veomni-review

Use this skill before committing ANY code change — this is a mandatory gate in the commit flow. Also trigger proactively when: you've made changes across multiple files and want to check consistency, you're unsure if a fix is safe, a change touches shared infrastructure (BaseTrainer, distributed, model loading, data pipeline), or a change is larger than a few lines. The review launches a subagent that checks implementation quality, multi-file consistency, and known constraint violations, then rates the change as safe/needs-attention/risky.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

88%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 well-structured, actionable pre-commit review workflow with a concrete subagent prompt template and explicit verdict-driven validation gates. Minor conciseness and organization nits (a duplicated make quality instruction, slightly over 50 lines) keep it just short of perfect.

Suggestions

Remove the duplicated 'Run make quality' instruction — keep it in only one place (e.g. step 5) and have the After Commit section reference it rather than restate it.

Consider moving the subagent prompt template into a references file and signaling it with a one-level-deep link, which would shorten SKILL.md and bring progressive disclosure to a 5.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence (no explanations of git diff, subagents, or ruff), but 'Run make quality' is stated twice (step 5 and the After Commit section), a minor redundancy that could be trimmed.	4 / 5
Actionability	Fully executable guidance: concrete commands (`git diff`, `make quality`), a specific file path (`.agents/knowledge/constraints.md`), and a copy-paste-ready subagent prompt template with clearly marked placeholders to fill.	5 / 5
Workflow Clarity	Clear five-step sequence with explicit validation checkpoints: the verdict table branches on safe/needs-attention/risky, 'risky' halts the commit, and `make quality` before the final commit provides a final gate with a fix-then-proceed loop for needs-attention.	5 / 5
Progressive Disclosure	Well-organized into clear sections (Steps, Subagent Launch, After Commit) with no nested references and no bundle files to navigate; the inline subagent prompt template is appropriately core, though the skill runs slightly over the 50-line simple-skill threshold.	4 / 5
	Total	18 / 20 Passed

Description

82%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, specific description that clearly states both what the skill does and when to use it, with concrete VeOmni-specific triggers and a clear verdict scheme. The only weakness is second-person voice in the trigger clauses, which costs it a specificity point.

Suggestions

Rewrite trigger clauses in third person to avoid the voice penalty, e.g. 'Trigger proactively when changes span multiple files and consistency needs checking, when a fix's safety is uncertain, when shared infrastructure (BaseTrainer, distributed, model loading, data pipeline) is touched, or when a change exceeds a few lines.'

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('launches a subagent that checks implementation quality, multi-file consistency, and known constraint violations, then rates the change as safe/needs-attention/risky') and names domains (BaseTrainer, distributed, model loading, data pipeline), which would be a 4, but the second-person phrasing ('you've made changes', 'you're unsure if a fix is safe') triggers the voice penalty reducing specificity by 1.	3 / 5
Completeness	Explicitly answers both what ('launches a subagent that checks implementation quality, multi-file consistency, and known constraint violations, then rates the change as safe/needs-attention/risky') and when ('before committing ANY code change... Also trigger proactively when:...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases a user would say are present ('before committing ANY code change', 'made changes across multiple files and want to check consistency', 'unsure if a fix is safe', 'larger than a few lines'), giving good keyword coverage with a few common variations missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche tied to the VeOmni framework with distinctive triggers (BaseTrainer, distributed, model loading, data pipeline, FSDP), making conflict with unrelated skills minimal.	5 / 5
	Total	17 / 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-review/SKILL.md
Commit: c465a63

Reviewed: about 19 hours 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.