CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

veomni-patchgen-model

Author or refresh a VeOmni model's patchgen-generated modeling under generated/ — GPU and/or NPU config, dense or MoE, text / VLM / Omni. Covers the patchgen decorators, sharing patches across sibling models via name_map, MoE fused-expert weight loading, Ulysses SP in multimodal forwards, __init__.py registration, running codegen, and the test cases. This is the modeling step of adding a new model, not only of refreshing an existing one. Trigger: 'add patchgen for a model', 'write a patch_gen_config', 'regenerate the generated modeling', 'add NPU patchgen', 'port a model to patchgen', 'transformers v5 migration'. Never hand-edit anything under generated/.

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

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.

An exceptionally actionable, well-sequenced protocol: every phase has executable commands and validation checkpoints, and category-specific material is properly split into real, well-signaled reference files. The main cost is token weight — some pitfalls are duplicated between phases and the Common Pitfalls section, and a few entries carry internal implementation history that could be trimmed or pushed to a reference file.

Suggestions

Deduplicate the partial-rotary/liger exception and the e2e -k mismatch guidance — keep the operational rule in the phase and drop the restated copy in Common Pitfalls (or vice versa, pointing to the phase).

Trim the empty-class-body pitfall to the symptom, the check (import the generated file), and the affected-model note; move the codegen.py _replace_method_body_with_preserved internals into a reference file.

The very long caveat inside the name_map table cell (Phase 2 patch primitives) would be more readable and cheaper as a short example block below the table.

DimensionReasoningScore

Conciseness

The body is dense with VeOmni-specific contract knowledge Claude cannot know (name_map dataclass caveat, partial-rotary liger NaN, loss_function signature), but it is not lean: the partial-rotary exception and the e2e -k mismatch pitfall each appear twice (Phase 2/7 and Common Pitfalls), and the empty-class-body pitfall narrates codegen.py internals and migration history ("This is wired up since the Llama migration", the list of 9 modeling files). This fits 'efficient; minor instances of over-explanation that could be trimmed' rather than the every-token-earns-its-place anchor.

4 / 5

Actionability

Fully executable throughout: copy-paste shell commands (curl -fsSL reference fetch, uv sync, patchgen invocations, per-suite pytest -k lines), a complete PatchConfig skeleton, three concrete __init__.py wiring patterns, and a keyword-rules table mapping each test suite to the exact -k argument including the no-underscore VL id convention. Matches the copy-paste-ready anchor with common cases covered.

5 / 5

Workflow Clarity

Phases 0-8 are clearly sequenced with an upfront suggested plan, and nearly every phase ends in an explicit "Validation" checkpoint; Phase 7 adds acceptance criteria and error-recovery loops (re-check with --collect-only when -k selects 0, use patchgen --check --fix instead of re-running patchgen to avoid the ruff/patchgen ping-pong). This matches the anchor for clear sequence, explicit validation, and feedback loops.

5 / 5

Progressive Disclosure

Scored against the actual bundle: three real one-level-deep references (references/model-examples.md, references/moe.md, references/multimodal.md) routed by a "What to read for your model" table, with the spine explicitly noting a dense text model "skips about 380 lines of MoE and multimodal material". Category-specific detail is correctly offloaded, references are clearly signaled with when-to-load conditions, and repo docs are named with paths. Matches the clear-overview/well-signaled-references anchor.

5 / 5

Total

19

/

20

Passed

Description

96%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: concrete, comprehensive capability coverage, third-person voice, and an explicit trigger clause with natural phrases. The only weakness is that the 'transformers v5 migration' trigger is broader than the skill's actual scope, creating minor overlap risk with sibling skills that own the pin-bump workflow.

Suggestions

Narrow the 'transformers v5 migration' trigger to something like 'refresh generated modeling after a transformers pin bump' so it does not capture requests that belong to the dependency-update skill.

Consider stating the boundary inline (e.g. 'for the modeling layer only; use the onboarding skill for trainer/data integration') to further reduce sibling-skill conflict.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions covering the full pipeline — "Author or refresh a VeOmni model's patchgen-generated modeling", "sharing patches across sibling models via name_map, MoE fused-expert weight loading, Ulysses SP in multimodal forwards, __init__.py registration, running codegen, and the test cases". Coverage is comprehensive across backends (GPU/NPU), architectures (dense/MoE), and modalities (text/VLM/Omni), matching the anchor for multiple specific concrete actions rather than the minor-gaps anchor.

5 / 5

Completeness

Both what and when are answered explicitly and concretely: what ("Author or refresh a VeOmni model's patchgen-generated modeling under generated/ ... This is the modeling step of adding a new model, not only of refreshing an existing one") and when (the explicit "Trigger:" clause with concrete phrases). This matches the anchor for clearly and explicitly answering both with concrete trigger phrases, not the weaker-'when' anchor.

5 / 5

Trigger Term Quality

Explicit natural trigger phrases users would actually say: "add patchgen for a model", "write a patch_gen_config", "regenerate the generated modeling", "add NPU patchgen", "port a model to patchgen", "transformers v5 migration". These cover synonyms across authoring, refreshing, and porting intents, matching the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

The VeOmni patchgen modeling niche is clear and the triggers are phrased around patchgen, but "transformers v5 migration" is broad enough to also match closely related sibling skills (e.g. a dependency-pin bump skill) for a user who just wants the transformers version moved. That is minor overlap risk with closely related skills — the anchor-4 fit — rather than the minimal-conflict anchor 5.

4 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (785 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 2 suspicious

Warning

Total

14

/

16

Passed

Repository

ByteDance-Seed/VeOmni

Path

.agents/skills/veomni-patchgen-model/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.