From sc-startup
Run repo startup: prompt load, checklist sync, optional PR triage, worktree hygiene, and CI pull. Best-effort with structured status.
How this skill is triggered — by the user, by Claude, or both
Slash command
/sc-startup:sc-startupThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Thin orchestration for the `/sc-startup` command. Validates config, launches background agents, aggregates statuses, and emits a concise startup report. Delegates all heavy lifting to agents via Agent Runner (registry enforced, audited).
Thin orchestration for the /sc-startup command. Validates config, launches background agents, aggregates statuses, and emits a concise startup report. Delegates all heavy lifting to agents via Agent Runner (registry enforced, audited).
/sc-startup [--pr] [--pull] [--fast] [--readonly]/sc-startup --init (config discovery and guided setup)ci-pr-agent (PR list/fix; list-only when --readonly)sc-worktree-scan / sc-worktree-cleanup (worktree hygiene; scan-only when --readonly)ci-automation (pull-only master → develop; must complete before checklist updates)sc-checklist-status (report/update checklist; report-only when --readonly; no auto-commit)sc-startup-init (detection-only: config presence, candidates, package detection; returns fenced JSON with YAML payload)--init: Agent Runner → sc-startup-init (detection-only). Parse results, use AskQuestion to fill missing/ambiguous settings (prompt path, checklist path, worktree-scan, pr-enabled, worktree-enabled). If not --readonly, write .claude/sc-startup.yaml; otherwise show synthesized YAML. Then continue..claude/sc-startup.yaml; validate required keys and enabled feature dependencies. Fail closed with DEPENDENCY.MISSING if enabled package absent.--fast: read startup prompt only, summarize role, exit (no agents/checklist).--pr and enabled: Agent Runner → ci-pr-agent (--list --fix, or list-only when --readonly).sc-worktree-{scan|cleanup} (scan/report-only when --readonly).--pull: Agent Runner → ci-automation (pull-only master → develop); wait for completion before checklist updates.sc-checklist-status (default update; report-only when --readonly). Checklist changes stay in workspace (no commit).If sc-checklist-status reports VALIDATION.INVALID_PATH (path escape), explicitly flag it as a warning/issue in the final report (include the word "warning" or "issue").
.claude/sc-startup.yaml)startup-prompt (string, required)check-list (string, required)worktree-scan (string: scan|cleanup|none|"")pr-enabled (bool, optional; must be false if PR package absent)worktree-enabled (bool, optional; must be false if worktree package absent)--readonly forces report-only everywhere..claude/state/logs/sc-startup/; prune after ~14 days.{agent_id, status: success|failure|timeout|partial, results, error?} plus narrative summary.{
"success": false,
"data": null,
"error": {
"code": "DEPENDENCY.MISSING",
"message": "Feature 'pr' enabled but required agent 'ci-pr-agent' is not installed",
"recoverable": true,
"suggested_action": "Install ci-pr-agent or set pr-enabled: false in .claude/sc-startup.yaml"
}
}
npx claudepluginhub randlee/synaptic-canvas --plugin sc-startupInitializes AgentOps project files (GOALS.md, PRODUCT.md, .agents/) based on repo state. Idempotent — fills in missing artifacts without overwriting existing ones.
Assesses a git repository's readiness for AI coding agents using the agentready CLI, then walks through and addresses each gap.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.