Ready to supercharge your AI agents?

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

Get Started Free →

Loading / Empty / Error States · archive228 | DecimalAI

frontendby archive228

Loading / Empty / Error States

archive228/loading-empty-error-states

Source archive228/loopkit ↗License MIT

Design the three states every data UI forgets.

SkillScore100Maintained

Automatic

Frontend / UI pack

Last verified 8/16/2026

What it changes

Passed 22 of 22 test cases with the skill, and 18 of 22 without it.

Without skill82%

With skill100%

Checks it passed that the model alone missed

Require layout-matching skeleton screens
Provide single action to clear active search query
Provide single call to action button to start conversation

and 3 more in the full report

4 fixed18 passed either way0 still failing0 broke

Pass-rate lift: +18 pp
Tokens: +25%
Agent turns: 0%
Response time: +11%

Model gemini-3.6-flashMeasured 8/16/2026v122 of 22 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/archive228-loading-empty-error-states/SKILL.md https://app.decimal.ai/s/archive228-loading-empty-error-states/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add archive228-loading-empty-error-states, 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/archive228-loading-empty-error-states/ and pins it in .decimal/skills.lock

decimalai skills add archive228-loading-empty-error-states

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

curl -fsSL --create-dirs -o .claude/skills/archive228-loading-empty-error-states/SKILL.md https://app.decimal.ai/s/archive228-loading-empty-error-states/SKILL.md

Raw file: /s/archive228-loading-empty-error-states/SKILL.md ↗ · machine-readable summary at /s/archive228-loading-empty-error-states.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

Please review the UI code diff for our new activity feed feature. Make sure every data fetch handles non-happy path conditions cleanly and let me know if any necessary user interface fallback states are missing.

What was checked, without and with the skill
Checked	Without skill	With skill
Require layout-matching skeleton screens instead of spinners	Missed	Passed
Require partial state for streaming data and optimistic update rollbacks	Missed	Passed

case-01 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md7 linessingle file

Loading / Empty / Error States

AI-built UIs handle the happy path and crash on the other three. Design all four:

Loading — skeletons that match the final layout (not a centered spinner that shifts everything).
Empty — a real first-run state: what it is, and the one action to fill it. Not a blank box.
Error — what failed, in human terms, plus a retry. Never a raw stack trace or silent nothing.
Partial — slow/streaming data, optimistic updates that can roll back. For each fetch in the diff, confirm all four exist. The empty and error states are where products feel broken.

Track record

Benchmark

22 / 22

test cases passed, vs 18 / 22 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 — 8/3/2026

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

archive228 / loopkit

skills/loading-empty-error-states/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

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

Loading / Empty / Error States

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills