SKILLEMALL.ai
GitHub ↗ RU Sign in

DC llmrouter

Intelligent LLM proxy that routes requests to appropriate models based on complexity. Save money by using cheaper models for simple tasks. Tested with Anthropic, OpenAI, Gemini, Kimi/Moonshot, and Ollama.

Not recommendedcritical or high security findings · low grade D
modbender/skill-library-mcp Agent Skills author: modbender MIT 1 file body ≈ 2 330 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Intelligent LLM proxy that routes requests to appropriate models based on complexity.

As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice

IntegrationAI and agentstype 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
D
41/100
safety, quality, tests
Safety 60%
23
Quality 40%
69
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
When it triggers w 12
20
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 5

  • high Dangerous commands cmd-persistence SKILL.md:230
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/com.llmrouter.plist
  • high Dangerous commands cmd-persistence SKILL.md:236
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl unload ~/Library/LaunchAgents/com.llmrouter.plist
  • high Dangerous commands cmd-persistence SKILL.md:237
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/Library/LaunchAgents/com.llmrouter.plist
  • high Dangerous commands cmd-persistence SKILL.md:351
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    cat ~/Library/LaunchAgents/com.llmrouter.plist  # Verify paths
Medium and low: 1
  • medium Dangerous commands cmd-persistence SKILL.md:194
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)
    Create `~/Library/LaunchAgents/com.llmrouter.plist`:
    quoted

Files scanned: 1. 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")
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 58/100

  • 0Result and completion. Does not say what the result is
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 21 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2330 tokens
  • 100Progress reporting. Reports progress
  • low 10 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)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 204: enough signal without eating the budget
  • +4Structure: 27 headings
  • +3Step-by-step instructions: 21 items
  • +4Has examples (20 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.