Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Apply an aesthetic profile — measured AI agent skill | DecimalAI

bitjaru/ss-restyle

NewSkillScoreMaintained

Apply one optional StyleSeed aesthetic profile without changing the selected output grammar, product job, or core design judgment.

design-mediaby bitjaru

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Design & UX Review pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/bitjaru-ss-restyle/SKILL.md

decimalai skills pull bitjaru-ss-restyle --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/bitjaru-ss-restyle/SKILL.md https://app.decimal.ai/s/bitjaru-ss-restyle/SKILL.md

Raw file: /s/bitjaru-ss-restyle/SKILL.md ↗ · machine-readable summary at /s/bitjaru-ss-restyle.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 6h ago

Yes — +64% lift-25% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	-51%	0%
case-01	✗→✓	▲ Improved	-20%	0%
case-05	✗→✓	▲ Improved	390%	0%
case-06	✗→✓	▲ Improved	14%	0%
case-08	✗→✓	▲ Improved	-25%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

bitjaru / styleseed

engine/.claude/skills/ss-restyle/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Apply an aesthetic profile

Read PRODUCT-PRINCIPLES.md, RULESETS.md, PRESETS.md, and STYLESEED.md. Profiles are coordinated visual axes; output grammars organize attention, information, and action. Keep them separate.

Workflow

Validate that the lock has one output grammar. If not, run /ss-setup first.
Select exactly one profile from PRESETS.md, or none. Never stack profiles.
Apply its coordinated radius, density, type, palette temperature, elevation, motion,

composition accent, and signature move inside the output grammar's allowed ranges.

Preserve deliberate brand values and required fonts when compatible. If incompatible, the

output grammar and core invariants win; explain the conflict.

Update Aesthetic profile and affected bounded values in STYLESEED.md. Do not rewrite the

output grammar or a reference-compiled rule set.

Run /ss-score to ≥80 and /ss-verify if renderable. Report the complete effective rule set,

not just the profile name.

Rules

A profile is optional appearance coordination, not a design-method exemption.
technical profile does not turn a commerce page into an observability console.
editorial profile does not justify unreadable serif body in a transaction workflow.
brutalist-lite still requires coherent states, contrast, and one border language.
Use /ss-dial for one-axis changes and /ss-reference for a new evidence-derived language.

Want to see if bitjaru/ss-restyle would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.