frontend by rshankras
visionOS Skills rshankras/visionos
visionOS skills — spatial design (layout ergonomics, eyes-and-hands input, motion comfort, immersion, environments) and widget patterns (mounting styles, glass/paper textures, proximity-aware layouts).
What it changes View full report → Passed 19 of 22 test cases with the skill, and 18 of 22 without it.
Without skill 82%
With skill 86%
Checks it passed that the model alone missed Recommends visionOS system glass and paper texture materials for appropriate visual hierarchy Recommends placing primary content directly in natural line of sight at comfortable arm-length distance2 fixed17 passed either way2 still failing1 broke
Pass-rate lift +5 pp
Tokens -6%
Agent turns 0%
Response time -18% Model gemini-3.6-flashMeasured 8/17/2026 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/rshankras-visionos/SKILL.md https://app.decimal.ai/s/rshankras-visionos/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add rshankras-visionos, 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/rshankras-visionos/ and pins it in .decimal/skills.lock
$ decimalai skills add rshankras-visionosCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/rshankras-visionos/SKILL.md https://app.decimal.ai/s/rshankras-visionos/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 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt Where should primary interactive windows be initially placed in visionOS virtual space relative to the user's natural gaze direction and distance?
What was checked, without and with the skill Checked Without skill With skill Recommends placing primary content directly in natural line of sight at comfortable arm-length distance Missed Passed
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 27 lines single file
visionOS Skills
Spatial-computing patterns for visionOS.
When This Skill Activates
Use this skill when the user:
Designs, builds, or reviews any visionOS app, window, volume, or immersive space
Asks about spatial layout, eye/hand input, hover effects, motion comfort, or environments
Builds or adapts widgets for visionOS
Asks about mounting styles , glass/paper textures , or spatial widget families
Needs proximity-aware layouts
Available Skills
Paths are relative to THIS file's directory — skills run with cwd set to the
user's project, so resolve each path from this SKILL.md's own location.
How to Route
Read widgets/SKILL.md (relative to this file) plus any reference files it lists.
Apply the guidance to the user's code.
When it activates Automatically, when a task matches.
Use when designing, building, or reviewing anything for visionOS.
Track record Benchmark 19 / 22
test cases passed, vs 18 / 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 License MITImported 8/3/2026Version v1