CtrlK
BlogDocsLog inGet started
Tessl Logo

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'.

71

Quality

86%

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

86%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 compact, well-structured checklist skill that is lean and easy to navigate with strong validation discipline in its refactoring workflow. Actionability could rise slightly by converting more 'what to check' rows into concrete commands.

Suggestions

Convert selected Impact Analysis 'What to check' cells into concrete commands (e.g., a grep/pytest snippet to locate affected trainer subclasses) to lift actionability.

Add an explicit error-recovery branch to Refactoring Safety Rules (e.g., 'if tests diverge from baseline, revert the single change and re-diagnose') to make the feedback loop fully explicit.

Optionally note the cross-cutting parallel test command that 'run the cross-cutting parallel tests' references, so the trap entry is directly executable.

DimensionReasoningScore

Conciseness

Lean table- and rule-based checklist with no over-explanation of concepts Claude already knows; every section earns its tokens.

5 / 5

Actionability

Provides concrete commands (`pytest tests/`), specific file paths, and explicit rules, but several Impact Analysis rows are 'what to check' descriptions rather than executable steps.

4 / 5

Workflow Clarity

The Refactoring Safety Rules sequence has explicit validation checkpoints (record baseline, verify tests match, re-check baseline at end), but error-recovery guidance when tests diverge is implicit rather than stated.

4 / 5

Progressive Disclosure

Under 50 lines with no need for external references, organized into clearly signaled ## sections; meets the simple-skill exception for a top score.

5 / 5

Total

18

/

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.

A well-constructed description that explicitly states both purpose and trigger conditions while carving out a distinct niche from sibling skills. Minor specificity gaps stem from 'covers' framing rather than enumerating concrete actions.

DimensionReasoningScore

Specificity

Names the VeOmni domain and lists several concrete coverage areas (modalities, trainer hierarchy, data pipeline, distributed code), though framed as 'covers' rather than concrete verbs, leaving minor gaps.

4 / 5

Completeness

Clearly answers 'what' (VeOmni checklist for feature dev/refactoring) and 'when' ('Use before implementing any non-trivial change' plus explicit triggers), with concrete trigger phrases.

5 / 5

Trigger Term Quality

Explicit 'Trigger:' clause lists five natural user phrases ('add feature', 'implement', 'refactor', 'reorganize', 'new capability'); good coverage with a few synonyms missing.

4 / 5

Distinctiveness Conflict Risk

VeOmni-specific niche with explicit redirection to veomni-new-model and veomni-new-op for adjacent work, minimizing conflict risk.

5 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ByteDance-Seed/VeOmni
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.