CtrlK
BlogDocsLog inGet started
Tessl Logo

siliconflow-img-gen

Generate or edit images via 火山方舟 (Volcengine Ark) Seedream API. Text-to-image default model doubao-seedream-4.5(fallback doubao-seedream-5.0-lite); image-edit supported via 1-3 reference images. Uses user's AWK_GEN_KEY (client-side only, never sent to server).

61

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/siliconflow-img-gen/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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, a clear validated workflow, and good organization. Its main weakness is conciseness — a duplicated verification section and a verbose billing/activation guide add tokens that don't earn their place.

Suggestions

Remove the duplicate top-level '⚠️ 生成后必须验证' section (lines ~199-206); keep the single authoritative checklist inside the best-practices workflow.

Condense the '模型开通指引' / '免费额度与付费提醒' section to the essential activation steps and a one-line billing caveat, moving detail to an external doc link.

Consider extracting the long '视频封面/海报最佳实践' guide into a separate references/ file linked from SKILL.md to tighten the overview.

DimensionReasoningScore

Conciseness

Mostly efficient and actionable, but the post-generation verification checklist is duplicated and the model-activation / free-quota / billing reminder section is verbose marketing-like material that could be trimmed.

3 / 5

Actionability

Fully copy-paste-ready commands throughout, a complete worked example with all flags, and a parameter table with defaults and specific size values covering the common cases.

5 / 5

Workflow Clarity

Explicit generate → verify-with-image-tool → retry (≤3) → mark-failed sequence with a ✅ checklist and feedback loop; validation is present so no destructive/batch cap applies.

5 / 5

Progressive Disclosure

Single bundle (scripts/gen.py + tests) with well-organized sections and a clearly signaled external API-doc link, but at 250+ lines the best-practices and billing sections are bulk that could be split into a separate reference file.

4 / 5

Total

17

/

20

Passed

Description

66%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.

The description clearly states what the skill does and names a specific vendor/API niche, but it omits any explicit 'Use when...' trigger guidance, which caps its completeness. Keyword coverage is solid though not exhaustive.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when the user asks to generate or edit images, create AI art, or produce posters/covers via Volcengine Seedream.'

Broaden trigger terms with natural synonyms users say ('draw', 'AI image', '图片生成', 'poster/cover') to improve distinctiveness and recall.

Mention key capability dimensions like output size presets or JPG/PNG output so the 'what' is more comprehensive.

DimensionReasoningScore

Specificity

Names several concrete actions — 'Generate or edit images', 'Text-to-image', 'image-edit supported via 1-3 reference images' — with minor gaps (no mention of sizing/output formats).

4 / 5

Completeness

Has a clear 'what' (image generation/editing via Volcengine Seedream API) but no explicit 'Use when...' trigger clause, capping completeness at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Good natural keywords ('generate or edit images', 'text-to-image', 'image-edit') but missing common synonyms like 'draw', 'AI image', or '图片生成'.

4 / 5

Distinctiveness Conflict Risk

The specific vendor API, AWK_GEN_KEY credential, and Seedream model names carve a clear niche, but 'generate/edit images' still overlaps with other image skills.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
TeamWiseFlow/xiaobei
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.