Menu
Run repo startup: prompt load, checklist sync, optional PR triage, worktree hygiene, and CI pull. Best-effort with structured status.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | sc-startup |
| version | 0.12.0 |
| description | Run repo startup: prompt load, checklist sync, optional PR triage, worktree hygiene, and CI pull. Best-effort with structured status. |
| entry_point | /sc-startup |
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 synthesized YAML preview)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). Report detected prompt/checklist candidates, installed packages, missing keys, and synthesized YAML. Do not block on AskUserQuestion; exit after reporting findings..claude/sc-startup.yaml; validate required keys and enabled feature dependencies. If config is missing or invalid, return concise guidance with detected candidates and recommend --init or manual file creation. 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"
}
}
Set up a repo-local just task runner with a root Justfile, optional .just/ helper scripts, and curated help, build, fmt, lint, test, and ci recipes. Use when a repo needs just, a Justfile, .just helpers, or when the user mentions task automation, "just build", "just lint", "just fmt", or dropping in a just system.
Create or harden CLIs intended primarily for AI or system consumption and secondarily for humans. Use when designing or implementing a JSON-first CLI with an MCP-ready contract seam, where every command supports machine output, errors are typed and actionable, mutating commands are auditable via corresponding read commands, and external integrations need simulator-backed testing. Do not use for human-first shell utilities, one-off scripts, or text-only CLIs.
Design stateful simulators for AI-facing CLIs that integrate with devices, networks, services, or databases. Use when a CLI needs realistic simulator-backed testing, configurable fault injection, persistent state, and a swappable adapter boundary so the same business logic runs against live and simulated backends. Do not use for shallow mocks, stateless test doubles, or CLIs with no external integration.
Critically review an existing CLI, MCP wrapper, or CLI plan for AI-first contract quality. Use when evaluating whether a CLI is JSON-first, has an MCP-ready contract seam without JSON reshaping, auditably models state changes, uses stateful simulator-backed testing for external integrations, and returns typed actionable errors. Do not use for general style review or human-first shell UX review.
Run CI quality gates with optional auto-fix and PR creation.
Run Codex tasks via the ai_cli Task Tool runner.