SKILLEMALL.ai
RU Sign in

AC local-first-llm

Routes LLM requests to a local model (Ollama, LM Studio, llamafile) before falling back to cloud APIs. Tracks token savings and cost avoidance in a persistent dashboard. Use when: (1) user asks to run a task with a local model first, (2) user wants to reduce cloud API costs or keep requests private, (3) user asks to see their token savings or LLM routing dashboard, (4) any request where local-vs-cloud routing should be decided automatically. Supports Ollama, LM Studio, and llamafile as local providers.

ClawHub Agent Skills author: OfflynAI v1.0.0 9 files body ≈ 1 012 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 57/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationAI and agentsData 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
A
93/100
safety, quality, tests
Safety 60%
95
Quality 40%
89
Run on models
none yet
Process rating
C
57/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

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

    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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • medium Dangerous commands cmd-pipe-to-shell references/local-providers.md:12
      Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
      curl -fsSL https://ollama.ai/install.sh | sh
      vendor-host

    Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 57/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 20When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 75Steps. 3 steps
    • 100Tools and files. No external tools needed
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1012 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress

    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 507: enough signal without eating the budget
    • +4Structure: 13 headings
    • +3Step-by-step instructions: 3 items
    • +4Has examples (9 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)
    • +3All 4 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: clean
    This looks like a coherent local-first LLM routing utility, with some disclosure and installation cautions but no artifact-backed evidence of malicious behavior.
    LLM: benign (medium) · VirusTotal: benign · 28 May 2026