Skip to main content
Glama
Wardrobe Capsule

Wardrobe Capsule

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
WARDROBE_CAPSULE_PATHNoSet WARDROBE_CAPSULE_PATH to choose the wardrobe file location (default: data/wardrobe.json next to the package).data/wardrobe.json

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
add_itemB

Log one piece of clothing you own.

category: tops, bottoms, dresses, outerwear, shoes or accessories. seasons: e.g. "all", "summer", "summer, spring". styles: casual, work, dressy, cozy, active or home. wearability: 1-5, how easy it is to throw on (5 = zero effort). last_worn: optional YYYY-MM-DD if you happened to note it.

list_itemsB

Show what's in the closet (optionally one category).

record_wearA

Mark an item as worn today (or a YYYY-MM-DD date).

suggest_outfitB

Suggest one outfit for today's weather and occasion.

Give a temperature in Celsius, or words like 'cool and rainy', or both. Occasions: errands, casual, work, cozy, active, fancy.

unworn_reportB

What hasn't been worn lately (default: last 90 days).

donate_triageB

Sort the closet into a donate bag and keepers by last-worn date.

Nothing is moved - read the list first, act only when you're ready.

mark_donatedC

Move one item out of the closet into the donate bag.

packing_listC

A trip packing list from your real items.

days is trip length (>=1), temp_c the average temperature (or weather_words like 'cool and rainy'), occasions a comma list per day (default casual, e.g. 'casual, work, fancy').

Prompts

Interactive templates invoked by user choice

NameDescription
get_dressed_todayA gentle, low-energy walk through getting dressed.

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.3/5.0

Scored across 8 tools

Disambiguation4/5

Most tools target a distinct resource+action (add_item, list_items, record_wear, mark_donated are unambiguous). The main overlap is packing_list vs suggest_outfit, which both consume weather + occasion inputs, though the multi-day trip list vs single-outfit framing keeps them separable. unworn_report vs donate_triage is close but descriptions distinguish reporting from triage sorting.

Naming Consistency3/5

All names are snake_case, but conventions are mixed: add_item/list_items/record_wear/suggest_outfit/mark_donated use verb_noun while packing_list/unworn_report/donate_triage are noun phrases. Readable overall, but the pattern is not predictable enough to guess an unseen tool's name.

Tool Count5/5

Eight tools is well within the ideal 3-15 range for a personal wardrobe assistant. Each tool maps to a distinct user intent: capture, view, wear tracking, suggestion, packing, and decluttering. No filler tools.

Completeness3/5

The surface covers adding, listing, wear tracking, outfit suggestion, and donation lifecycle, but lacks any update/edit operation — you cannot correct an item's category, seasons, style, or wearability after logging. There is also no get-item detail view or way to undo mark_donated, creating dead ends.

Maintenance

ActivityMaintained
ResponsivenessNo issues