CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

82%

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

75%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, repo-specific checklist: nearly every line encodes non-obvious project knowledge (impact areas, traps, config coupling) with concrete commands and explicit baseline-validation in the refactoring workflow. Remaining improvements are marginal - trimming the extension-point prose and naming the specific parallel tests to run.

DimensionReasoningScore

Conciseness

The body is dense with repo-specific facts (import-time registration side effects, DEFAULT_DATA_COLLATE_INFO coupling, strict SP ordering) with no basic-concept padding, but the ~30-line extension-point documentation section and the long 'AI self-inflicted defense loop' parenthetical could be tightened or moved to a reference file.

4 / 5

Actionability

Concrete commands are given ('pytest tests/', 'make -C docs html SPHINXOPTS=-W'), along with exact file paths, concrete conventions, and a reference example page, matching 'mostly executable guidance'. Minor gaps remain, e.g., 'run the cross-cutting parallel tests' without naming which tests or the command to run them.

4 / 5

Workflow Clarity

The refactoring workflow has an explicit validation loop (record baseline, one change per commit, verify tests match baseline, re-check baseline at the end) and the docs section requires a -W build before committing, but there are no error-recovery feedback loops (what to do when baseline comparison fails), matching anchor 4 rather than 5.

4 / 5

Progressive Disclosure

The single-file skill has well-organized sections with clear pointers to other skills (/veomni-review, /veomni-debug) and knowledge files (.agents/knowledge/testing.md, a reference doc page), and no bundle files exist to structure. The detailed extension-point contract subsection is the one piece of content that arguably belongs in a separate reference file, keeping this at anchor 4.

4 / 5

Total

16

/

20

Passed

Description

83%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 explicitly states what the skill covers, when to use it, and how it differs from sibling skills, with concrete trigger phrases. The main weaknesses are slightly scope-level (rather than action-level) capability listing and a few missing natural trigger synonyms.

DimensionReasoningScore

Specificity

The description names the domain ('VeOmni-specific checklist for feature development and refactoring') and lists several concrete coverage areas ('impact analysis across modalities, trainer hierarchy, data pipeline, and distributed code'), but it describes scope rather than a comprehensive list of discrete actions, matching anchor 4 rather than 5.

4 / 5

Completeness

Both 'what' ('VeOmni-specific checklist for feature development and refactoring. Covers impact analysis across modalities...') and 'when' ('Use before implementing any non-trivial change' plus concrete trigger phrases) are explicitly and clearly stated, matching the anchor-5 example.

5 / 5

Trigger Term Quality

Explicit trigger terms ('add feature', 'implement', 'refactor', 'reorganize', 'new capability') are natural phrases users would say, but common synonyms such as 'extend', 'modify', or 'restructure' are missing, so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

'VeOmni-specific' establishes a clear niche and the description explicitly routes model-specific and ops-specific work to sibling skills ('use veomni-new-model or veomni-new-op instead'), but generic trigger words like 'implement' and 'refactor' could fire in many coding contexts, leaving minor overlap risk.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

ByteDance-Seed/VeOmni

Path

.agents/skills/veomni-develop/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.