Menu
Generate a sprint status report for the current phase. Default is --table.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Orchestrate multi-sprint phases where arch-ctm (Codex) is the sole developer, with pipelined QA via quality-mgr teammate. Team-lead tracks findings and schedules fix passes.
Session initialization for the team-lead identity. Confirms identity and detects whether a full team restore is needed. Only run when ATM_IDENTITY=team-lead.
Reusable QA orchestration skill for GitHub PRs. Use for multi-pass QA, CI monitoring with `atm gh monitor`, one-shot PR reporting with `atm gh pr report`, and template-driven findings/final quality reports.
Orchestrate multi-sprint phase execution as team-lead (ARCH-ATM). Manages sprint waves, scrum-master lifecycle, PR merges, arch-ctm reviews, and integration branch strategy. This skill is for the TEAM-LEAD only, not for scrum-masters.
Launch and verify named teammates that participate in team messaging. Use when setting up a new team member with mailbox polling, troubleshooting why a teammate is not receiving messages, or creating named Claude/Codex/Gemini teammates with team-scoped communication.
Run ATM health diagnostics, present severity-sorted findings, and delegate deep remediation analysis to the atm-doctor agent when critical findings exist.
| name | sprint-report |
| description | Generate a sprint status report for the current phase. Default is --table. |
Build fenced JSON and pipe to the Jinja2 template. mode controls table vs detailed.
/sprint-report [--table | --detailed]
Default: --table
Always use atm gh pr list first โ single call, returns all open PRs with CI and merge state:
atm gh pr list
This is faster and sufficient for populating sprint_rows and integration_row. Only drill into individual gh run view calls if you need failure details for a specific job.
Dogfooding rule: If atm gh pr list output is missing information needed to fill the report (e.g., no per-job failure detail, no QA state, truncated CI summary), file a GitHub issue describing what field or format change would make it sufficient, then improve the command. Do not silently work around gaps with extra gh CLI calls โ surface them as product issues.
The template path is relative โ must run from the main repo root (not a worktree).
cd "${CLAUDE_PROJECT_DIR:-$(git worktree list | head -1 | awk '{print $1}')}"
echo '<json>' > /tmp/sprint-report.json
sc-compose render .claude/skills/sprint-report/report.md.j2 --var-file /tmp/sprint-report.json
{
"mode": "table",
"sprint_rows": "| AK.1 | โ
| โ
| ๐ | #621 |\n| AK.2 | โ
| โ
| ๐ | #622 |",
"integration_row": "| **integrate** | | โ | ๐ | โ |"
}
{
"mode": "detailed",
"sprint_rows": "Sprint: AK.1 Contract reconciliation\nPR: #621\nQA: PASS โ (iter 3)\nCI: Merged to integrate/phase-AK โ\nโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ\nSprint: AK.2 OTel core\nPR: #622\nQA: PASS โ\nCI: Running (1 pending)",
"integration_row": "Integration: integrate/phase-AK โ develop\nCI: Running โ pending AK.4 + AK.5"
}
| State | DEV | QA | CI |
|---|---|---|---|
| Assigned | ๐ฅ | ๐ฅ | |
| In progress | ๐ | ๐ | ๐ |
| Done/Pass | โ | โ | โ |
| Findings | ๐ฉ | ๐ฉ | |
| Fixing | ๐จ | ||
| Blocked | ๐ง | ||
| Fail | โ | ||
| Merged | ๐ | ||
| Ready to merge | ๐ |