CtrlK
BlogDocsLog inGet started
Tessl Logo

ai-image-creator

Generate, edit-from-reference, or analyze images with AI via OpenRouter (gemini, geminipro, riverflow, flux2, seedream, gpt5, gpt5.4; Cloudflare AI Gateway BYOK). Also analyze a video (--analyze-video, read-only — no video generated) into a text description for video prompts. Use when the user asks to generate an image, create a PNG, make an icon, make it transparent, edit with a reference, design a logo/banner, describe/analyze/explain an image ("what's in this image"), or describe/analyze a video ("what happens in this video").

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 content is a dense, executable reference with excellent actionability, well-sequenced workflows including explicit validation and feedback loops, and strong one-level-deep progressive disclosure to verified bundle files. Its only weakness is mild verbosity in the Video Analysis and Composite sections that could be tightened without losing clarity.

Suggestions

Trim the Video Analysis section: collapse the repeated 15-model list into a single "run --list-models" pointer and shorten the structured-JSON field enumeration to the handful of fields that matter for grounding (summary, shot_timeline, uncertain_details, video_generation_prompt).

Compress the Composite vs. AI Generation decision rule into a compact if/then table or a single rule line; the current four-bullet ALL/ANY contrast restates the same distinction three times.

DimensionReasoningScore

Conciseness

The body is largely lean — tables for models/params/env vars and copy-paste bash with no basic-concept padding — but the Video Analysis section (a long structured-JSON field enumeration, repeated 15-model lists) and the Composite decision prose could be trimmed. Falls at 4 rather than 5 because of these minor over-explanation pockets.

4 / 5

Actionability

Fully executable copy-paste bash blocks for every mode (generate, transparent, ref-edit, analyze, analyze-video with all flag combinations, composite init/validate/generate, post-processing) with concrete flag values and expected JSON output formats, covering the common cases.

5 / 5

Workflow Clarity

Clear numbered sequence (Write Prompt → Enhancement → Run → Cleanup → Verify → Post-Process) with explicit validation checkpoints ("file OUTPUT_PATH", confirm "PNG image data"), a composite --validate-before-generate gate, and a video --verify feedback loop (classify supported/contradicted/not_visible → corrections).

5 / 5

Progressive Disclosure

The body is an overview pointing one level deep to 7 verified-present reference files and 2 scripts, each clearly signaled with its contents and a when-to-read condition (the Category Detection table provides strong navigation); API/setup/prompt-pattern detail is appropriately split out of the body.

5 / 5

Total

19

/

20

Passed

Description

100%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 is a strong, third-person trigger statement that concretely states capabilities and enumerates the natural phrases a user would say, explicitly covering both what the skill does and when to invoke it. It is distinguishable from sibling skills via specific model keywords and image/video analysis triggers.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across all script modes — "Generate, edit-from-reference, or analyze images", "analyze a video ... into a text description" — plus enumerated model keywords, giving comprehensive coverage rather than the minor gaps that define a 4.

5 / 5

Completeness

Explicitly answers "what" (generate/edit/analyze images and video) and "when" via a detailed "Use when the user asks to..." clause with concrete trigger phrases, satisfying both halves explicitly.

5 / 5

Trigger Term Quality

Covers natural user phrases ("generate an image", "make an icon", "make it transparent", "design a logo/banner", "what's in this image", "what happens in this video") including the PNG synonym/format extension, matching the comprehensive-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

Clear niche (AI image generation/edit/analysis via Cloudflare BYOK/OpenRouter) with model-specific and mode-specific trigger phrases; the carved-out "what's in this image"/"what happens in this video" triggers minimize wrong-skill activation.

5 / 5

Total

20

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

metadata_version

'metadata.version' is missing

Warning

Total

14

/

16

Passed

Repository
centminmod/my-claude-code-setup
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.