skills.rest
Priivacy-ai
Priivacy-aiOFFICIAL
Explore all skills by this author →
GitHub

spk-run-program-orchestrate

Orchestrates multi-repo Spec Kitty missions across dependencies, parallel agents, and review gates.

1.6k|156|Updated Oct 9, 2025
Search Tags:#parallel agents#multi-repo# orchestration#review gates#dependency ordering#spec-Driven Development#Spec Kitty
One-click install
npx skills add https://github.com/Priivacy-ai/spec-kitty --skill spk-run-program-orchestrate
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: spk-run-program-orchestrate
Source: https://github.com/Priivacy-ai/spec-kitty/tree/main/src/charter/offering/skills/spk-run-program-orchestrate
Command: npx skills add https://github.com/Priivacy-ai/spec-kitty --skill spk-run-program-orchestrate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating several related Spec Kitty missions or repositories as one program is error-prone: dependency order gets lost, parallel agents collide, and review or merge gates get skipped. This Skill provides a structured flow for running multi-mission programs without bypassing per-mission governance.

Core Features & Use Cases

  • Dependency-Ordered Execution: Builds the mission dependency order before launching any work so upstream missions finish first.
  • Per-Mission Next Actions: Delegates each mission's authoritative next step to the spk-run-next workflow.
  • Gate Preservation: Keeps review, accept, merge, mission-review, and retrospective gates per mission while surfacing blockers as program-level risks.
  • Use Case: A team splitting a product release across three repositories runs the missions as one program, parallelizing only where dependencies allow and tracking blockers centrally.

Quick Start

Ask the agent to orchestrate your related Spec Kitty missions as a single program, building the dependency order and coordinating parallel work across repositories.

Frequently Asked Questions about spk-run-program-orchestrate

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I coordinate multiple Spec Kitty missions as one program?▼

Build the mission dependency order first, then use spk-run-next for each mission's authoritative next action. Coordinate parallel implementation only where dependencies allow, and keep review, accept, and merge gates per mission.

How do I run parallel AI agents across multiple repositories?▼

Parallelize implementation only where mission dependencies allow, using isolated git worktrees per mission. Each mission still passes through its own review, accept, and merge gates before closeout.

Does program orchestration skip mission-level review gates?▼

No. Review, accept, merge, mission-review, and retrospective gates remain enforced per mission. The orchestration layer surfaces blockers as program risks without bypassing any mission-level gate.

What happens when a mission is blocked during program orchestration?▼

Blockers are surfaced as program-level risks so dependent missions can be paused or reordered. The blocked mission's own gates and lifecycle state remain unchanged until the blocker is resolved.

When should I use single-mission workflows instead of program orchestration?▼

Use single-mission workflows when work is confined to one repository or has no cross-mission dependencies. Program orchestration is intended for coordinating several related missions or repositories as one effort.

Related Skills

Explore More Software Engineering Skills→
kimprobablykimprobably

spec-kitty.plan

Generate planning artifacts from a validated spec-kitty mission specification.

Community
Intermediate
mykaarmamykaarma

spec-to-code

Parse written specifications into dependency-ordered missions with gated execution and test validation.

Official
Advanced
xxihxxih
1

claude-devfleet

Coordinate multiple AI agents across isolated git worktrees with task DAGs and structured reports.

Community
Advanced
RobinNorbergRobinNorberg
5

autoresearch

Run bounded iterative improvement loops with evaluator-driven logs and cron reruns.

Community
Advanced