design media by aiskillstore
Visual Asset Workflow Skill aiskillstore/visual-asset-workflow
Guides educational visual asset creation using professional creative briefs, proficiency alignment, prerequisite validation, and duplicate prevention.
What it changes View full report → Passed 19 of 22 test cases with the skill, and 10 of 22 without it.
Without skill 45%
With skill 86%
Checks it passed that the model alone missed and 14 more in the full report
10 fixed9 passed either way2 still failing1 broke
Pass-rate lift +41 pp
Tokens +53%
Agent turns 0%
Response time -35% Model gemini-3.6-flashMeasured 8/21/2026 v1 19 of 22 cases passed with skill
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/aiskillstore-visual-asset-workflow/SKILL.md https://app.decimal.ai/s/aiskillstore-visual-asset-workflow/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add aiskillstore-visual-asset-workflow, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/aiskillstore-visual-asset-workflow/ and pins it in .decimal/skills.lock
$ decimalai skills add aiskillstore-visual-asset-workflowCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/aiskillstore-visual-asset-workflow/SKILL.md https://app.decimal.ai/s/aiskillstore-visual-asset-workflow/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt What are the structural constraints for B1 intermediate learner visual assets regarding grid complexity and target grasp time?
What was checked, without and with the skill Checked Without skill With skill The response specifies a maximum grid size of 3x3 for B1 learners. The response sets the target grasp time limit to under 10 seconds for B1 learners.
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 304 lines single file
Visual Asset Workflow Skill
Context & Problem
Educational visual generation converges toward generic infographics with technical specifications ("44pt Roboto Bold, 250px box") that activate prediction mode instead of reasoning mode. This produces bland, PowerPoint-default aesthetics instead of distinctive, pedagogically effective visuals.
This skill provides professional creative brief methodology to activate Gemini 3's reasoning capabilities.
Core Principles
Story activates reasoning - Narrative intent produces distinctive visuals; technical specs produce generic onesProficiency dictates complexity - A2 students need <5 sec grasp; C2 professionals handle dense informationPrerequisites gate content - Visuals cannot assume knowledge students don't have yetPedagogy drives hierarchy - Visual weight teaches importance, not arbitrary aesthetics
Dimensional Guidance
Planning Before Execution
Avoid: Jumping into visual analysis without context
Prefer: Strategic planning phase (Q0)
Read FIRST:
apps/learn-app/docs/chapter-index.md → Extract part, proficiency (A2/B1/C2), prerequisitesapps/learn-app/docs/[part]/[chapter]/README.md → Understand lesson structure
Detect conflicts BEFORE work:
Proficiency-complexity mismatch (complex visual for A2 beginners)
Prerequisite violations (Python code when students haven't learned it)
Pedagogical layer incoherence (Layer 1 content using Layer 4 approaches)
Output strategic plan, WAIT for approval before proceeding.
Principle: Plan prevents wasted work (Chapter 9 failure: 5 wrong lessons from skipping planning)
Track record Benchmark 19 / 22
test cases passed, vs 10 / 22 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported aiskillstore / marketplace
skills/92bilal26/visual-asset-workflow/SKILL.md
View on GitHub ↗ Imported 8/3/2026Version v1