SKILLEMALL.ai
GitHub ↗ RU Sign in

AB image-craft

Curated image generation assistant covering four categories — characters, scenes, products, and style transformation — for generating high-quality stylized 3D images. Trigger keywords: figure, doll, portrait, chibi, city, landmark, movie scene, room, logo, brand, product, ad, low-poly, meme, 3D, knolling, sticker.

ClawHub Agent Skills author: ericn26-star v1.0.0 MIT-0 3 files body ≈ 4 897 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process B 70/100 · Nearly there — weak spots: when it triggers, consistency, progress reporting

GeneratorInfrastructureMarketingDesigntype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
95/100
safety, quality, tests
Safety 60%
100
Quality 40%
87
Run on models
none yet
Process rating
B
70/100
Nearly there
Progress reporting w 2
0
When it triggers w 12
20
Consistency w 8
40
the three weakest of ten parameters · all ten
This is a copy of a skill from another catalog; the rating counts the canonical one: image-craft (ClawHub)

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 0

    ✓ No critical or high findings

    Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 70/100

    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 40Consistency. Frontmatter name (image-craft) differs from the folder (eric-image-craft-v2)
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 70Failures and branches. 7 branches
    • 70Execution cost. Instruction body is 4897 tokens
    • 100Tools and files. No external tools needed
    • 100Steps. 158 steps
    • 100Running it twice. No mutating operations
    • low 12 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (3 tags): a typed call is more reliable

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +1No license
    • +2Single-language instructions
    • +3Description length 315: enough signal without eating the budget
    • +4Structure: 38 headings
    • +3Step-by-step instructions: 158 items
    • +3Output format is stated explicitly
    • +4Has examples (18 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: clean
    This is an instruction-only image generation skill with proportionate image and lookup tool use, though its broad trigger words may cause occasional unintended activation.
    LLM: benign (high) · VirusTotal: · 29 May 2026