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.

global
origin:ECC
New~365
v1.2Saved Jul 14, 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

52/100

Grade

C

Adequate

Safety

88

Quality

38

Clarity

56

Completeness

32

Summary

Ralphinho RFC Pipeline is a meta-orchestration skill that guides multi-agent systems through large feature decomposition using RFC-driven DAG execution. It defines a 7-stage pipeline for breaking work into independently verifiable units, managing dependencies, and merging with quality gates—but provides mostly structural templates and process rules without concrete implementation guidance or tool integration.

Detected Capabilities

process orchestrationdependency managementmerge queue enforcementunit tracking and recoveryoutput reporting

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

large feature decompositionrfc-driven workflowmulti-unit orchestrationdependency managementmerge queue integrationrfc pipeline

Referenced Domains

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

github.com

Use Cases

  • >Decompose large features into agent-manageable work units
  • Orchestrate parallel implementation across multiple RFC-derived tasks
  • Enforce dependency validation before unit merges
  • Prevent merge conflicts through queue-based integration
  • Track and recover from stalled or failed work units
  • Generate execution logs and dependency graphs for large projects

Quality Notes

  • Skill is a process template rather than actionable instructions—lacks concrete guidance on how agents execute steps 1–7
  • Unit spec template is well-structured (id, depends_on, scope, acceptance_tests, risk_level, rollback_plan) but no example instantiation provided
  • Merge queue rules are documented but lack implementation details (how does the agent rebase branches, re-run tests, detect failures?)
  • Complexity tiers are defined but not tied to specific tool patterns or execution strategies
  • Recovery procedure is outlined but vague—'snapshot findings' and 'regenerate narrowed unit scope' need concrete instructions
  • Quality pipeline stages are listed but no success criteria defined (what does 'tests pass' look like?)
  • Output artifacts are declared but format/structure not specified—agent cannot verify completion
  • No tool patterns or command examples provided—agent must infer how to interact with git, test frameworks, or CI/CD systems
  • Ties to 'humanplane' patterns and ECC origin suggest domain-specific knowledge not explained for general users
Model: claude-haiku-4-5-20251001Analyzed: Jul 14, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.2

Content updated

2026-07-14

Latest
v1.1

Content updated

2026-04-20

v1.0

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

2026-03-16

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

Command Palette

Search for a command to run...