Skill Llm Router
Route direct LLM integration work to exactly one provider and region skill when the user names a provider, region, or exact maintained model. Do not recommend models, infer regions, or silently choose among ambiguous provider entries.
Install
$ agentstack add skill-joeylu-runtime-free-llm-integration-skills-skill-llm-router ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-joeylu-runtime-free-llm-integration-skills-skill-llm-router) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Skill LLM Router
Purpose
Select exactly one provider skill before implementation. This router is the only skill in this pack allowed to trigger implicitly.
Routing Rules
- If the user names a provider and region, select that exact provider skill.
- If the user names an exact model but not a provider, search each maintained provider skill's
references/model-catalog.mdfile. - If one exact provider-region match exists, select it.
- If the same model exists in multiple regional skills, require an explicit region or connection profile; do not guess.
- If no exact catalog match exists, stop. Do not recommend a substitute or moving alias.
- After selection, load only the chosen provider
SKILL.mdand its stated shared/provider references. - Never rewrite provider, region, model, API surface, API version, endpoint kind, profile, or route key.
Provider Map
- OpenAI:
LLM/skill-llm-openai/SKILL.md - Aliyun Bailian China Mainland:
LLM/skill-llm-aliyun-bailian-cn/SKILL.md - Aliyun Bailian International:
LLM/skill-llm-aliyun-bailian-intl/SKILL.md - DeepSeek:
LLM/skill-llm-deepseek/SKILL.md - Gemini Developer API:
LLM/skill-llm-gemini/SKILL.md - MiniMax China Mainland:
LLM/skill-llm-minimax-cn/SKILL.md - MiniMax International:
LLM/skill-llm-minimax-intl/SKILL.md
Out of Scope
- model ranking or recommendation
- provider fallback
- region inference from language, IP address, currency, or user location
- adding new models during ordinary implementation
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: joeylu
- Source: joeylu/runtime-free-llm-integration-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.