md. Publish to groovebook? Run /groove-groovebook-publish." If groovebook: is absent: skip silently./groove-utilities-memory-graduate <topic> to promote it to AGENTS.md permanently." — only suggest if the lesson was just confirmed, not every compound run./groove-utilities-memory-promises <text>. If none found: skip silently..groove/memory/learned/signals.md under a table; create the file with a header and table header row if it does not exist| YYYY-MM-DD | <rating>/5 | <one-line context from the session topic> |Groove engineering workflow system. Top-level entry point. Use groove-daily-*, groove-work-*, groove-utilities-*, groove-admin-* for all workflow and admin commands.
Install a rich Claude Code statusline into ~/.claude/hooks/ and ~/.claude/settings.json. Displays model, git context, token usage, effort level, 5h/7d usage limits, and active /loop count with next-fire time.
Set up task backend and configuration.