Ready to supercharge your AI agents?

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

Get Started Free →

Data Product UX · qierkang | DecimalAI

frontendby qierkang

Data Product UX

qierkang/data-product-ux

Source qierkang/platform-project-skill ↗License MIT

Design and implement high-quality data-heavy product experiences.

SkillScore88Maintained

Automatic

Design & UX Review pack

Last verified 8/28/2026

What it changes

Passed 21 of 24 test cases with the skill, and 19 of 24 without it.

Without skill79%

With skill88%

Checks it passed that the model alone missed

Include retry handling in result states.
Include saved views in query state controls.
Define the explicit next action for metrics.

and 5 more in the full report

3 fixed18 passed either way2 still failing1 broke

Pass-rate lift: +8 pp
Tokens: +73%
Agent turns: 0%
Response time: +51%

Model gemini-3.6-flashMeasured 8/28/2026v121 of 24 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/qierkang-data-product-ux/SKILL.md https://app.decimal.ai/s/qierkang-data-product-ux/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add qierkang-data-product-ux, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

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

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/qierkang-data-product-ux/ and pins it in .decimal/skills.lock

decimalai skills add qierkang-data-product-ux

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

curl -fsSL --create-dirs -o .claude/skills/qierkang-data-product-ux/SKILL.md https://app.decimal.ai/s/qierkang-data-product-ux/SKILL.md

Raw file: /s/qierkang-data-product-ux/SKILL.md ↗ · machine-readable summary at /s/qierkang-data-product-ux.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

Our engineering team is revamping our financial performance monitoring tool. Draft an end-to-end UX architecture document covering decision context framing, query and URL state controls, chart drill-down interaction patterns, performance strategy for high data volumes, and mandatory UI completion checks.

What was checked, without and with the skill
Checked	Without skill	With skill
Require defining a comparison baseline alongside primary metrics.	Missed	Passed
Include saved views in query state controls.	Missed	Passed
Include reset controls in query state controls.	Missed	Passed
Include retry handling in result states.	Missed	Passed
Specify time zone consistency rules across data columns.	Missed	Passed
Require failure state testing in completion verification checks.	Missed	Passed

case-03 · gemini-3.6-flash · 8/28/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md13 lines2 files

Data Product UX

A data surface must help users understand, decide, and act; displaying more metrics is not sufficient.

Define the decision, primary metric, comparison baseline, freshness, and next action.
Design query state: search, filters, sort, pagination, URL state, saved views, and reset.
Design result state: loading, partial, empty, stale, error, permission, and retry.
Keep column ownership, units, precision, time zone, null semantics, and export fields consistent.
Let charts support comparison and drill-down, with labels, accessible summaries, and a detail path.
For long tasks, show stage, progress source, last update, cancellation or retry, and history.
Choose pagination, virtualization, aggregation, and lazy loading from measured volume.

Completion requires realistic dense data, zero data, failure, keyboard, and narrow-viewport browser checks.

Track record

Benchmark

21 / 24

test cases passed, vs 19 / 24 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/9/2026

View 15 scanner checks

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

qierkang / platform-project-skill

assets/templates/omni-platform/.agents/skills/data-product-ux/SKILL.md

View on GitHub ↗

License MITImported 8/9/2026Version v1Bundled 1 file

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Data Product UX

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills