Claude Code Plugins

Community-maintained marketplace

Feedback

multi-model

@DNYoussef/context-cascade
8
0

Coordinate multiple models for routing, ensembling, or fallback strategies.

Install Skill

1Download skill
2Enable skills in Claude

Open claude.ai/settings/capabilities and find the "Skills" section

3Upload to Claude

Click "Upload skill" and select the downloaded ZIP file

Note: Please verify skill by going through its instructions before using it.

SKILL.md

name multi-model
description Coordinate multiple models for routing, ensembling, or fallback strategies.
allowed-tools Read, Write, Edit, Bash, Glob, Grep, Task, TodoWrite
model sonnet
x-version 3.2.0
x-category platforms
x-vcl-compliance v3.1.1
x-cognitive-frames HON, MOR, COM, CLS, EVD, ASP, SPC

Purpose

Design model routing and orchestration playbooks with clear guardrails and observability.

Trigger Conditions

  • Use this skill when: Need model selection, fallback, or ensemble flows across providers.
  • Reroute when: If limited to single provider, use its dedicated skill.

Guardrails (Inherited from Skill-Forge + Prompt-Architect)

  • Structure-first: every platform skill keeps SKILL.md, examples/, and tests/ populated; create resources/ and references/ as needed. Log any missing artifact and fill a placeholder before proceeding.
  • Confidence ceilings are mandatory in outputs: inference/report 0.70, research 0.85, observation/definition 0.95. State as Confidence: X.XX (ceiling: TYPE Y.YY).
  • English-only user-facing text; keep VCL markers internal. Do not leak internal notation.
  • Adversarial validation is required before sign-off: boundary, failure, and COV checks with notes.
  • MCP tagging for runs: WHO=multi-model-{session}, WHY=skill-execution, namespace skills/platforms/multi-model/{project}.

Execution Framework

  1. Intent & Constraints — clarify task goal, inputs, success criteria, and risk limits; extract hard/soft/inferred constraints explicitly.
  2. Plan & Docs — outline steps, needed examples/tests, and data contracts; confirm platform-specific policies.
  3. Build & Optimize — apply platform playbook below; keep iterative checkpoints and diffs.
  4. Validate — run adversarial tests, measure KPIs, and record evidence with ceilings.
  5. Deliver & Hand off — summarize decisions, artifacts, and next actions; capture learnings for reuse.

Platform Playbook

  • Workflow patterns:
    • Define routing policies by task, cost, and latency
    • Implement fallback chains with health checks
    • Log decisions and outcomes for continuous tuning
  • Anti-patterns to avoid: Routing without telemetry, Infinite fallback loops without stop conditions, Mixing models without normalizing prompts
  • Example executions:
    • Route generation to cost-effective model with quality checks
    • Blend embeddings from multiple providers for robustness

Documentation & Artifacts

  • SKILL.md (this file) is canonical; keep quick-reference notes in README.md if present.
  • examples/ should hold runnable or narrative examples; tests/ should include validation steps or checklists.
  • resources/ stores helper scripts/templates; references/ stores background links or research.
  • Update metadata.json version if behavior meaningfully changes.

Verification Checklist

  • Trigger matched and reroute considered
  • Examples/tests present or stubbed with TODOs
  • Constraints captured and confidence ceiling stated
  • Validation evidence captured (boundary, failure, COV)
  • MCP tags applied for this run

Confidence: 0.70 (ceiling: inference 0.70) - Standardized platform skill rewrite aligned with skill-forge + prompt-architect guardrails.