Menú
Repair Claude teammate routing after same-session compaction or resume when sc-lint still exists on disk and the saved leadSessionId still matches the current SESSION_ID, but SendMessage or teammate reachability is broken.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Guide a consuming repository through `sc-lint-version` adoption using the authoritative consumer-integration workflow, existing CLI testability seams, existing simulators or transcripts, and only thin normalization hooks when unavoidable.
Orchestrate sc-lint sprint work where team-lead coordinates, clint is the sole developer, and quality-mgr enforces the QA gate.
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.
Run the repo Rust TODO finder during sprint-end or integration review and turn every discovered TODO into a QA finding rather than deferred work.
Orchestrate pre-dispatch QA finding triage as team-lead. Launch one qa-triage agent per finding, collect phase-scoped Turtle records, aggregate by promoted branch, and only then dispatch branch-scoped fix assignments to clint.
Team-lead drives plan hardening after the current plan state already exists in repo docs.
| name | restore-team-communications |
| version | 0.2.0 |
| description | Repair Claude teammate routing after same-session compaction or resume when sc-lint still exists on disk and the saved leadSessionId still matches the current SESSION_ID, but SendMessage or teammate reachability is broken. |
Use this skill only when all of these are true:
ATM_IDENTITY=team-leadSESSION_ID still matches leadSessionId in
~/.claude/teams/sc-lint/config.jsonDo not use this skill for fresh startup or after clear. If the current
SESSION_ID does not match leadSessionId, use /team-lead and follow the
full restore procedure instead.
First, try normal Claude-to-Claude communication before changing anything:
SendMessage(to="<claude-teammate>", message="ping: verify sc-lint communications path")
If the message is delivered and acknowledged, stop. No repair is needed.
Do not read inbox files, session files, or tmux panes directly on this path.
Back up before any destructive recovery:
atm teams backup sc-lint
BACKUP_PATH=$(ls -td ~/.claude/teams/.backups/sc-lint/*/ | head -1)
cp -r ~/.claude/tasks/sc-lint/ "$BACKUP_PATH/tasks-cc"
echo "CC task list backed up to $BACKUP_PATH/tasks-cc"
Clear both live Claude routing state and the persisted team directory:
TeamDelete
rm -rf ~/.claude/teams/sc-lint
If TeamDelete reports no active team name, proceed. That means live routing
was already absent.
Recreate the team:
TeamCreate(team_name="sc-lint", description="sc-lint development team", agent_type="team-lead")
Then restore from the most recent backup:
atm teams restore sc-lint --from "$BACKUP_PATH"
If required members are missing after restore, add them before verification.
Repair is not complete until all checks pass:
SendMessage to another Claude teammate.atm send to a non-Claude model.atm send to Codex and verify the nudge fires.For Codex-directed ATM sends, the nudge must include a clear call to action, not just a passive unread-mail announcement. Preferred structured nudge payload:
<atm><action>read atm</action><action>ack <TASK-ID></action><action>execute assigned task</action><when idle="immediate" busy="after-current-task"/><console announce="concise" pause="false"/></atm>
Fallback plain-text wording:
read atm for task <TASK-ID> and complete it before stopping
If the task is queued behind active work, use a queued-task nudge instead of an interruptive one.
If the repair succeeded:
If the repair failed, stop and report the exact failed verification step.