model-selection

Automatically applies when choosing LLM models and providers. Ensures proper model comparison, provider selection, cost optimization, fallback patterns, and multi-model strategies.

Install with Tessl CLI

npx tessl i github:majiayu000/claude-skill-registry-data --skill model-selection

What are skills?

Review — 61%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 9 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

92%

LLM Gateway Service

Model registry and task-based routing

Criteria

Without context

With context

ModelRegistry class

62%

100%

Full model metadata

100%

Capabilities fields

100%

Quality tier values

100%

Pricing in MTok units

100%

ModelRouter class

100%

Named rules with priority

100%

Rule condition callables

100%

Default fallback model

No hardcoded model IDs at call sites

100%

Routing logic documented

100%

Three traffic patterns routed

100%

Without context: $0.2699 · 1m 13s · 13 turns · 20 in / 4,678 out tokens

With context: $0.5293 · 1m 47s · 21 turns · 138 in / 6,473 out tokens

92%

LLM Cost Audit Tool

Cost estimation and batch cost analysis

Criteria

Without context

With context

MTok pricing unit

100%

estimate_cost function

80%

100%

Batch analysis: total_cost_usd

100%

Batch analysis: avg_cost_per_request

100%

Batch analysis: total_tokens

25%

100%

Batch analysis: cost_per_1k_tokens

100%

At least 3 models compared

100%

find_cheapest_model logic

100%

Model registry used

100%

cost_report.txt produced

100%

Reads requests.csv

100%

Cost logged per request

100%

Without context: $0.2475 · 57s · 12 turns · 17 in / 4,079 out tokens

With context: $0.6922 · 2m 19s · 25 turns · 210 in / 9,394 out tokens

96%

41%

Reliable LLM Completion Service

Fallback chain and provider reliability

Criteria

Without context

With context

FallbackChain class

30%

100%

Ordered fallback attempt

100%

model_used in result

100%

fallback_occurred in result

100%

response in result

37%

100%

Warning logged on failure

100%

Exception on all failures

100%

Exception message format

37%

50%

ModelRegistry integration

100%

Demo runs without API keys

100%

Demo shows fallback_occurred=True

20%

100%

Without context: $0.1754 · 52s · 11 turns · 16 in / 3,252 out tokens

With context: $0.5272 · 1m 59s · 21 turns · 275 in / 7,240 out tokens

Evaluated: about 24 hours ago
Agent: Claude Code

Table of Contents

LLM Gateway Service LLM Cost Audit Tool Reliable LLM Completion Service

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.