一键导入
daily-checkin
Mid-day progress check against the daily plan. Scans for new DMs, checks capacity, and helps reprioritize if needed.
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
Mid-day progress check against the daily plan. Scans for new DMs, checks capacity, and helps reprioritize if needed.
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
Config-driven visible plan-to-PR workflow for Workbench engineering work. Use for agent-flow, full lifecycle, visible agents, Helix-style implementation, cross-repo context, HTML plans, PR breakdowns, small or stacked PRs, reviewer packets, review from packet, Claude/Codex pairing, worktrees, Jira/PR handoffs, continuation handoffs, or approved bypass of detailed PR slicing.
Freeform ideation and structured shortlisting. Generates 8-10 approaches including wild cards, then converges on 2-4 viable options with tradeoffs. Use before /forge or standalone for any creative exploration.
Read Outlook Web calendar via Chrome and extract meeting data for capacity planning. Writes to context/active/calendar.md so other skills use real numbers.
Show remaining capacity today and this week by reading daily and weekly plans. Flags overcommitment. Use when checking if there's room for more work.
Read and critically summarize a Confluence document. Surfaces key decisions, gaps, open questions, and suggests review questions.
Create a release branch and managed _release worktree in a Workbench repo using canonical Python worktree tooling. Use when the user wants to cut a release, create a release branch, start a release process, preview the next release branch name, or keep release work out of main/develop.
| name | daily-checkin |
| description | Mid-day progress check against the daily plan. Scans for new DMs, checks capacity, and helps reprioritize if needed. |
Path resolution: This skill may run from any repo. All
context/andconfig.yamlpaths are relative to the workbench root, not the current working directory. Read~/.codex/workbench-rootor~/.claude/workbench-rootto get the absolute workbench path, then prepend it to allcontext/andconfig.yamlreferences. See PATHS.md.
Review progress against today's plan and help maintain focus.
The user's Slack display name is defined in config.yaml under user.slack_display_name. Slack channels are defined in config.yaml under slack.channels.
Read the daily plan file at context/active/daily.md.
If no plan exists, say so and suggest running /morning-triage.
Look at the checkboxes and time estimates in the plan:
Also read the weekly plan (context/active/weekly.md) for weekly context:
Read config.yaml to get the user's Slack display name from user.slack_display_name. Search for recent messages mentioning that name using mcp__claude_ai_Slack_MCP__slack_search_public_and_private. Check if any new DMs or @mentions have come in since the morning triage.
Also do a lightweight check of highest-priority channels from config.yaml: slack.channels — check operations channels first (any incidents?), then product channels (any new urgent issues?), then key engineering channels (any threads waiting on a response?).
Only report if there's something that changes priorities.
Format:
Progress: X/Y items completed
Time: Xh used / Yh estimated remaining / Zh available today
Weekly: Xh committed / Yh remaining this week
Unanswered DMs/@mentions: N (if any new ones)
Top incomplete: [item] — WHY this matters: [reason] — est: Xh
New from Slack: [anything urgent, or "nothing new"]
Then ask:
If priorities change based on the conversation, update the daily plan file with:
Direct and supportive, not nagging. The goal is to help maintain focus, not to judge. If nothing's been checked off, ask "what's been taking up your time?" — there's usually a good reason (meetings, unexpected incident, etc.) and the plan should adapt.