New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Output Dev Model Selection

by growthxai in growthxai/output

Pick the right LLM model for an Output SDK prompt file. An agent skill from growthxai/output.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Output Dev Model Selection

skills CLI
$ npx skills add growthxai/output --skill output-dev-model-selection -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install growthxai/output output-dev-model-selection --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/growthxai/output.git skills-src && mkdir -p .claude/skills && cp -r skills-src/coding_assistants/claude/plugins/outputai/skills/output-dev-model-selection .claude/skills/output-dev-model-selection && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
output-dev-model-selection
GitHub stars
440
Token cost
~1.9k tokens
SKILL.md length
718 words
Files
1
Skills in repo
52
Repo updated
First seen
Licence
Apache-2.0

At a glance

Pick the right LLM model for an Output SDK prompt file. An agent skill from growthxai/output.

  • Works in 5 steps: Determine task priority → Determine provider → Map provider name to snapshot key → …
  • Writing a new .prompt file
  • SKILL.md covers Live model snapshot, Snapshot shape, Decision flow and See also
  • Calls curl and jq; reaches ai-gateway.vercel.sh

What it does

Output Dev Model Selection is an agent skill from growthxai/output. Pick the right LLM model for an Output SDK prompt file. Use when writing a new .prompt file, reviewing a model choice, or upgrading a stale model. Walks through priority (reasoning/balance/speed/cost), provider selection, and a live lookup against the Vercel AI Gateway model index.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering. It works with Vercel. The repository describes itself as: The open-source TypeScript framework for building AI workflows and agents. Designed for Claude Code describe what you want, Claude builds it, with all the best practices already… The licence is Apache-2.0.

When your agent uses it

  • Writing a new .prompt file
  • Reviewing a model choice
  • Upgrading a stale model

Example prompts

  • “/output-dev-model-selection”

Requirements

  • Pre-approved tools (allowed-tools): Bash(curl *), Bash(jq *), Read, Glob

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Determine task priority
  2. Determine provider
  3. Map provider name to snapshot key
  4. Pick a model from the provider's list
  5. Translate the gateway ID into a prompt-file model string

What it can do on your machine

Read from SKILL.md and the folder at commit 52b51ac. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(curl *)
    • Bash(jq *)
    • Read
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • curl
    • jq

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • ai-gateway.vercel.sh

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Output Dev Model Selection loads about 1.9k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 718 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from growthxai/output at commit 52b51ac, republished under its Apache-2.0 licence (© growthxai). 718 words, ~1,921 tokens.

Download SKILL.mdSave it as .claude/skills/output-dev-model-selection/SKILL.md (or your agent's skills folder).
name
output-dev-model-selection
description
Pick the right LLM model for an Output SDK prompt file. Use when writing a new .prompt file, reviewing a model choice, or upgrading a stale model. Walks through priority (reasoning/balance/speed/cost), provider selection, and a live lookup against the Vercel AI Gateway model index.
allowed-tools
Bash(curl *), Bash(jq *), Read, Glob

Picking a Model for an Output SDK Prompt

This skill is the single source of truth for model selection across Output SDK skills and agents. Other skills link here instead of pinning specific model IDs, because model rosters drift faster than docs.

Live model snapshot

We run this at skill-load time to fetch the 10 most recently released models per provider from the Vercel AI Gateway:

bash
output=$(curl -fsS https://ai-gateway.vercel.sh/v1/models 2>/dev/null | jq '
  .data as $models
  | {
      anthropic: ([ $models[] | select(.id | startswith("anthropic/")) ] | sort_by(.released) | reverse | .[0:10]),
      openai:    ([ $models[] | select(.id | startswith("openai/"))    ] | sort_by(.released) | reverse | .[0:10]),
      google:    ([ $models[] | select(.id | startswith("google/"))    ] | sort_by(.released) | reverse | .[0:10])
    }
' 2>/dev/null)
if [ -n "$output" ]; then printf '%s\n' "$output"; else echo "(snapshot unavailable)"; fi
Snapshot Data
output=$(curl -fsS https://ai-gateway.vercel.sh/v1/models 2>/dev/null | jq '
  .data as $models
  | {
      anthropic: ([ $models[] | select(.id | startswith("anthropic/")) ] | sort_by(.released) | reverse | .[0:10]),
      openai:    ([ $models[] | select(.id | startswith("openai/"))    ] | sort_by(.released) | reverse | .[0:10]),
      google:    ([ $models[] | select(.id | startswith("google/"))    ] | sort_by(.released) | reverse | .[0:10])
    }
' 2>/dev/null)
if [ -n "$output" ]; then printf '%s\n' "$output"; else echo "(snapshot unavailable)"; fi
Snapshot Fallback

If the block above is empty, the script didn't execute automatically — likely because part of it (jq, curl, or network access) is missing. Query and filter the snapshot yourself before continuing.

Snapshot shape

jsonc
{
  "anthropic": [ <model>, ..., <up to 10> ],
  "openai":    [ <model>, ..., <up to 10> ],
  "google":    [ <model>, ..., <up to 10> ]
}

Each <model> is the unmodified gateway payload. Useful fields per model:

FieldWhat to use it for
idThe provider-prefixed ID (eg anthropic/claude-sonnet-4.6) — translate to prompt-file form (Step 5)
releasedUnix timestamp of release. Snapshot is already sorted newest-first per provider.
nameHuman-readable name
descriptionOne-paragraph capability summary — read this when comparing similarly-named tiers
context_windowMax input tokens. Matters when prompts include large context (codebases, long docs)
max_tokensMax single-response output tokens
tagsCapability flags. reasoning, tool-use, vision, file-input, web-search, image-generation, explicit-caching, implicit-caching
pricing.input / pricing.outputPer-token cost (USD). Multiply by 1,000,000 for "per 1M tokens"
pricing.input_cache_readCached-input price — usually 10× cheaper than input
typelanguage for chat models; image models surface as image-generation and aren't valid for .prompt files

Decision flow

Step 1 — Determine task priority

Pick the first row that fits. If unclear, default to reasoning.

PriorityUse when
reasoning (default)Complex multi-step logic, structured output extraction, judges with edge cases, anything where wrong > slow
balanceMost generative work — summarization, classification, content drafting, conversation
speedShort interactive responses, low-latency UI loops, simple transforms
costBulk batch processing where token spend dominates and quality floor is forgiving
Step 2 — Determine provider

Scan existing *.prompt files in the workflow (and its siblings under src/workflows/) and tally what provider: they declare.

  • If the workflow (or sibling workflows) already use one provider, match it. Mixing providers means the runtime needs API keys for each — operational footgun.
  • If no existing prompts, default to anthropic.
  • Only switch provider when the user explicitly asks, or when a feature you need (eg Gemini's useSearchGrounding, OpenAI's maxToolCalls) is provider-specific.
Step 3 — Map provider name to snapshot key

Output SDK provider: values don't always line up with the snapshot keys, since Vercel groups Gemini under google/:

Output SDK providerSnapshot key
anthropicanthropic
openaiopenai
google-vertex (Gemini models)google
google-vertex (Claude models)anthropic (then re-add the @vertex suffix manually)
amazon-bedrockanthropic (then translate to bedrock namespace manually)
Show full SKILL.md (297 more words)Show less
Step 4 — Pick a model from the provider's list

The list is already sorted newest-first. Walk it top-down and pick the first model whose id matches the tier for your priority.

Skip these by default:

  • type != "language" (eg gpt-image-2, gemini-embedding-2) — not valid for .prompt files.
  • IDs containing preview, alpha, or beta. Use stable / GA models only, even if a newer preview/alpha/beta exists. Only pick a non-stable model when the user explicitly asks for it ("use the preview", "I want the new beta", etc.).
PriorityAnthropic — match id containingOpenAI — match idGoogle — match id
reasoningclaude-opus- (and tags includes reasoning)ends with -procontains -pro
balanceclaude-sonnet-base gpt-N.M (no -mini/-nano/-pro suffix)contains -pro
speedclaude-haiku-ends with -miniends with -flash (not -flash-lite)
costclaude-haiku-ends with -nanocontains -flash-lite

Tie-breakers when multiple stable models match:

  • Prefer the unversioned alias (claude-sonnet-4.6) over a dated snapshot (claude-sonnet-4-20250514) unless reproducibility is required (eg eval judges).
  • If two truly equivalent rows exist, take the one with the larger context_window, then lower pricing.input.

If every match in the snapshot is a preview/alpha/beta — meaning the entire tier is in pre-release — surface that to the user and ask before picking one. Don't silently use a preview because it was the only thing available.

Step 5 — Translate the gateway ID into a prompt-file model string

Gateway IDs carry a provider prefix and use dots; prompt-file IDs strip the prefix and use hyphens. Apply two transformations: drop everything up to and including the first /, then replace . with -.

Gateway idPrompt-file model:
anthropic/claude-sonnet-4.6claude-sonnet-4-6
openai/gpt-5.5gpt-5-5
google/gemini-3-flashgemini-3-flash

Drop the translated string into your .prompt frontmatter:

yaml
---
provider: anthropic
model: claude-sonnet-4-6
temperature: 0.7
maxOutputTokens: 4096
---

See also

© growthxai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in coding_assistants/claude/plugins/outputai/skills/output-dev-model-selection of growthxai/output.

Open the folder on GitHubat commit 52b51ac

Compare with similar skills

Output Dev Model Selection next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Output Dev Model Selection compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Output Dev Model Selection this skillgrowthxai/output440—~1.9kAutomated safety check: PassApache-2.0
Build Agentsvercel/vercel-plugin301—~1.4kAutomated safety check: PassCustom licence
AI SDKvercel-labs/ai-facts16821 repos~1.2kAutomated safety check: PassNone
Agent Inspectrajudandigam/agent-inspect165—~424Automated safety check: PassMIT
Sentry Setup AI MonitoringLiorVainer/data-israel130—~1.8kAutomated safety check: PassApache-2.0
Add Model PageComfy-Org/ComfyUI_frontend2.1k—~1.5kAutomated safety check: PassGPL-3.0

Similar skills

  • Build Agents

    vercel/vercel-plugin

    Official

    Default guidance for building AI agents. An agent skill from vercel/vercel-plugin.

    301 GitHub stars~1.4k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • AI SDK

    vercel-labs/ai-facts

    Official

    Answer questions about the AI SDK and help build AI-powered features.

    168 GitHub starsUsed in 21 repos~1.2k tokens
    AI & LLM EngineeringAuto-check passed

  • Agent Inspect

    rajudandigam/agent-inspect

    Local evidence debugger and trajectory-test toolkit for TypeScript AI agents.

    165 GitHub stars~424 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Sentry Setup AI Monitoring

    LiorVainer/data-israel

    Setup Sentry AI Agent Monitoring in any project. An agent skill from LiorVainer/data-israel.

    130 GitHub stars~1.8k tokensUpdated 4 mo ago
    AI & LLM EngineeringAuto-check passed

  • Add Model Page

    Comfy-Org/ComfyUI_frontend

    add, update, or remove a model page entry on the comfy org website.

    2.1k GitHub stars~1.5k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Sentry Setup AI Monitoring

    getsentry/sentry-for-ai

    Official

    Setup Sentry AI Agent Monitoring in any project. An agent skill from getsentry/sentry-for-ai.

    268 GitHub stars~5.5k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: notes

More from growthxai/output

All 52 skills in this repo

  • LLM Output Schema Constraints

    growthxai/output

    Zod schema constraints that Anthropic rejects or silently ignores when sent as structured-output tool definitions via aiSdk.Output.object().

    440 GitHub stars~597 tokensUpdated yesterday
    Auto-check passed

  • Output Build Workflow

    growthxai/output

    Implement an Output SDK workflow from a plan document. An agent skill from growthxai/output.

    440 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed

  • Output Credentials Edit

    growthxai/output

    View, edit, and set encrypted credentials in an Output.ai project.

    440 GitHub stars~1.1k tokensUpdated yesterday
    Auto-check: notes

  • Output Credentials Env Vars

    growthxai/output

    Wire encrypted credentials to environment variables using the credential: convention.

    440 GitHub stars~930 tokensUpdated yesterday
    Auto-check: notes

  • Output Credentials Init

    growthxai/output

    Initialize encrypted credentials for an Output.ai project. An agent skill from growthxai/output.

    440 GitHub stars~803 tokensUpdated yesterday
    Auto-check: notes

  • Output Debug Workflow

    growthxai/output

    Debug Output SDK workflow issues. An agent skill from growthxai/output.

    440 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Output Dev Model Selection

What does Output Dev Model Selection do?

Pick the right LLM model for an Output SDK prompt file. An agent skill from growthxai/output. Output Dev Model Selection is an agent skill from growthxai/output. Pick the right LLM model for an Output SDK prompt file.

When should I use Output Dev Model Selection?

Output Dev Model Selection fits situations like: writing a new .prompt file; reviewing a model choice; upgrading a stale model.

How do I install Output Dev Model Selection in Claude Code?

Run `npx skills add growthxai/output --skill output-dev-model-selection -a claude-code`. Or copy the skill folder (coding_assistants/claude/plugins/outputai/skills/output-dev-model-selection in growthxai/output) into .claude/skills/output-dev-model-selection in your project. Claude Code loads it when a task matches its description.

How do I install Output Dev Model Selection in Codex?

Run `npx skills add growthxai/output --skill output-dev-model-selection -a codex`. Or copy the skill folder (coding_assistants/claude/plugins/outputai/skills/output-dev-model-selection in growthxai/output) into .agents/skills/output-dev-model-selection in your project. Codex loads it when a task matches its description.

Can I use Output Dev Model Selection in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add growthxai/output --skill output-dev-model-selection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/output-dev-model-selection, .gemini/skills/output-dev-model-selection, .github/skills/output-dev-model-selection and .opencode/skills/output-dev-model-selection in your project.

What does Output Dev Model Selection need to run?

Going by SKILL.md and its folder, Output Dev Model Selection needs the command-line tools its instructions call (curl and jq). Its frontmatter pre-approves these tools: Bash(curl *), Bash(jq *), Read, Glob.

Does Output Dev Model Selection access the network?

SKILL.md names 1 domain. In commands or code: ai-gateway.vercel.sh; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Output Dev Model Selection safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Output Dev Model Selection use?

Output Dev Model Selection is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Output Dev Model Selection use?

About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Output Dev Model Selection?

Skills that share tags, products or a category with Output Dev Model Selection: Build Agents (vercel/vercel-plugin, 301 stars), AI SDK (vercel-labs/ai-facts, 168 stars), Agent Inspect (rajudandigam/agent-inspect, 165 stars) and Sentry Setup AI Monitoring (LiorVainer/data-israel, 130 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Output Dev Model Selection?

growthxai (a GitHub organization) maintains it in growthxai/output, which has 440 GitHub stars. The repository holds 52 skills in this directory. The repository was last updated on October 7, 2026.

Source: growthxai/output on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.