CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

veomni-gpu-to-npu

Plan and migrate an existing VeOmni GPU model implementation to Ascend NPU. Use when the GPU patchgen path already works and the model needs a migration file inventory, dependency auditing, NPU operator selection, patchgen integration, multimodal wrapper adaptation, or focused model tests. Gemma 3 is the worked example.

Quality

94%

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

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.

An excellent, dense, highly actionable skill body: concrete commands and code, explicit validation checkpoints with reproducibility requirements, and a completion checklist, all while assuming Claude's competence. The only structural improvement is moving specialized detail blocks (op-selection table, multimodal distributed-training mechanics, key-mapping tables) into reference files to slim the main body.

DimensionReasoningScore

Conciseness

Nearly every line carries non-obvious, VeOmni-specific operational knowledge ("Model classes must own instance-local `VeomniOp` handles", "Never import a vendor kernel directly from generated modeling", the RMSNorm variant and checkpoint key-mapping specifics) with no explanations of concepts Claude already knows and no padded sections. Every token earns its place for a task of this complexity.

5 / 5

Actionability

Provides real executable commands (rg audits, `patchgen ... --diff -v`, `python -m py_compile`, `make quality`) and concrete code for the patch spec, VeomniOp handle construction, and device-dispatch __init__. The `<model>` placeholders are explicitly justified ("Adjust the rows to the target model", Gemma 3 named as the worked example), which the guidelines permit, and no key execution detail is missing.

5 / 5

Workflow Clarity

A clear four-phase sequence (Audit → Implement → Adapt multimodal wrappers → Generate and Validate) with explicit validation at each step: run PatchGen twice and require no diff, py_compile, import check, `make quality`, focused model tests, and a Completion Checklist. Conditional branches ("If the required `(op, variant, implementation)` row is missing, follow `veomni-new-op`") plus hard-failure rules ("Treat unexpected keys or uninitialized vision/projector parameters as hard failures") provide error-recovery guidance.

5 / 5

Progressive Disclosure

Sections are well organized and external references are clearly signaled and one level deep ("Read these references before changing model code"; "Read `.agents/skills/veomni-patchgen-model/references/multimodal.md`"), but the ~160-line body inlines detail-dense material — the operator-selection table, multimodal DDP dummy-forward mechanics, and checkpoint key mapping — that would naturally live in reference files, and no bundle files exist to offload it. This is "good structure; minor organization gaps" rather than fully appropriate splitting.

4 / 5

Total

19

/

20

Passed

Description

88%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 description: it states a concrete capability set and an explicit, well-conditioned Use-when clause that clearly separates it from generic model work. Keyword coverage is domain-appropriate but could add a few natural synonyms ("port", "torch_npu", "CANN") to strengthen triggering.

DimensionReasoningScore

Specificity

Names the core action ("Plan and migrate an existing VeOmni GPU model implementation to Ascend NPU") and enumerates concrete sub-actions — "migration file inventory, dependency auditing, NPU operator selection, patchgen integration, multimodal wrapper adaptation, or focused model tests" — covering the full workflow rather than just a few actions.

5 / 5

Completeness

Explicitly answers both: what ("Plan and migrate an existing VeOmni GPU model implementation to Ascend NPU") and when ("Use when the GPU patchgen path already works and the model needs a migration file inventory, dependency auditing, ..."). The when-clause is explicit and states concrete preconditions, matching the top anchor.

5 / 5

Trigger Term Quality

Includes strong natural domain terms ("VeOmni", "GPU", "Ascend NPU", "migrate", "patchgen", "Gemma 3") that a user in this repo would say, but misses a few common variations such as "port", "torch_npu", or "CANN". This fits "good keyword coverage; a few natural terms missing" rather than comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (GPU-to-NPU migration gated on "the GPU patchgen path already works"), but the phrase "patchgen integration" and the cited sibling skills (veomni-patchgen-model, veomni-new-op) create minor overlap risk with closely related skills — "mostly distinct; minor overlap risk" rather than minimal conflict risk.

4 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

ByteDance-Seed/VeOmni

Path

.agents/skills/veomni-gpu-to-npu/SKILL.md

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.