Ralphinho RFC Pipeline
Split an oversized RFC into a multi-agent execution DAG with Ralphinho: work units with dependencies and acceptance tests, per-unit research-plan-implement-test-review, merge queue with rebases, final system verification.
- What
- Split an oversized RFC into a multi-agent execution DAG with Ralphinho: work units with dependencies and acceptance tests, per-unit research-plan-implement-test-review, merge queue with rebases, final system verification.
- Cost
- Free
- Needs
- Use "Ralphinho RFC Pipeline" with your Muse.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor: the Ralphinho RFC pipeline, inspired by humanplane-style RFC decomposition patterns, for features too large for a single agent pass. The pipeline runs seven stages: RFC intake, DAG decomposition into work units with explicit dependencies, unit assignment, unit implementation, unit validation, merge queue and integration, and final system verification. Every work unit carries a spec with id, depends_on, scope, acceptance_tests, risk_level, and rollback_plan. Three complexity tiers sort the units: isolated file edits with deterministic tests at tier 1, multi-file behavior changes with moderate integration risk at tier 2, and schema, auth, performance, or security changes at tier 3. Each unit runs its own quality pipeline of research, implementation plan, implementation, tests, review, and a merge-ready report. The merge queue rules are strict: never merge a unit with unresolved dependency failures, always rebase unit branches on the latest integration branch, re-run integration tests after each queued merge. Recovery is defined too: evict a stalled unit, snapshot findings, regenerate a narrowed scope, retry with updated constraints. Outputs are an RFC execution log, unit scorecards, a dependency graph snapshot, and an integration risk summary. By @affaan-m, listed here with credit to its creator. From the affaan-m/ECC repository (MIT). Honest caveats: this is a workflow wrapper, not an orchestrator runtime; for small features a single pass is cheaper and faster. Skill Harbor never reviews the code, review it yourself before use.
Version:
Install
Copy the install package below, then paste it into MuseThe install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Use "Ralphinho RFC Pipeline" with your Muse. Prerequisites: none to install. Pure workflow guidance; an RFC or large feature spec to decompose helps. 1. Open the skill: https://github.com/affaan-m/ECC/blob/main/skills/ralphinho-rfc-pipeline/SKILL.md and copy the full SKILL.md text. 2. Paste it into a chat with Muse and add: "Decompose this RFC into a work-unit DAG: [paste the RFC]. Assign complexity tiers." 3. Review the unit specs and dependencies, then execute unit by unit through the merge queue. Tip: keep each unit's acceptance tests concrete and verifiable before implementation starts. Safety: a skill is plain-text instructions; it runs nothing by itself. Review generated commands before running them.
Saved to your recent installs. Find it anytime on /connect.
Questions
How do I install a build?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.