skills.sh
AvailableUniversal skill installation, including Claude Code and Codex.
npx skills add https://github.com/ulpi-io/skills-autonomous-engineering --skill schedule-recurring-agentschedule-recurring-agentCreates repeat-safe standing work with an idempotent brief, justified cadence, per-run bound, and off-switch.
Confirm the work is recurring and its autonomous action scope is authorized.
Write a self-contained brief with deduplication, reporting, escalation, and a per-run cap.
Choose the least-frequent cadence that still meets the work’s arrival window.
Choose durable cloud routine or in-session cron honestly and confirm registration.
Inspect for duplicates and tear the routine down when its stop condition is met.
▸ operating envelope
The shortest useful definition of where this skill helps—and where it should stay out of the way.
▸ output contract
▸ enforcement
Scripts are linked when this skill owns deterministic machinery. The remaining rules are explicit operating contracts and must not be marketed as hooks.
This skill composes platform tools and verification evidence; it does not claim a dedicated guard script.
▸ install and invoke
Universal skill installation, including Claude Code and Codex.
npx skills add https://github.com/ulpi-io/skills-autonomous-engineering --skill schedule-recurring-agentInstall the full plugin, then invoke /schedule-recurring-agent or let routing select it from context.
A work in progress on the codex-native-plugin branch — build it, start a new session, then invoke $autonomous-engineering:schedule-recurring-agent.
▸ composes with