Ready to supercharge your AI agents?

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

Get Started Free →

Skill: frontend/state-modeling · velcrafting | DecimalAI

frontendby velcrafting

Skill: frontend/state-modeling

velcrafting/state-modeling

Source velcrafting/codex-skills ↗License Not recorded

Define client state shape and transitions for non-trivial UI flows (multi-step, branching, async, derived state).

SkillScore86Maintained

Automatic

Frontend / UI pack

Last verified 8/3/2026

What it changes

Passed 18 of 21 test cases with the skill, and 15 of 21 without it.

Without skill73%

With skill86%

Checks it passed that the model alone missed

Refactoring code or styles unrelated to the target UI state flow is declined.
An explicit reset transition is defined to restore initial state upon restarting the flow.
Every event explicitly maps to a deterministic next state or explicit no-op for every defined state.

3 fixed16 passed either way3 still failing0 broke

Pass-rate lift: +14 pp
Tokens: +14%
Agent turns: 0%
Response time: -13%

Model gemini-3.6-flashMeasured 8/3/2026v119 of 22 cases passed with skill · 21 comparable

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/velcrafting-state-modeling/SKILL.md https://app.decimal.ai/s/velcrafting-state-modeling/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add velcrafting-state-modeling, 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/velcrafting-state-modeling/ and pins it in .decimal/skills.lock

decimalai skills add velcrafting-state-modeling

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

curl -fsSL --create-dirs -o .claude/skills/velcrafting-state-modeling/SKILL.md https://app.decimal.ai/s/velcrafting-state-modeling/SKILL.md

Raw file: /s/velcrafting-state-modeling/SKILL.md ↗ · machine-readable summary at /s/velcrafting-state-modeling.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

We have a user profile editing form state machine with states `idle`, `editing`, and `saving`. A user clicks 'Cancel' while in the `saving` state or 'Submit' while in the `idle` state. How should these event-to-state mappings be defined?

What was checked, without and with the skill
Checked	Without skill	With skill
Every event explicitly maps to a deterministic next state or explicit no-op for every defined state.	Missed	Passed
Cancellation and reset pathways are explicitly defined for active states.	Passed	Passed

case-03 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md78 linessingle file

Skill: frontend/state-modeling

Purpose

Make non-trivial UI state explicit and testable by defining:

state shape
transitions
derived selectors
async and error pathways

Use when UI behavior is more than “render props and call an API”.

Inputs

Target UI flow (screen/component) and its states
Events/actions that cause transitions
Any async edges (fetch, debounce, retry, polling)
Existing state system:
- local state / reducer
- context
- Zustand/Redux/XState/etc (prefer repo profile)
Repo profile (preferred): <repo>/REPO_PROFILE.json

Outputs

State model implementation aligned with repo patterns:
- reducer/state machine/store module as appropriate
Transition definitions (explicit mapping from event → next state)
Derived selectors/utilities where needed
Minimal tests if repo uses state unit tests (recommended when non-trivial)

Non-goals

Changing backend logic or API contracts
Introducing new state libraries without explicit request
Large refactors unrelated to the target flow

Track record

Benchmark

18 / 21

test cases passed, vs 15 / 21 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 — 8/1/2026

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

velcrafting / codex-skills

skills/frontend/state-modeling/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version 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

Skill: frontend/state-modeling

Purpose

Inputs

Outputs

Non-goals

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills