CtrlK
BlogDocsLog inGet started
Tessl Logo

minicpm5-deploy-lmstudio

Run MiniCPM5-1B or MiniCPM5-2B in LM Studio (desktop GUI) using either the GGUF runtime (cross-platform) or the MLX runtime (Apple Silicon, faster). Includes OpenAI-compatible local server. Use when the user mentions "LM Studio", desktop GUI inference, "lms" CLI, or wants a no-code chat UI for MiniCPM5.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, executable skill body covering both runtimes with concrete commands and a validation checkpoint, plus clean one-level references. Only minor tightening of the MLX paragraph and clarifying the shared $LMS variable would push it to full marks.

Suggestions

Trim the MLX checkpoint paragraph (step 2B) to the essential repo/conversion facts to reduce over-explanation.

Re-declare or note the $LMS variable in section 2B so the MLX path is self-contained and copy-paste ready without 2A.

Move the LM Studio 0.4.13 version note into a versioned/deprecated-style section so the time-sensitive detail does not weigh on conciseness.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence (no basics explained), but the MLX checkpoint paragraph and a few explanatory lines edge toward minor over-explanation that could be trimmed.

4 / 5

Actionability

Copy-paste ready bash for install, both runtime paths, and a validation curl with exact JSON; a small gap is the cross-section reuse of the $LMS variable defined only in 2A.

4 / 5

Workflow Clarity

Numbered steps (1, 2A/2B, 3) with explicit validation — `lms ps` to verify load and a curl with expected output "2" — providing a clear feedback checkpoint.

5 / 5

Progressive Disclosure

Well-organized sections with one-level-deep references (docs/deployment/lmstudio.md and sibling skills) and clear navigation; no nested or buried references.

5 / 5

Total

18

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that names the domain, both runtimes, and the OpenAI server, paired with an explicit trigger clause using natural terms a user would say. Minor room to add format synonyms, but overall highly actionable and distinctive.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and runtime options — GGUF (cross-platform) and MLX (Apple Silicon, faster) — plus an OpenAI-compatible server, giving comprehensive coverage rather than just several actions.

5 / 5

Completeness

Explicitly answers both what (run MiniCPM5-1B/2B in LM Studio via two runtimes with a local server) and when via a concrete "Use when the user mentions..." clause.

5 / 5

Trigger Term Quality

Natural trigger phrases users would say ("LM Studio", desktop GUI inference, "lms" CLI, no-code chat UI) with good coverage, though it omits some synonyms/extensions like file formats.

4 / 5

Distinctiveness Conflict Risk

Clear niche tied to a specific app (LM Studio) and model family (MiniCPM5) with distinct triggers, yielding minimal overlap with sibling deploy skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository
OpenBMB/MiniCPM
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.