model-pilot

Match task complexity to the right model. Quick heuristic check before expensive tasks — recommends cheaper models when quality won't suffer. Fetches live pricing via web_fetch. Use when: (1) starting an expensive task, (2) 'can a cheaper model do this?', (3) 'is this the right model?', (4) comparing model costs. Homepage: https://clawhub.ai/skills/model-pilot

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "model-pilot" with this command: npx skills add tommot2/model-pilot

Model Pilot v2.0

Install: clawhub install model-pilot

Stop overpaying for intelligence. Match every task to the cheapest model that delivers the quality you need.

Language

Detect from user's message language. Default: English.

When to Activate

  • User explicitly asks about model choice or cost
  • A task is starting that will be expensive (agent judgment — don't analyze trivial tasks)
  • User says "save tokens", "cheaper model", "right model?"

Do NOT activate for trivial tasks — formatting, greetings, simple lookups.

Quick Complexity Check

Before an expensive task, ask yourself:

1. What is the task? (classify)
2. What model is active?
3. Could a cheaper model handle this equally well?
4. If yes → recommend switch + estimated savings
5. If no → proceed, explain why

Tier Classification

TierTasksModel
🟢 RoutineFormatting, Q&A, reminders, greetings, file opsCheapest available
🟡 IntermediateEmail drafting, code review, data analysis, translationsMid-tier
🔴 ComplexArchitecture decisions, creative writing, debugging complex issuesBest available

Signal: Task needs <1000 output tokens + no creativity = Tier 1.

Live Pricing

Fetch current pricing when user asks about costs:

web_fetch https://z.ai/pricing
web_search "openai gpt-4o pricing per token"

Do NOT hardcode prices — they change frequently. Always fetch live.

Cost Estimation

Quick formula:

Estimated cost = (input_tokens / 1M × input_price) + (output_tokens / 1M × output_price)

Show to user:

Model: GLM-5-Turbo
  Input: ~5K tokens
  Output: ~2K tokens
  Estimated cost: ~$0.002
  Could use: GLM-4 (~$0.001) — saves ~50%

Quick Commands

User saysAction
"right model?"Quick complexity check
"model cost"Cost estimate for current task
"compare models"Live pricing comparison
"cheaper option"Find cheaper model for same task

Guidelines for Agent

  1. Don't waste tokens analyzing cheap tasks — check only for expensive ones
  2. Use live pricing — never hardcode
  3. Be honest about quality — if cheaper means worse, say so
  4. Keep it quick — 5 seconds of thinking max
  5. Match user language

What This Skill Does NOT Do

  • Does NOT switch models automatically — recommends only
  • Does NOT persist anything
  • Does NOT access credentials
  • Does NOT modify any files

More by TommoT2

  • cross-check — Auto-detect and verify assumptions in your responses
  • context-brief — Persistent context survival across sessions
  • setup-doctor — Diagnose and fix OpenClaw setup issues

Install the full suite:

clawhub install model-pilot cross-check context-brief setup-doctor

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

Aliyun Drive Uploader

阿里云盘文件上传与管理。使用 refresh_token 认证,支持大文件分片上传、自动创建文件夹、文件搜索、分享链接等。当用户需要上传文件到阿里云盘、创建文件夹、搜索文件、管理分享链接时使用。

Registry SourceRecently Updated
General

Skill Manager All In One | 一站式技能管理器

Manage OpenClaw skills end-to-end. 一站式管理 OpenClaw 技能的创建、修改、发布、更新、升版与审计。

Registry SourceRecently Updated
General

Contact Centre Grok Pack

Triage call-centre and voice support transcripts into summaries, sentiment, urgency, routing queues, and follow-up actions. Use for OpenClaw-ready Grok/voice...

Registry SourceRecently Updated
General

3dgs Method Compare

Compare 3D Gaussian Splatting variants across multiple dimensions. Generates detailed comparison tables covering primitive representation, rendering formulat...

Registry SourceRecently Updated