ralphinho-rfc-pipeline
Runs multiple AI agents together to review and merge code changes using quality checks.
Installation
Paste this into Claude Code, Cursor, or any agent that can run commands.
What this skill does
What it does: - Breaks down a big feature request into smaller independent pieces of work - Assigns each piece to be done separately and checked for quality - Manages the order so pieces that depend on each other get done in the right order - Combines all the pieces back together and tests the whole thing - Tracks which pieces are done, which are waiting, and which have problems
When to use it: - A feature is too big for one person or one step to handle - You need to split the work into pieces that can be checked separately - Different pieces depend on each other and need to be done in a certain order - You need to make sure each piece works before combining them all together
SKILL.mdShow the author's original SKILL.md
--- name: ralphinho-rfc-pipeline description: RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration. metadata: origin: ECC --- # Ralphinho RFC Pipeline Inspired by [humanplane](https://github.com/humanplane) style RFC decomposition patterns and multi-unit orchestration workflows. Use this skill when a feature is too large for a single agent pass and must be split into independently verifiable work units. ## Pipeline Stages 1. RFC intake 2. DAG decomposition 3. Unit assignment 4. Unit implementation 5. Unit validation 6. Merge queue and integration 7. Final system verification ## Unit Spec Template Each work unit should include: - `id` - `depends_on` - `scope` - `acceptance_tests` - `risk_level` - `rollback_plan` ## Complexity Tiers - Tier 1: isolated file edits, deterministic tests - Tier 2: multi-file behavior changes, moderate integration risk - Tier 3: schema/auth/perf/security changes ## Quality Pipeline per Unit 1. research 2. implementation plan 3. implementation 4. tests 5. review 6. merge-ready report ## Merge Queue Rules - Never merge a unit with unresolved dependency failures. - Always rebase unit branches on latest integration branch. - Re-run integration tests after each queued merge. ## Recovery If a unit stalls: - evict from active queue - snapshot findings - regenerate narrowed unit scope - retry with updated constraints ## Outputs - RFC execution log - unit scorecards - dependency graph snapshot - integration risk summary
Mirrored from the author's public source. Install counts from the open skills registry.