CtrlK
BlogDocsLog inGet started
Tessl Logo

minicpm5-deploy-ollama

Run MiniCPM5-1B via Ollama on macOS / Linux laptop using the released GGUF. Use when the user wants "ollama run", "ollama pull", a Modelfile-driven setup, or one-line laptop deployment.

73

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

96%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.

The body is a tight, fully executable deployment runbook with a clear sequenced workflow and an explicit validation checkpoint. Its only weakness is progressive disclosure: it leans slightly past the simple-skill threshold and points to an external doc that is not present in the bundle.

Suggestions

Either remove the external Reference link to docs/deployment/ollama.md (not present in the bundle) or add that file so the reference resolves and navigation is trustworthy.

If the skill stays single-purpose, trim toward the ~50-line simple-skill range or move the think-mode/raw-mode detail into a bundled reference file to strengthen progressive disclosure.

DimensionReasoningScore

Conciseness

The body is lean: it never explains what Ollama, GGUF, or quantization are, jumps straight to a compact input table and executable bash, and every section (input, steps, think mode, pitfalls, when-not-to-use) earns its place.

5 / 5

Actionability

All guidance is copy-paste executable — install commands, huggingface-cli download, a complete Modelfile, ollama create/run, an OpenAI-compatible validation curl, and a raw-mode think example — covering the common cases with real URLs and values.

5 / 5

Workflow Clarity

A clearly numbered install→download+Modelfile→create+run→validate sequence includes an explicit validation checkpoint with expected output ('"2"') and a pitfalls section with error-recovery guidance, matching the 5 anchor.

5 / 5

Progressive Disclosure

Content is well-organized into clearly headed, single-purpose sections with no nested or buried references, but it slightly exceeds the simple-skill line count and its one external reference (docs/deployment/ollama.md) is not present in the bundle, a minor organization gap below the 5 anchor.

4 / 5

Total

19

/

20

Passed

Description

87%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.

The description is specific, uses third person, and pairs a clear capability statement with concrete, naturally phrased triggers, making it both complete and distinctive. Minor keyword synonym coverage is the only gap.

DimensionReasoningScore

Specificity

Names the concrete stack (MiniCPM5-1B, Ollama, macOS/Linux laptop, released GGUF) and the core action ('Run'), but does not enumerate the full create/run/validate surface, leaving minor coverage gaps consistent with the 4 anchor.

4 / 5

Completeness

Explicitly answers both 'what' (run MiniCPM5-1B via Ollama on a laptop using the released GGUF) and 'when' (a concrete 'Use when...' clause listing specific triggers), matching the 5 anchor; the 'when' is specific rather than merely adequate.

5 / 5

Trigger Term Quality

Quotes natural user phrases verbatim ('ollama run', 'ollama pull', 'Modelfile-driven setup', 'one-line laptop deployment'), giving good keyword coverage; a few synonyms/extensions are absent so it is not the 5-level comprehensive example.

4 / 5

Distinctiveness Conflict Risk

Scoped to a specific model + runtime + platform niche with distinct triggers (MiniCPM5-1B, Ollama, macOS/Linux laptop), giving minimal overlap with other deployment skills.

5 / 5

Total

18

/

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.