From orqit
Living registry of platform operations that are known-automatable (API/CLI with session-store receipts) vs. truly manual (with evidence of why). Consult before labeling any step "manual" or "founder web-UI" in a plan, spec, or handoff.
How this skill is triggered — by the user, by Claude, or both
Slash command
/orqit:automation-registryThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
A living registry of platform operations with evidence of whether they are API/CLI-automatable or genuinely manual. Consult this before labeling any step "manual" in a plan, spec, or handoff.
A living registry of platform operations with evidence of whether they are API/CLI-automatable or genuinely manual. Consult this before labeling any step "manual" in a plan, spec, or handoff.
Before labeling a step "manual," cite one of:
If no evidence exists, draft the step as an API attempt with a run-time fallback to manual — never as manual upfront.
| Platform | Operation | Status | Receipt | Notes |
|---|---|---|---|---|
| GitHub | Create repo | Automatable | gh repo create | Supports --public/--private/--org flags |
| GitHub | Open PR | Automatable | gh pr create | Full field support |
| GitHub | Close PR | Automatable | gh pr close | Supports --comment |
| GitHub | Create/close issue | Automatable | gh issue create / gh issue close | |
| GitHub | Add label | Automatable | gh label create / gh issue edit --add-label | |
| GitHub | Trigger workflow | Automatable | gh workflow run | Requires workflow_dispatch trigger |
Add rows as you automate new operations. Format: Platform → Operation → Automatable/Manual → Receipt (command, session ID, or doc URL) → Notes.
When you successfully automate a new operation:
When you discover a genuinely manual operation:
npx claudepluginhub foculoom/plugins --plugin orqitGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.