CtrlK
BlogDocsLog inGet started
Tessl Logo

minicpm5-deploy-transformers

Run MiniCPM5-1B or MiniCPM5-2B with Hugging Face Transformers for one-shot Python generation on GPU (bfloat16) or CPU (float32). Use when the user wants a quick Python script, no server, no extra deps, or asks for "Transformers", "AutoModelForCausalLM", "model.generate" with MiniCPM5.

76

Quality

96%

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

92%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 concise, fully executable skill body with clear sequencing, an explicit validation checkpoint, and well-organized sections appropriate for a simple single-purpose task. The only minor weakness is light redundancy between the sampling table and the preceding prose.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence with no padding, but the sampling-defaults table partially re-states the prose on line 62 (enable_thinking/temperature per model), a minor redundancy that could be trimmed.

4 / 5

Actionability

Fully executable copy-paste install commands and run script, an inline CPU variant, a defaults table, and a LoRA snippet — all concrete and covering the common cases.

5 / 5

Workflow Clarity

Clear two-step sequence (Install → Run) with an explicit Validate checkpoint ('A coherent answer to 1+1=?'); this is a non-destructive generation skill so the batch/destruction validation cap does not apply.

5 / 5

Progressive Disclosure

Under 50 lines with well-organized sections and a single one-level-deep reference link to docs/deployment/transformers.md; appropriate for a simple single-purpose skill with no external bundle needed.

5 / 5

Total

19

/

20

Passed

Description

100%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 tight, highly specific description that names models, runtime, hardware modes, and concrete trigger phrases covering both natural and technical terminology. It cleanly answers what the skill does and when to invoke it with minimal conflict risk.

DimensionReasoningScore

Specificity

Names the exact models (MiniCPM5-1B/2B), the runtime (Hugging Face Transformers), the output type (one-shot Python generation), and both hardware modes with dtypes (GPU bfloat16, CPU float32) — comprehensive concrete actions.

5 / 5

Completeness

Explicitly answers both 'what' (run MiniCPM5 with Transformers for one-shot generation) and 'when' via a concrete 'Use when...' clause with multiple trigger conditions.

5 / 5

Trigger Term Quality

Covers natural phrases ('quick Python script', 'no server', 'no extra deps') plus technical trigger terms users would say ('Transformers', 'AutoModelForCausalLM', 'model.generate', 'MiniCPM5').

5 / 5

Distinctiveness Conflict Risk

Scoped specifically to MiniCPM5 on the Transformers path with distinctive triggers (AutoModelForCausalLM, model.generate, no-server), clearly separating it from server-based (vllm/sglang) skills.

5 / 5

Total

20

/

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.

Validation — 15 / 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.