alv-gemini

LLM one-shot Q&A, summaries, and generation via SkillBoss API Hub.

Security Scan

The skill is internally consistent: it provides instructions to call SkillBoss's /v1/pilot endpoint and only requests a single SKILLBOSS_API_KEY which matches that purpose.

Purpose & Capability

Name/description state the skill proxies LLM requests via SkillBoss API Hub; the SKILL.md only shows POSTs to https://api.heybossai.com/v1/pilot and requires SKILLBOSS_API_KEY — this credential is appropriate and expected for the claimed functionality.

Instruction Scope

Runtime instructions are limited to making HTTP requests to SkillBoss and returning results (Python and curl examples). They do not instruct reading other environment variables, local files, or transmitting data to unrelated endpoints.

Install Mechanism

No install spec and no code files (instruction-only). That minimizes disk/write risk — nothing is downloaded or executed beyond making network requests at runtime.

Credentials

Only a single environment variable (SKILLBOSS_API_KEY) is required, which is proportional to an API-client skill. No additional unrelated secrets or config paths are requested.

Persistence & Privilege

always is false and there is no install or configuration that would persist or modify other skills. The skill can be invoked by the agent (normal default) but does not request elevated or permanent presence.

Assessment

This skill appears coherent and low-risk, but treat SKILLBOSS_API_KEY like any secret: only provide a key with the minimum required privileges and do not reuse high-privilege credentials. Verify you trust the provider (https://api.heybossai.com) and their privacy/data-retention policies before sending sensitive prompts, since requests and user content will go to an external service. Because this is instruction-only, there was no code to scan — if you need stronger assurance, ask the publisher for an official homepage/terms, or request a vetted connector from your platform instead of a third-party API key. If you have doubts, test with a limited-scope or ephemeral API key first.

LLM via SkillBoss API Hub

Use SkillBoss API Hub for one-shot Q&A, summaries, and text generation. The /v1/pilot endpoint automatically routes to the optimal LLM (including Gemini, Claude, GPT, etc.).

Quick start (Python)

import requests, os

SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

def ask(prompt: str, prefer: str = "balanced") -> str:
    r = requests.post(
        "https://api.heybossai.com/v1/pilot",
        headers={"Authorization": f"Bearer {SKILLBOSS_API_KEY}", "Content-Type": "application/json"},
        json={"type": "chat", "inputs": {"messages": [{"role": "user", "content": prompt}]}, "prefer": prefer},
        timeout=60,
    )
    return r.json()["result"]["choices"][0]["message"]["content"]

# One-shot Q&A
print(ask("Answer this question..."))

# Request JSON output
print(ask("Return JSON: list 3 items", prefer="quality"))

Quick start (curl)

curl -s https://api.heybossai.com/v1/pilot \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"chat","inputs":{"messages":[{"role":"user","content":"Summarize this text..."}]},"prefer":"balanced"}'

Prefer options

• balanced — default, cost-effective
• quality — highest quality model
• price — fastest / cheapest

Notes

• No CLI installation required; all calls go through SkillBoss API Hub.
• Set SKILLBOSS_API_KEY before running.