Explain

Skill avanrossum/claude-local-llm-skills/skills/explain

Explain what a file or function does using the local LLM — quick context without burning Claude tokensFrom its SKILL.md

Install

npx -y skills add avanrossum/claude-local-llm-skills --skill explain

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.1 KB, as published. Nobody here has run it

/explain — Explain Code via Local LLM

You are explaining code using the local/remote LLM to save Claude tokens. Good for quick "what does this do" questions during onboarding or exploration.

Arguments: $ARGUMENTS

Step 1 — Resolve Target

Parse the argument:

path/to/file.py — explain the whole file
path/to/file.py:function_name — explain a specific function (read the file, extract just that function)
path/to/file.py:ClassName — explain a specific class

If a function/class name is given, use Grep to find it in the file and extract it with surrounding context.

Step 2 — Send to Local LLM

LLM_API_TOKEN=$(security find-generic-password -a "$USER" -s "lm-studio-token" -w 2>/dev/null)
curl -s "${LLM_BASE_URL:-https://lm.mipyip.com}/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LLM_API_TOKEN" \
  -d '{
    "model": "'"${LLM_MODEL:-qwen/qwen3.5-35b-a3b}"'",
    "messages": [
      {"role": "system", "content": "You are a senior developer explaining code to a colleague. Explain what this code does in plain language:\n- What is its purpose?\n- How does it work (key logic flow)?\n- What are its inputs and outputs?\n- Any notable patterns, side effects, or gotchas?\n\nBe concise but thorough. Aim for 5-15 lines."},
      {"role": "user", "content": "{content}"}
    ],
    "stream": false,
    "temperature": 0.3
  }'

Environment variables:

LLM_BASE_URL — override endpoint (default: https://lm.mipyip.com)
LLM_MODEL — override model (default: qwen/qwen3.5-35b-a3b)
Bearer token from macOS Keychain (lm-studio-token) or LLM_API_TOKEN env var

Step 3 — Present Results

Relay the explanation directly. Don't add your own commentary unless the user asks follow-up questions — at that point you can use your own capabilities.

Error Handling

If the LLM is unreachable, explain the code yourself
If the file doesn't exist, say so