SkillRepo
Sign InSign Up
Catalog
affaan-m/ralphinho-rfc-pipeline

affaan-m

ralphinho-rfc-pipeline

RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration. Use when running RFC-driven multi-agent execution with quality gates and a merge queue.

NewUpdated Sep 9, 2026

Ralphinho RFC Pipeline

Inspired by 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
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

72/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

85

Quality

68

Clarity

75

Completeness

62

Summary

The Ralphinho RFC Pipeline skill provides architectural guidance for executing large features through RFC-driven multi-agent DAG orchestration with work unit decomposition, quality gates, and merge queue management. It establishes a structured 7-stage pipeline with complexity tiers, dependency tracking, and recovery protocols for coordinating parallel agent work on complex projects.

Detected Capabilities

workflow orchestrationdependency graph managementwork unit trackingmerge queue coordinationtest/review gatingrecovery/rollback planning

Trigger Keywords

Phrases that agents use to match this skill to user intent.

rfc-driven feature developmentmulti-agent work orchestrationcomplex feature decompositionmerge queue managementdag-based coordinationwork unit pipelinefeature integrationdependency-tracked execution

Referenced Domains

External domains referenced in skill content, detected by static analysis.

github.com

Use Cases

  • Splitting large features into independently verifiable work units with tracked dependencies
  • Orchestrating multi-agent parallel work using RFC decomposition patterns
  • Managing feature integration through merge queues with quality gates and rebasing rules
  • Tracking work unit complexity tiers (isolated edits, multi-file changes, schema/auth/perf changes)
  • Recovering from stalled units by narrowing scope and re-executing with updated constraints
  • Generating execution logs, unit scorecards, dependency graphs, and integration risk summaries

Quality Notes

  • Skill provides clear architectural pattern with 7-stage pipeline and explicit unit spec template (id, depends_on, scope, acceptance_tests, risk_level, rollback_plan)
  • Complexity tier system effectively categorizes work by integration risk (Tier 1-3)
  • Quality pipeline per unit is well-defined with 6 sequential steps (research through merge-ready report)
  • Merge queue rules are specific and actionable (no unresolved dependencies, rebase on integration branch, re-run tests)
  • Recovery protocol provides concrete steps for stalled units (evict, snapshot, narrow scope, retry)
  • Outputs are well-specified (RFC log, scorecards, dependency graph, risk summary)
  • Documentation lacks concrete examples of unit specs, DAG structures, or pipeline execution traces
  • No guidance on how agents should coordinate state or communicate unit results between stages
  • Missing details on what constitutes 'merge-ready' or how review stage gates implementation
  • No prescribed format for dependency graph snapshots or risk summary output
  • Recovery protocol refers to 'narrowed unit scope' but does not explain how scope narrowing should be determined
  • Limited error handling guidance for failed units or circular dependency detection
Model: claude-haiku-4-5-20251001Analyzed: Sep 9, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

  1. v2.0

    Contract changed: description

    ✦ AIClarifies skill activation context in description.

    triggering2026-09-09

    LATEST
  2. v1.2

    Content updated

    ✦ AINo behavioral changes detected.

    2026-07-14

    View This Version
  3. v1.1

    Content updated

    ✦ AIAdds LICENSE file.

    2026-04-20

    View This Version
  4. v1.0

    Seeded from github.com/affaan-m/everything-claude-code

    2026-03-16

    View This VersionInitial version

Use affaan-m/ralphinho-rfc-pipeline in your dev environment

Start a Developer trial

Command Palette

Search for a command to run...