seedream

Generate AI images using Volcengine Seedream model. Supports text-to-image (T2I), image editing (I2I), multi-image fusion, and web-search-based generation. Use this skill when the user wants to create, generate, or edit images.

Quality

80%

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

Fix and improve this skill with Tessl

tessl review fix ./SKILLs/seedream/SKILL.md

Quality

Content

71%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.

The body is highly actionable, with executable commands for every mode and thorough error handling, but it is over-long: duplicated configuration instructions, general prompt-writing guidance, and usage galleries inflate the token budget. Most of that overflow belongs in one-level-deep reference files that don't exist.

Suggestions

Deduplicate API key setup: keep one canonical configuration section and remove the repeated export instructions from the quick-start path.

Move '提示词最佳实践', '常见使用场景', and the error catalog into a references/ file (e.g., references/prompting.md, references/errors.md) and link them from SKILL.md to cut the ~440-line body down to an operational overview.

Trim '轮询和超时控制' and '高级选项' to the parameter table plus one example, since --poll-interval/--timeout defaults are already documented in the parameter table.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational but contains redundant and padded sections: API key setup is explained twice (the quick-start export block and the '如何配置 API Key' section), '轮询和超时控制' shows three examples differing only in numbers, and '常见使用场景' and '提示词最佳实践' repeat general prompting knowledge Claude already has. Not a 2 because the bulk is genuinely task-specific operational detail.	3 / 5
Actionability	Every generation mode ships a copy-paste-ready bash invocation of scripts/generate-image.sh with concrete flags, backed by a full parameter table with defaults, a status table, and an error catalog with cause-and-solution pairs. The referenced scripts (generate-image.sh, generate_image.js) exist in the bundle.	5 / 5
Workflow Clarity	The three-step synchronous workflow (submit, wait, download) is clearly stated, and the error section provides recovery guidance (retry after 429, raise --timeout). It falls short of 5 because checkpoints are catalog-style rather than an explicit validate-then-proceed loop, and there is no post-download verification step.	4 / 5
Progressive Disclosure	Sections are well-organized and the script bundle is correctly referenced, but ~440 lines are entirely inlined in SKILL.md. Content that clearly belongs in reference files — prompt best practices, usage scenarios, the error catalog, and the model comparison — has no references/ directory to be split into. Good structure, but heavy content that should be separate is inline.	3 / 5
	Total	15 / 20 Passed

Description

88%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 that clearly states capabilities in third person with an explicit 'Use this skill when...' trigger clause. Its only weaknesses are missing common trigger synonyms and a trigger phrase that could overlap with other image-generation skills.

Dimension	Reasoning	Score
Specificity	The description lists four concrete, distinct capabilities — 'text-to-image (T2I), image editing (I2I), multi-image fusion, and web-search-based generation' — in third person, comprehensively covering the skill's modes. Only advanced variants (e.g., sequential group generation) are omitted, which does not drop it below the comprehensive anchor.	5 / 5
Completeness	It explicitly answers both: what — 'Generate AI images using Volcengine Seedream model. Supports text-to-image (T2I), image editing (I2I)...' — and when — 'Use this skill when the user wants to create, generate, or edit images' with concrete trigger verbs.	5 / 5
Trigger Term Quality	'create, generate, or edit images' are natural phrases users would say, giving good keyword coverage. Common synonyms and variations like 'draw', 'make a picture', 'AI art', or 'illustration' are missing, so it falls short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Naming 'Volcengine Seedream' carves a clear niche with mostly distinct triggers, but the generic 'create, generate, or edit images' trigger would also match other image-generation skills, leaving minor overlap risk.	4 / 5
	Total	18 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: netease-youdao/LobsterAI
Path: SKILLs/seedream/SKILL.md
Commit: 791a352

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.