Skills Plugins MCP Prompt Model 博客 我的中心

close-month

Closes the month — reconciles QB vs payment processors, flags gaps, writes P&L narrative, exports close packet. Accepts optional month and save-to arguments.

DeepseekModel 官方收录技能 质量 优秀 · 90 v1.0.0

获取

https://deepseekmodel.com/api/download.php?id=anthropics-knowledge-work-plugins-small-business-skills-close-month-skill-md&format=skill
下载 .skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用
.skill 文件中 system_prompt 字段的实际内容。
name close-month description Closes the month — reconciles QB vs payment processors, flags gaps, writes P&L narrative, exports close packet. Accepts optional month and save-to arguments. allowed-tools Read, WebFetch, Bash Run the month-end close workflow. Reconcile, flag gaps, narrate the P&L, and export the close packet for the owner's records (and their accountant). Parse arguments: --month (default: previous calendar month) — YYYY-MM format --save-to (default files ) — files (Google Drive / OneDrive), desktop (local), or both Step 1 — Reconcile Trigger the month-end-prep skill workflow: Pull all QuickBooks transactions for the target month. Pull settlements from each connected payment processor (PayPal, Stripe, Square) for the same month. Match QB entries to processor settlements by amount + date (±2 days). Surface three gap categories: Unmatched processor settlements — money came in via PayPal/Stripe/Square but never landed in QB Unmatched QB deposits — QB shows income with no processor record (cash? wire? misclassified?) Variance lines — matched but amount differs (fees, refunds split) Step 2 — Flag suspicious entries Surface in the same report: Uncategorized transactions — QB entries with no category Suspicious duplicates — same amount, same vendor, within 3 days Missing receipts — QB entries above $75 with no attachment For each, recommend an action: categorize as X, delete duplicate, attach receipt from inbox. Wait for owner to triage flagged items before generating the narrative. Do not auto-categorize or auto-delete. Step 3 — P&L narrative After triage, generate a plain-English P&L narrative: {Month YYYY} closed at ${revenue} revenue ({+/-}{X}% vs prior month). Top driver: {category/customer}. Biggest swing: {category} {direction} ${amount} because {reason inferred from transactions}. Margin: {X}% ({+/-}Y pts vs prior). {Cost-side commentary}. Three notable items: 1. ... 2. ... 3. ... Numbers come from QB; the why comes from cross-referencing top transactions, vendor names, and prior-month deltas. Step 4 — Export the close packet Generate two files: close-packet-{YYYY-MM}.xlsx — multi-tab workbook: Reconciliation — QB ↔ processor match table with gap rows highlighted Flagged — uncategorized / duplicates / missing receipts P&L — formatted income statement with prior-month delta column Trial Balance — accounts + ending balances close-packet-{YYYY-MM}.pdf — one-page summary: P&L narrative + top-line numbers + gap count Save both to the chosen --save-to location. Filename format: close-packet-2026-04.xlsx etc. Connector failures If QuickBooks is unreachable, stop — reconciliation requires QB as the source of truth. If a payment processor (PayPal, Stripe, Square) is unreachable, run reconciliation against the available processors and note "PayPal not connected — PayPal settlements skipped from reconciliation" (or whichever is missing). If all processors are missing, run QB-only analysis and flag it. Approval gates Never auto-fix flagged items. Always show the gap, recommend an action, wait for the owner. Never delete duplicates without explicit confirmation. Show both records side-by-side. Saving the packet is auto — it goes to the owner's own drive. Output End the run with a one-paragraph recap: revenue, margin, gap count remaining (if any), file paths to the saved packet. If gaps were not all resolved, list them so the owner can revisit.
Agent 识别该技能的关键词,点击任意一个即可复制。

该技能未提供触发词。

下载的 .skill 包内含以下字段。
字段 说明
format格式标识(skill/v1)
skill_id技能唯一 ID
name技能名称
version版本号
description技能描述
category所属分类(数组)
trigger_words触发词列表
tags标签列表
source来源标识
source_url来源链接(本页地址)
exported_at导出时间(每次下载生成)
system_prompt系统提示词正文
model_config模型参数:provider / model / temperature / max_tokens / top_p
examples示例
install_guide各平台导入说明(Coze / Dify / Claude / 自定义框架)
同一份技能可按不同平台格式导出。
.skill 标准格式,含 system_prompt 与 model_config,导入任意 Agent 框架即可使用 下载
.skillpro 增强格式,额外含脚本 / 工具 / 依赖 / 钩子占位 下载
.json 纯 JSON 导出,只含 system_prompt 与模型参数 下载
Coze 带 frontmatter 的 Markdown,Coze 平台导入用 下载
Dify Dify DSL,创建应用后直接导入 下载

每日精选 Skill 推荐,免费送到你邮箱

输入邮箱,每天接收一个精选 AI Agent 技能推荐。完全免费,持续更新。

验证码 --

提交后我们会发送一封确认邮件,点击邮件里的链接才会开始收信。

完全免费,取消任意时间。我们不会发送垃圾邮件。