veomni-develop

VeOmni-specific checklist for feature development and refactoring. Covers impact analysis across modalities, trainer hierarchy, data pipeline, and distributed code. Use before implementing any non-trivial change. For model-specific or ops-specific work, use veomni-new-model or veomni-new-op instead. Trigger: 'add feature', 'implement', 'refactor', 'reorganize', 'new capability'.

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%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 high-quality, dense checklist skill: actionable, concise, with explicit validation checkpoints in its refactoring workflow and clean sectioning that defers detail to one-level-deep knowledge files. No significant weaknesses across any dimension.

Dimension	Reasoning	Score
Conciseness	Lean, dense checklist with no padding and no explanation of concepts Claude already knows (FSDP2, collators, FA varlen are named without tutorial prose); every line carries a specific path, rule, or constraint.	5 / 5
Actionability	Concrete, executable guidance throughout — exact paths (veomni/data/data_collator.py), commands (pytest tests/, grep all YAML files), and precise orderings (pad → slice → FA kwargs → slice position_ids); as an instruction-only skill the absence of code blocks is not penalized since the guidance is directly actionable.	5 / 5
Workflow Clarity	The Refactoring Safety Rules give a clear numbered sequence with explicit validation checkpoints (baseline before, verify tests match baseline after each change, check baseline again at end), satisfying the feedback-loop requirement for destructive/batch work.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections and points to one-level-deep detail files (Follow .agents/knowledge/testing.md, update .agents/knowledge/architecture.md, constraints.md) rather than inlining them; no nested reference chains.	5 / 5
	Total	20 / 20 Passed

Description

95%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, well-structured description that states both what it does and when to use it, supplies natural trigger terms, and explicitly routes adjacent work to sibling skills. Only minor room for a more action-oriented verb list.

Dimension	Reasoning	Score
Specificity	Names the domain ('feature development and refactoring') and lists several concrete coverage areas ('impact analysis across modalities, trainer hierarchy, data pipeline, and distributed code'); short of 5 only because 'checklist' is a somewhat abstract framing of the actions rather than a fuller enumeration.	4 / 5
Completeness	Clearly states what ('VeOmni-specific checklist... Covers impact analysis...') and when ('Use before implementing any non-trivial change') plus concrete trigger phrases, hitting the explicit what-and-with-when anchor.	5 / 5
Trigger Term Quality	Explicit 'Trigger:' clause lists natural phrases users say ('add feature', 'implement', 'refactor', 'reorganize', 'new capability') with synonyms (refactor/reorganize, add feature/new capability), matching the comprehensive-synonyms anchor.	5 / 5
Distinctiveness Conflict Risk	Scoped to VeOmni and actively disambiguates from siblings ('For model-specific or ops-specific work, use veomni-new-model or veomni-new-op instead'), giving a clear niche with minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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-develop/SKILL.md
Commit: b8a3edc

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.