Launchpad
npx machina-cli add skill smith-horn/product-builder-starter/launchpad --openclawLaunchpad
End-to-end orchestrator that chains SPARC or wave-planner (Stage 1), plan-review (Stage 2), linear (Stage 3), and hive-workers-skill (Stage 4) into a single interruptible workflow.
Stage 1 routing (ADR-109):
- Infra changes (Docker, CI, entrypoints, hooks, dev tooling) → SPARC researcher + architect →
docs/internal/implementation/{slug}.md - Feature work (application code, new endpoints, UI) → wave-planner → hive-mind YAML configs
Execution
When triggered, immediately:
- Read
./agent-prompt.md - Spawn a single Task with
subagent_type: "general-purpose"passing the agent-prompt content as the prompt - Include in the prompt: the user's request (issue IDs, project name, or description), current working directory, and any flags (
--from,--skip-review,--fresh,--infra,--feature) - Wait for the agent to complete
- Present the agent's summary to the user
Do NOT execute the workflow in this session. The subagent handles all stage sequencing, gate prompts, resume detection, and skill dispatching.
Execution Context Requirements
This skill spawns a general-purpose subagent that coordinates stages via nested Task dispatches.
Foreground execution required: Yes. Interactive stage gates use AskUserQuestion which auto-denies in background mode.
Dispatcher tools (frontmatter): Read, Task, AskUserQuestion Subagent tools: Read, Write, Edit, Bash, Grep, Glob, Task, AskUserQuestion, TodoWrite
Reference: Subagent Tool Permissions
Sub-Documentation
| Document | Contents |
|---|---|
| agent-prompt.md | Full coordinator logic: input parsing, Stage 0 infra detection, stage routing, resume detection, error handling |
Related Skills
| Skill | Role |
|---|---|
| sparc-methodology | Stage 1a (infra): SPARC researcher + architect → implementation plan |
| wave-planner | Stage 1b (feature): Generate wave plan + hive configs |
| plan-review-skill | Stage 2: VP review of plan (both paths) |
| linear | Stage 3: Create Linear project + issues |
| hive-workers-skill | Stage 4: Execute waves via ruflo swarm |
Infra Trigger Criteria (ADR-109)
Stage 1a (SPARC) is selected when scope includes any of:
docker-entrypoint.sh,Dockerfile,docker-compose.yml.github/workflows/*.yml.husky/*,pre-commit,pre-pushhook scriptsscripts/files called by Docker/CI/hookspackage.jsonscriptsblock changes- Dev tooling config:
.eslintrc,vitest.config.ts,turbo.json
Stage 1b (wave-planner) for everything else. Mixed scope → use Stage 1a.
Override with flags: --infra forces Stage 1a, --feature forces Stage 1b.
Changelog
v1.2.0 (2026-02-19)
- Section 2: Add MISSING/OK skill classification with explicit consent gate for optional skills
- Section 7: Replace silent Stage 4 fallback with explicit AskUserQuestion consent gate
v1.1.0 (2026-02-18)
- Add Stage 0 infra detection routing (ADR-109)
- Add
sparc-methodologytocomposesas Stage 1a for infra changes - Add
--infra/--featureoverride flags - Update description and Related Skills table
v1.0.0
- Initial release: 4-stage pipeline (Plan, Review, Issues, Execute)
- Interruptible stage gates with standardized 5-option prompts
- Resume detection via multi-signal artifact checks
- Skill existence checks with graceful fallbacks
Source
git clone https://github.com/smith-horn/product-builder-starter/blob/main/skills/launchpad/SKILL.mdView on GitHub Overview
Launchpad is an end-to-end orchestrator that chains SPARC or wave-planner (Stage 1), plan-review, linear, and hive-workers-skill into a single interruptible workflow. It automatically routes infra changes through SPARC research instead of wave-planner, aligning infra work with architectural review. Use it to kick off new initiatives, execute a batch of Linear issues, or run plan-to-deployment workflows.
How This Skill Works
When triggered, Launchpad immediately reads the agent-prompt, spawns a general-purpose subagent with the prompt content and context, and passes along the user request plus directory and flags. The subagent coordinates Stage 1 routing (infra via SPARC or feature via wave-planner), Stage 2 plan-review, Stage 3 linear, and Stage 4 hive-workers-skill, handling gates, resume detection, and dispatching. It does not execute the workflow in the current session; the subagent manages the end-to-end sequencing and returns a summary once complete.
When to Use It
- Starting a new initiative that requires coordinated infra and feature work
- Executing a set of Linear issues across teams to deliver a feature
- Running a plan-to-deployment workflow for a release
- Coordinating infra changes that should route through SPARC research (Stage 1a) rather than wave-planner (Stage 1b)
- Orchestrating a multi-stage rollout with gating and review at each stage
Quick Start
- Step 1: Trigger Launchpad to start an end-to-end workflow for your initiative
- Step 2: It reads agent-prompt.md and spawns a general-purpose subagent with your prompt and flags (--from, --skip-review, --fresh, --infra, --feature)
- Step 3: Wait for the subagent to complete and review the generated summary
Best Practices
- Define clear issue IDs or project scope when triggering to ensure correct Stage 1 routing
- Use --infra to force SPARC-based Stage 1 routing for infra changes, or --feature for wave-planner routing
- Keep agent-prompt.md up-to-date to reflect current workflow expectations
- Prepare plan-review inputs early to minimize gate stalls during Stage 2
- Monitor subagent prompts and leverage AskUserQuestion gates for critical decisions
Example Use Cases
- Launch a new product initiative by routing infra work through SPARC (Stage 1a) and then applying feature work via wave-planner (Stage 1b) into hive-workers-skill for execution
- Execute a batch of Linear issues to deliver a UI overhaul, with the plan reviewed and then deployed through the hive workers
- Run a plan-to-deployment for a backend migration, coordinating infra changes, code updates, and deployment steps in one workflow
- Coordinate a cross-team rollout where infra changes require architect review while feature work proceeds in parallel
- Orchestrate a risky release by enabling interactive gates and resuming after approvals to ensure compliance and rollback readiness
