MO

model-management

Manage the lifecycle of AI models from integration to empirical testing.

Install

mkdir -p .claude/skills/model-management && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/4590" && unzip -o skill.zip -d .claude/skills/model-management && rm skill.zip

Installs to .claude/skills/model-management

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Add, update, or remove text/image/video/audio/embeddings models. Covers the full lifecycle: files to touch, what to verify, and how to test empirically before merging.
167 charsno explicit “when” trigger
Intermediate

Key capabilities

  • →Audit field-parity for model updates
  • →Execute empirical model performance matrices
  • →Manage model slug and alias mappings
  • →Verify pricing and provider configuration
  • →Generate PR checklists for model lifecycle changes

How it works

Follows a defined checklist of verification steps and test matrices to ensure model parity before committing provider changes to production.

Inputs & outputs

You give it
Changes to model configuration or providers
You get back
Verified parity test results and checklists

When to use model-management

  • →Adding a new AI model provider
  • →Verifying model pricing or capabilities
  • →Updating model aliases
  • →Testing model parity

About this skill

Model management

Use this workflow for every model change. Keep the implementation minimal, preserve the public contract unless the user explicitly approves a change, and prove provider behavior with real requests.

Load context first

  1. Read the repository AGENTS.md.
  2. Read the live registry entry, runtime config, handler, schemas, and tests. The repository is the source of truth for what Pollinations currently offers.
  3. Read the relevant local active plan when present:
    • temp/manage_inference.md
    • temp/manage_inferenceport.md
    • temp/manage_gpus.md
    • temp/manage_azure_limits.md
  4. Check GitHub for open or merged PRs that may already implement or conflict with the work.
  5. Check current official provider documentation, catalog, pricing, availability, quotas, and deprecation notices. Then probe the exact route; the live response wins over documentation.

The temp plans are ignored operational state, not repository truth. When working in a linked worktree where they are absent, locate the primary checkout with git worktree list and read them there. Never copy balances, prices, PR statuses, quotas, or candidate rankings into this skill.

Read operating-policy.md before recommending a route or model. Read only the other references needed for the task:

TaskRequired references
Find code or run locallyrepository-and-local-testing.md
Add, update, reroute, rename, or removechange-and-test-matrix.md
New model, provider, model ID, or pricebilling-verification.md

Mandatory confirmation gate

Apply this gate only to a proposed tracked model mutation. Do not turn a read-only status confirmation, an approval of an already-documented planning decision, or a correction of an operational fact into a different mutation. Treat a generic “confirm” as approval only for the exact contract just shown.

Do not edit any model until the user confirms its complete business and inference contract. Inspect the code and provider first; do not ask the user to discover values for you.

Show one complete row per model:

FieldRequired value
Canonical namePublic model ID after the change
AliasesEvery compatibility alias, or none
priceMultiplierExact multiplier after provider cost
paidOnlyWhether purchased pack balance is required
Pollinations GPUyes only if Pollinations operates the production hardware
Registry providerConfigured primary provider
Primary routeProvider, deployment/host, and exact upstream model ID
Best fallback candidateProvider, deployment/host, exact upstream model ID, and why it is the best viable alternative; or none found with the searched routes
Pollinations fallbackuse <candidate> or none, with the reason for declining or lacking a viable candidate

Ask:

Please confirm: canonical name X, aliases A/none, price multiplier M, paid-only yes/no, Pollinations GPU yes/no, registry provider P, primary route R, best fallback candidate C/none found, and Pollinations fallback decision use C/none. Are all of these correct?

An answer approves only the values shown. If a value is unknown, inferred, conflicting, or route-dependent, label it UNKNOWN, explain the evidence, and wait for that exact decision. A batch approval is valid only when every row is complete.

Public API changes require separate confirmation

Model approval does not authorize adding, renaming, removing, or changing a public endpoint, method, transport, request or response schema, streaming behavior, or event protocol. Do not propose an API-surface change without a concrete user or developer problem it solves.

Before editing, present:

  • the user/developer problem and the current public contract;
  • the exact proposed routes, methods, transports, schemas, streaming behavior, and events;
  • the compatibility reference, resolved by the order in step 4;
  • whether the change is additive, behavioral, deprecating, or breaking, and the affected clients;
  • the migration, coexistence, and removal plan, or none.

State plainly: This adds/changes the public API: ... Then ask for explicit confirmation of that exact API change. If the problem, standard, or compatibility impact is unclear, do not edit.

Secrets are a separate approval

Model approval never authorizes adding, rotating, synchronizing, deploying, revoking, or otherwise mutating a credential. Follow the exact approval wording, execution order, verification, and rollback rules in AGENTS.md. Do not duplicate or weaken that process here.

Workflow

1. Reconcile current state

  • Resolve aliases to the canonical registry entry.
  • API keys store model categories and canonical model IDs. A rename keeps working for keys that stored the old ID only while the old ID stays an alias. A model that changes category changes which restricted keys reach it; state that in the PR.
  • Models served at /alpha/decisions use category: "decision". Keys need decision on that route; on chat endpoints, text also allows them.
  • Audit every modality registry and every model change merged to main since the current production revision; production can lag behind main.
  • If a model or provider is missing from the registry, check git log --all -- <path> and gh pr list --state merged --search <model> before re-adding it — it may have been removed on purpose, added and reverted, or replaced.
  • Trace every reachable runtime route and any configured fallback.
  • Distinguish the configured provider from the provider that served an observed request.
  • Compare the intended change with open PRs and active plan entries.
  • Remove shipped work from active plans after production verification; do not keep a completed archive.

2. Research the exact route

  • Use official provider/model sources for release, model identity, pricing, regions, preview status, quotas, rate limits, context, inputs, outputs, tools, caching, and deprecation.
  • Deduplicate the canonical model across providers.
  • List material route differences. Equal model names do not prove equal capabilities.
  • Probe the exact deployment and request shape Pollinations will use.
  • For every addition or modification, run a fresh web search across provider catalogs and official documentation to discover viable fallback routes; do not rely only on repository integrations or remembered availability. Verify each serious candidate against its current official model page and pricing, then probe the exact route. Compare checkpoint identity, capabilities, parameters, formats, safety/privacy, availability, latency, price, permissions, and billing. Recommend the best candidate or state none found; never omit the fallback decision because the primary route is healthy.
  • Inspect provider-managed routing/fallback defaults and controls. Report identity, capability, pricing, residency, and observability tradeoffs.

For direct Novita discovery, use the supported model catalog and account quotas with an existing authorized key. Quota queries require modal=llm; query RPM and TPM separately with productType=Public Endpoint and the exact model as quotaObject, then check the returned identity. The OpenAI-compatible base is https://api.novita.ai/openai/v1; probe the exact upstream model using Chat Completions. Request stream_options.include_usage for streaming and prove terminal usage, cache/reasoning billing, capabilities and burst capacity through local Gen before routing traffic. Gateway availability does not prove direct access or independent capacity: OpenRouter/Vercel routes backed by Novita can share the same upstream pool. Keep direct provider attribution and charges distinct from gateway-billed traffic; use the Economics Novita connector guide for supported billing sources. Preserve the existing public contract and fallback mechanism.

3. Confirm the contract

Present the mandatory row and obtain explicit confirmation before editing. If a capability or access change is intentional, state it plainly.

4. Implement the smallest complete change

  • Canonical public IDs use <publisher-slug>/<official-model-slug>. Keep both components lowercase, preserve the publisher's model family and version, and follow the publisher's public slug when one exists. Never invent, drop, or silently advance a version.
  • publisher is the human-readable publisher (OpenAI, Anthropic, xAI), not the inference provider. Keep provider deployment IDs, casing, punctuation, and revision suffixes internal when they are routing details rather than the publisher's public model identity.
  • Never encode an inference provider in a public canonical ID. Deduplicate the same publisher model across providers behind one public identity and declare automatic routing through the registry's ordered fallback relationship.
  • Name hidden fallback registry entries <public-canonical-id>:<provider>. The public registry key, catalogs, request model, and permissions remain the public ID. Keep fallback identity separate from priority: never use :fallback, numbered fallback suffixes, or priority labels in these IDs.
  • For a pinned OpenRouter endpoint, append a meaningful qualifier from the start: <public-canonical-id>:<provider>:<route-qualifier>, such as google/gemini-2.5-flash-lite:openrouter:vertex-global or google/gemini-2.5-flash-lite:openrouter:ai-studio. Distinguish multiple deployments through the same provider explicitly. Use lowercase labels; never encode priority or the temporary fall

Content truncated.

When not to use it

  • →When deploying services directly to production
  • →For investigating model-internal runtime errors

Prerequisites

Development access to model registry

Limitations

  • →Requires manual execution of empirical tests
  • →Limited to tracking model registration and parity
  • →Not a replacement for real-time model debugging

How it compares

It replaces ad-hoc testing with a standardized lifecycle process, reducing the risk of regression in AI model integrations.

Compared to similar skills

model-management side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
model-management (this skill)15moCautionIntermediate
llama-factory1512moNo flagsAdvanced
senior-prompt-engineer711moReviewAdvanced
dspy410moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

llama-factory

zechenzhangAGI

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

15112

senior-prompt-engineer

davila7

World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.

743

dspy

davila7

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

430

agentic-development

alinaqi

Build AI agents with Pydantic AI (Python) and Claude SDK (Node.js)

19

model-merging

davila7

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

32

context-engineering

mrgoonie

Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, optimizing token usage, implementing memory systems, building multi-agent coordination, evaluating agent performance, or developing LLM-powered pipelines. Covers context fundamentals, degradation patterns, optimization techniques (compaction, masking, caching), compression strategies, memory architectures, multi-agent patterns, LLM-as-Judge evaluation, tool design, and project development.

10

Search skills

Search the agent skills registry