360 Secure SkillHub
360 安全技能中心

AKM Fashion

先建模再决策的衣橱搭配技能：按引导提问、记录模板、执行提示的顺序，梳理身体条件、场景、现有衣橱资产、功能需求、购买容忍度与反例偏好，输出场景判断、搭配建议、理由、缺口分析、购买优先级与缺失输入清单；不含图像识别、虚拟试穿或纯美学情绪板。

sirsws
sirsws
热度 47.25
最近更新 2026-05-11 17:36:54
分类：生活依赖：内部调用大模型应用场景：推荐 / 购物 / 工作流

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add akm-fashion-strategist
Metadata
name
akm-fashion-strategist
description
AKM implementation for wardrobe and outfit decision workflows. Models body context, scenes, wardrobe assets, and functional constraints before outputting styling decisions.

AKM Fashion

AKM Fashion is a profile-first wardrobe and outfit decision skill for real scene and asset constraints.

It does not start with a moodboard. It starts by modeling the operator: body context, scenes, wardrobe assets, functional needs, purchase tolerance, and anti-patterns.

Quick Reference

Item Details
Primary outcome a wardrobe-aware outfit or purchase decision
Best use case when generic styling advice fails because the user's real wardrobe and scene constraints matter
Public source https://github.com/sirsws/akm/tree/main/branches/fashion
Sample record https://github.com/sirsws/akm/blob/main/branches/fashion/skill/SAMPLE_RECORD.md
Research paper https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6231466
Install source https://github.com/sirsws/akm

Public Links

  • GitHub branch: https://github.com/sirsws/akm/tree/main/branches/fashion
  • Skill files: https://github.com/sirsws/akm/tree/main/branches/fashion/skill
  • Sample record: https://github.com/sirsws/akm/blob/main/branches/fashion/skill/SAMPLE_RECORD.md
  • Branch paper: https://github.com/sirsws/akm/tree/main/branches/fashion/paper
  • SSRN paper: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6231466

Installation

ClawHub / OpenClaw:

  • install from this listing

Skills CLI:

npx skills add https://github.com/sirsws/akm --skill akm-fashion-strategist --full-depth

What This Skill Changes

Most styling agents answer too early.

They do not know what the user already owns, which scenes matter, what body issues need handling, or which functional constraints dominate the decision. That is where generic taste talk starts.

AKM Fashion changes the order of operations: profile first, decision second.

When to Use

Use this skill when:

  • the user needs scene-specific outfit decisions
  • current wardrobe assets materially constrain the solution space
  • comfort and function matter, not only aesthetics
  • purchase priorities are more useful than vague inspiration
  • generic style advice keeps missing the real problem

Do not use this skill when:

  • the user only wants casual fashion chat
  • image recognition or virtual try-on is being requested
  • the wardrobe state is unknown and the user refuses to provide it
  • the user wants pure aesthetic moodboarding without operational decisions

Core Rule

No wardrobe model, no serious styling decision.

If the necessary state is unclear, the skill should surface MissingInputs instead of pretending the wardrobe is already known.

Workflow

  1. ELICITATION_PROMPT.md
  2. RECORD_TEMPLATE.md
  3. EXECUTION_PROMPT.md
  4. SAMPLE_RECORD.md

Output Contract

Outputs should include:

  • SceneJudgment
  • OutfitRecommendation
  • WhyThisWorks
  • GapAnalysis
  • PurchasePriority
  • MissingInputs

Operating Boundary

AKM Fashion is a wardrobe decision aid. It is not an image-recognition tool, not a virtual try-on product, and not a generic taste generator that hides missing context behind aesthetic language.

Files to Load

Read these files before running the skill:

  • ELICITATION_PROMPT.md
  • RECORD_TEMPLATE.md
  • EXECUTION_PROMPT.md
  • SAMPLE_RECORD.md