filtalgo/Filtmall-Shopping-Skill
filtmall-shopping
Verified筛电(Filtmall / Filtalgo)官方商品发现与交易 Skill。用户未指定其他平台,并明确要寻找、选择、购买、推荐或比较真实商品时自动调用;包括先描述困扰再明确询问“有什么商品推荐”。用户明确说是筛电/Filtmall 的购物车、支付、订单、物流、退款、售后或客服任务时也调用。平台不明的账户状态短句先澄清平台,不登录、不查询。已进入商品或成分流程后出现严重过敏时只做安全拦截,不搜索或交易;脱离购物场景的医疗陈述不自动调用。用户明确询问单个化妆品成分时可进入只读查询。明确指定其他平台、纯困扰陈述、一般知识或无购物意图的医疗问题不调用。Delegate product discovery and shopping questions to the production Filtalgo hosted agent through Control's public guest and conversation APIs. Use scripts/service.py in one-shot or persistent line-delimited JSON mode; it manages guest identity, waits for terminal state, and returns answers and product cards. Supports follow-up, resumption, cancellation and clearing. Available tools depend on the target Agent; member transactions require separate authorization and an Agent with commerce tools.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 46.6 KB |
| agents/openai.yaml | config | 832 B |
| references/protocol.md | markdown | 18.0 KB |
| references/xiaoyi.md | markdown | 6.4 KB |
| scripts/address_cards.py | script | 10.9 KB |
| scripts/cards.py | script | 30.3 KB |
| scripts/client.py | script | 56.2 KB |
| scripts/commerce_render.py | script | 19.6 KB |
| scripts/commerce_ui.py | script | 2.9 KB |
| scripts/control_agent.py | script | 32.7 KB |
| scripts/customer_service_cards.py | script | 10.5 KB |
| scripts/logistics_cards.py | script | 14.1 KB |
| scripts/phone_privacy.py | script | 1017 B |
| scripts/region_lookup.py | script | 10.9 KB |
| scripts/service.py | script | 24.8 KB |
| scripts/update_check.py | script | 13.0 KB |
scripts/region_lookup.py
View on GitHub#!/usr/bin/env python3
"""用当前环境的地区目录解析三级名称,街道及门牌保留为详细地址。"""
import argparse
import json
import re
import sys
import unicodedata
from pathlib import Path
SKILL_DIR = Path(__file__).resolve().parents[1]
DATA_PATH = SKILL_DIR / 'data' / 'regions-prod.json'
LEVELS = ('province', 'city', 'district', 'street')
SEPARATORS = ' \t\r\n,,/、>>'
MUNICIPALITIES = {'北京', '上海', '天津', '重庆'}
# 仅用于自治州/自治县/自治旗的名称尾部,不对普通地名做任意截断。
AUTONOMOUS_ETHNIC_SUFFIX = re.compile(
r'(?:土家族|朝鲜族|达斡尔族|鄂温克族|仡佬族|布依族|仫佬族|毛南族|'
r'哈尼族|纳西族|拉祜族|布朗族|独龙族|普米族|傈僳族|裕固族|景颇族|'
r'哈萨克族|东乡族|保安族|撒拉族|蒙古族|满族|回族|畲族|苗族|瑶族|'
r'侗族|壮族|黎族|羌族|彝族|藏族|水族|傣族|佤族|白族|怒族|土族|'
r'柯尔克孜|哈萨克|塔吉克|蒙古|锡伯|各族)+$'
)
def strip_separators(value):
return re.sub(r'^[\s,,/、>>]+', '', value)
class RegionMatchError(ValueError):
def __init__(self, code, level, parent, candidates):
self.result = {'ok': False, 'error': code, 'level': level,
'parent_id': parent, 'candidates': candidates,
'message': '请明确%s;不自动选择候选或推断地区。' % level}
super().__init__(self.result['message'])
def normalize_name(value):
return ''.join(unicodedata.normalize('NFKC', value).split())
def aliases(node):
"""仅去已知行政后缀,不做包含匹配或编辑距离纠错。"""
name = normalize_name(node['name'])
suffixes = {
'province': ('壮族自治区', '回族自治区', '维吾尔自治区', '自治区', '特别行政区', '省', '市'),
'city': ('自治州', '地区', '市', '盟'),
'district': ('自治县', '自治旗', '区', '县', '市'),
'street': ('街道', '乡', '镇'),
}
names = {name}
for suffix in suffixes[node['level']]:
if name.endswith(suffix) and len(name) > len(suffix):
stem = name[:-len(suffix)]
names.add(stem)
if suffix in ('自治州', '自治县', '自治旗'):
short = AUTONOMOUS_ETHNIC_SUFFIX.sub('', stem)
# 鄂温克族自治旗/东乡族自治县等本身以民族名命名。
if not short and stem.endswith('族'):
short = stem[:-1]
if len(short) >= 2:
names.add(short)
break
return names
def validate_directory(data):
if not isinstance(data, dict) or not isinstance(data.get('environment'), str) or not data['environment'].strip():
raise ValueError('地区目录必须标明 environment')
nodes = data.get('nodes')
if not isinstance(nodes, list) or not nodes or len(nodes) > 200000:
raise ValueError('地区目录节点数量无效')
by_id = {}
for node in nodes:
if not isinstance(node, dict) or any(not isinstance(node.get(k), str) or not node[k].strip() for k in ('id', 'parent_id', 'name', 'level')):
raise ValueError('地区节点字段无效')
if node['level'] not in LEVELS or node['id'] == '0' or node['id'] in by_id:
raise ValueError('地区节点级别或ID无效/重复')
by_id[node['id']] = node
for node in nodes:
parent = by_id.get(node['parent_id'])
if node['level'] == 'province':
valid = node['parent_id'] == '0'
else:
valid = parent is not None and LEVELS.index(parent['level']) + 1 == LEVELS.index(node['level'])
if not valid:
raise ValueError('地区目录父子关系无效')
return nodes
def select_one(matches, level, parent):
if len(matches) != 1:
raise RegionMatchError('REGION_NOT_UNIQUE' if matches else 'REGION_NOT_FOUND',
level, parent, matches)
return matches[0]
def match_name(value, children, level, parent):
value = normalize_name(value)
exact = [node for node in children if normalize_name(node['name']) == value]
return select_one(exact or [node for node in children if value in aliases(node)], level, parent)
def named_path(values, nodes, use_ids=False):
parent, path = '0', []
for value, level in zip(values, LEVELS[:3]):
children = [node for node in nodes if node['parent_id'] == parent and node['level'] == level]
node = (select_one([n for n in children if n['id'] == value.strip()], level, parent)
if use_ids else match_name(value, children, level, parent))
path.append(node)
parent = node['id']
return path
def text_path(address, nodes):
remaining, parent, path = strip_separators(address), '0', []
for level in LEVELS[:3]:
children = [node for node in nodes if node['parent_id'] == parent and node['level'] == level]
matches = [(node, name) for node in children for name in aliases(node)
if normalize_name(remaining[:len(name)]) == name]
if not matches and level == 'city' and len(children) == 1 and aliases(path[0]) & MUNICIPALITIES:
# 直辖市省/市同名且市节点唯一时,允许原文只写一次。
node = children[0]
else:
longest = max((len(name) for _, name in matches), default=0)
longest_matches = [(node, name) for node, name in matches if len(name) == longest]
exact = [(node, name) for node, name in longest_matches if name == normalize_name(node['name'])]
matched = {node['id']: (node, name) for node, name in (exact or longest_matches)}
node = select_one([item[0] for item in matched.values()], level, parent)
name = matched[node['id']][1]
tail = remaining[len(name):]
if level == 'district' and name != normalize_name(node['name']) and tail and not (tail[0].isspace() or tail[0] in SEPARATORS):
raise RegionMatchError('REGION_BOUNDARY_UNCLEAR', level, parent, [node])
remaining = strip_separators(tail)
path.append(node)
parent = node['id']
return path, remaining.strip()
def string_list(value, lengths):
if not isinstance(value, list) or len(value) not in lengths or any(not isinstance(v, str) or not v.strip() for v in value):
raise ValueError('请提供三个省市区名称;prepare 可多提供一个街道/乡镇字符串')
return [v.strip() for v in value]
def lookup(request, data):
if not isinstance(request, dict):
raise ValueError('请求必须为 JSON 对象')
nodes = validate_directory(data)
if request.get('environment') != data['environment']:
return {'ok': False, 'error': 'ENVIRONMENT_MISMATCH',
'message': '必须使用与请求环境一致的地区目录,不得跨环境使用地区ID。'}
op = request.get('op', 'prepare')
if op == 'children':
parent = request.get('parent_id', '0')
if not isinstance(parent, str):
raise ValueError('parent_id 必须是字符串')
if parent != '0' and not any(n['id'] == parent for n in nodes):
raise ValueError('找不到上级地区')
return {'ok': True, 'environment': data['environment'], 'parent_id': parent,
'regions': [n for n in nodes if n['parent_id'] == parent]}
if op not in ('resolve', 'prepare'):
raise ValueError('op 必须是 children、resolve 或 prepare')
detail = request.get('detail', '')
if not isinstance(detail, str):
raise ValueError('detail 必须是字符串')
detail = detail.strip()
detail_required = not bool(detail)
try:
if op == 'resolve':
names, ids = request.get('names'), request.get('ids')
if (names is None) == (ids is None) or 'address' in request:
raise ValueError('resolve 请提供 names 或 ids 中的一项')
path = named_path(string_list(names if names is not None else ids, (3,)), nodes, ids is not None)
else:
if 'ids' in request or ('address' in request) == ('names' in request):
raise ValueError('prepare 请提供 address 或 names 中的一项,不接受ids')
if 'address' in request:
address = request['address']
if 'detail' in request or not isinstance(address, str) or not address.strip() or len(address) > 4096:
raise ValueError('address 须为非空地址文本,不能同时传入detail,最长4096字符')
path, detail = text_path(address, nodes)
detail_required = not bool(detail)
else:
names = string_list(request['names'], (3, 4))
path = named_path(names[:3], nodes)
if len(names) == 4 and detail == names[3]:
detail_required = True
if len(names) == 4 and not detail.startswith(names[3]):
detail = names[3] + detail
# 只写到街道/乡镇仍须补充位置;不强制门牌必须含数字。
detail_required = detail_required or bool(re.fullmatch(r'.+(?:街道|乡|镇)', detail))
ids, names = [n['id'] for n in path], [n['name'] for n in path]
return {'ok': True, 'environment': data['environment'], 'ids': ids, 'names': names,
'region_id_path': ','.join(ids), 'region_path': ','.join(names),
'detail': detail, 'detail_required': detail_required, 'requires_confirmation': True,
'snapshot_at': data.get('retrieved_at')}
except RegionMatchError as exc:
return exc.result
def main():
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument('--data-file', type=Path,
help='当前环境的可信地区目录;默认按environment选择内置prod或pre快照')
args = parser.parse_args()
try:
request = json.load(sys.stdin)
if not isinstance(request, dict):
raise ValueError('请求必须为 JSON 对象')
if 'environment' not in request:
request['environment'] = json.loads((SKILL_DIR / 'defaults.json').read_text(encoding='utf8'))['environment']
environment = request['environment']
data_file = args.data_file
if data_file is None:
if environment not in ('prod', 'pre'):
raise ValueError('当前环境没有内置地区目录,请用--data-file提供同环境可信目录')
data_file = SKILL_DIR / 'data' / ('regions-' + environment + '.json')
data = json.loads(data_file.read_text(encoding='utf-8-sig'))
result = lookup(request, data)
except (ValueError, KeyError, OSError) as exc:
result = {'ok': False, 'error': 'INVALID_REQUEST_OR_DATA', 'message': str(exc)}
print(json.dumps(result, ensure_ascii=False))
return 0 if result['ok'] else 1
if __name__ == '__main__':
sys.exit(main())
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |