SKILLEMALL.ai
GitHub ↗ RU Sign in

BF free-model-router

为 OpenClaw 提供免费模型智能路由服务，支持本地代理、自动配置、自动轮询、故障切换和配置零侵入。在需要设置免费模型路由、配置 Provider、切换模型或诊断模型可用性问题时使用。

ClawHub Agent Skills author: LaoDao v2.2.0 MIT-0 80 files body ≈ 1 584 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 36/100 · Will not run — References files that are not bundled: {url}

ProcedureSoftware developmentData and analyticstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
90
Quality 40%
64
Run on models
none yet
Process rating
F
36/100
Will not run
References files that are not bundled: {url}
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 10

✓ No critical or high findings

Medium and low: 10
  • low Secrets in code secret-password-literal core/admin/admin-routes.js:1
    Hard-coded password / key literal (may be an example)
    const fs=require("fs"),path=require("path"),auth=require("./auth"),srp=require("./srp"),PUBLIC_DIR=path.join(__dirname,"public");function registerRoutes(e){return{handleAdminRequest:function(e,s){cons
  • low Dangerous commands cmd-pipe-to-shell core/admin/public/js/admin.js:1
    Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed; security demo / example)
    const API_BASE="";let _isLocalAccess=!1;function getAuthHeaders(){if(_isLocalAccess)return{};const e=localStorage.getItem("adminToken");return e?{Authorization:"Bearer "+e}:{}}async function initAuth(
    detectorcode literaldemo
  • low Secrets in code secret-password-literal core/route-engine.js:1
    Hard-coded password / key literal (may be an example)
    const path=require("path"),fs=require("fs"),config=require("./config"),monitorLogger=require("./monitor-logger"),serverClient=require("./server-client"),notifications=require("./notifications"),health
  • low Secrets in code secret-high-entropy-token package-lock.json:82
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…55h/ff8EMaJ+cYhy…4pW+sXf9…fFg==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:209
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…IRT+10J3…DFX+wKFiWjqWp/iCfL…SCR+0w/h1ES/MjA==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:226
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…hjc+H3XB…EI2+jeA8…6pF+UStUCfEpdysA==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:243
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…ZVS+3FYl…bbw==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:413
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…XAu+wKhL…NtR+lZ2B4uwr+usqG…vGw==",
    quoted
  • low Dangerous commands cmd-execpolicy-bypass package.json:29
    Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)
    "build:standalone:win": "powershell -ExecutionPolicy Bypass -File deploy\\deploy.ps1",
    quoted
  • low Secrets in code secret-high-entropy-token scripts/free-model-cli.js:1
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    const http=require("http"),{spawn}=require("child_process"),path=require("path"),fs=require("fs"),os=require("os"),ROUTER_HOST="127.0.0.1",ROUTER_PORT=5678,ROUTER_BASE="http://127.0.0.1:5678",configMo
    detector

Files scanned: 45. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: {url}

Process rating: all ten parameters 36/100

Will not run. References files that are not bundled: {url}
  • 0Tools and files. 1 referenced file(s) missing: {url}
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (free-model-router) differs from the folder (free-model-router-v1)
  • 50Failures and branches. 0 branches, has a failure section
  • 100Steps. 39 steps
  • 100Execution cost. Instruction body is 1584 tokens
  • 100Running it twice. No mutating operations
  • low 14 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 94: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -34 of 5 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +4Structure: 20 headings
  • +3Step-by-step instructions: 39 items
  • +4Has examples (6 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.

External checks

ClawHub: suspicious
The skill is mostly a disclosed local model router, but it also ships under-scoped admin, credit-grant, and updater capabilities that go beyond ordinary routing.
LLM: suspicious (high) · 12 Aug 2026