← 返回 Skills 市场

Free Ride Xiaoshu

Name: Free Ride Xiaoshu
Author: xiaomaju-888

作者 xiaomaju-888 · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

总下载

当前安装

版本数

在 OpenClaw 中安装

/install free-ride-xiaoshu

功能描述

Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates opencla...

使用说明 (SKILL.md)

FreeRide - Free AI for OpenClaw

What This Skill Does

Configures OpenClaw to use free AI models from OpenRouter. Sets the best free model as primary, adds ranked fallbacks so rate limits don't interrupt the user, and preserves existing config.

Prerequisites

Before running any FreeRide command, ensure:

OPENROUTER_API_KEY is set. Check with echo $OPENROUTER_API_KEY. If empty, the user must get a free key at https://openrouter.ai/keys and set it:
```
export OPENROUTER_API_KEY="sk-or-v1-..."
# Or persist it:
openclaw config set env.OPENROUTER_API_KEY "sk-or-v1-..."
```
The freeride CLI is installed. Check with which freeride. If not found:
```
cd ~/.openclaw/workspace/skills/free-ride
pip install -e .
```

Primary Workflow

When the user wants free AI, run these steps in order:

# Step 1: Configure best free model + fallbacks
freeride auto

# Step 2: Restart gateway so OpenClaw picks up the changes
openclaw gateway restart

That's it. The user now has free AI with automatic fallback switching.

Verify by telling the user to send /status to check the active model.

Commands Reference

Command	When to use it
`freeride auto`	User wants free AI set up (most common)
`freeride auto -f`	User wants fallbacks but wants to keep their current primary model
`freeride auto -c 10`	User wants more fallbacks (default is 5)
`freeride list`	User wants to see available free models
`freeride list -n 30`	User wants to see all free models
`freeride switch \x3Cmodel>`	User wants a specific model (e.g. `freeride switch qwen3-coder`)
`freeride switch \x3Cmodel> -f`	Add specific model as fallback only
`freeride status`	Check current FreeRide configuration
`freeride fallbacks`	Update only the fallback models
`freeride refresh`	Force refresh the cached model list

After any command that changes config, always run openclaw gateway restart.

What It Writes to Config

FreeRide updates only these keys in ~/.openclaw/openclaw.json:

agents.defaults.model.primary — e.g. openrouter/qwen/qwen3-coder:free
agents.defaults.model.fallbacks — e.g. ["openrouter/free", "nvidia/nemotron:free", ...]
agents.defaults.models — allowlist so /model command shows the free models

Everything else (gateway, channels, plugins, env, customInstructions, named agents) is preserved.

The first fallback is always openrouter/free — OpenRouter's smart router that auto-picks the best available model based on the request.

Watcher (Optional)

For auto-rotation when rate limited, the user can run:

freeride-watcher --daemon    # Continuous monitoring
freeride-watcher --rotate    # Force rotate now
freeride-watcher --status    # Check rotation history

Troubleshooting

Problem	Fix
`freeride: command not found`	`cd ~/.openclaw/workspace/skills/free-ride && pip install -e .`
`OPENROUTER_API_KEY not set`	User needs a key from https://openrouter.ai/keys
Changes not taking effect	`openclaw gateway restart` then `/new` for fresh session
Agent shows 0 tokens	Check `freeride status` — primary should be `openrouter/\x3Cprovider>/\x3Cmodel>:free`

安全使用建议

This skill appears to do what it says (manage OpenRouter free models and update your OpenClaw config), but there are a few red flags to check before installing: - Verify the source/trust: the registry metadata lists no homepage/source; confirm the package origin (GitHub repo) and that the author is trustworthy. Clone and inspect the repository before pip installing. - Back up your OpenClaw config (~/.openclaw/openclaw.json) before running the tool; it will modify agents.defaults.model, fallbacks, and models. - Confirm the OPENROUTER_API_KEY requirement: provide a dedicated OpenRouter key and consider its permissions; the watcher will make frequent API calls (health checks and rotations) which will use that key. - Because the package installs code (setup.py) and creates CLI binaries, review main.py and watcher.py fully (they are present and straightforward) to ensure there are no hidden network endpoints or unexpected host URLs. The code appears to call only openrouter.ai and uses local cache/state files under ~/.openclaw. - If you want lower risk, run the watcher in a constrained environment (not with elevated privileges), and test 'freeride list' and 'freeride status' first to observe behavior. Given the metadata inconsistencies (declared required env var absent from top-level registry metadata and missing/duplicated install instructions), proceed with caution and manual review before granting persistent use.

功能分析

Type: OpenClaw Skill Name: free-ride-xiaoshu Version: 1.0.0 The FreeRide skill bundle is a legitimate utility for managing free AI models from OpenRouter within the OpenClaw environment. It fetches model lists from the official OpenRouter API, ranks them based on technical criteria, and updates the local OpenClaw configuration file (~/.openclaw/openclaw.json) to automate model switching and fallback handling. The code (main.py, watcher.py) is well-documented, lacks obfuscation, and performs only the actions described in its documentation without any signs of data exfiltration or malicious intent.

能力评估

ℹ Purpose & Capability

The name/description match what the code and SKILL.md do: fetch free models from OpenRouter, rank them, and update OpenClaw config. Modifying ~/.openclaw/openclaw.json and restarting the gateway is expected for this purpose. However, registry metadata at the top claims 'Required env vars: none' while skill.json and SKILL.md require OPENROUTER_API_KEY — an inconsistency in declared requirements and metadata source information (source/homepage unknown) that should be resolved.

ℹ Instruction Scope

SKILL.md instructs only the actions necessary for the stated purpose: set OPENROUTER_API_KEY, install the freeride package locally, run freeride commands, and restart openclaw gateway. It explicitly reads/writes only ~/.openclaw/openclaw.json and stores caches/state under ~/.openclaw — which is within the skill's domain. No instructions request unrelated system files or unrelated credentials. Note: the SKILL.md recommends installing (pip install -e .) which results in code being written/executed locally — this expands runtime surface compared to a purely instruction-only skill.

ℹ Install Mechanism

There is no registry install spec in the metadata shown, but the package includes setup.py, requirements.txt, and SKILL.md/README install instructions that direct the user to pip install -e . (and an npx clawhub install command in README/skill.json). The Python dependency is only 'requests', from PyPI (reasonable). This is not high-risk, but the mismatch between 'no install spec' in registry metadata and multiple install instructions in files is a packaging/integrity inconsistency to be aware of.

ℹ Credentials

The skill requires a single service credential (OPENROUTER_API_KEY) which is proportional to the described functionality. The code will also read the key from ~/.openclaw/openclaw.json if present. That behavior is reasonable, but the top-level registry metadata incorrectly lists no required env vars while skill.json and SKILL.md declare the API key as required — this discrepancy reduces confidence in the metadata accuracy.

✓ Persistence & Privilege

always: false and normal autonomous invocation are used. The skill writes only to its own cache/state files and to the OpenClaw config (~/.openclaw/openclaw.json) which is expected for a skill that reconfigures OpenClaw. It does not request system-wide privileges or modify other skills' config beyond the stated keys.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install free-ride-xiaoshu
安装完成后，直接呼叫该 Skill 的名称或使用 /free-ride-xiaoshu 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release of FreeRide for OpenClaw - Automatically configures OpenClaw to use free AI models from OpenRouter. - Ranks and selects the best free model as primary; adds automatic fallbacks for seamless switching. - Writes only model-related keys to config, preserving all other user settings. - Provides CLI commands for setup, model switching, fallback management, and troubleshooting. - Includes optional watcher for handling automatic model rotation on rate limits.

元数据

Slug free-ride-xiaoshu

版本 1.0.0

许可证 MIT-0

累计安装 1

当前安装数 1

历史版本数 1

常见问题