Skills Plugins MCP Prompt Model 博客 我的中心

sales-brief

Surfaces top and bottom sellers, identifies seasonality patterns, and produces a 2-week content brief to push winners and clear slow movers. Accepts optional lookback window of 30, 60, or 90 days.

DeepseekModel キュレーション済みスキル 品質 優秀 · 90 v1.0.0

取得

https://deepseekmodel.com/api/download.php?id=anthropics-knowledge-work-plugins-small-business-skills-sales-brief-skill-md&format=skill
ダウンロード .skill 標準形式。system_prompt と model_config を収録し、任意の Agent で利用可能
.skill ファイルの system_prompt フィールドの実際の内容。
name sales-brief description Surfaces top and bottom sellers, identifies seasonality patterns, and produces a 2-week content brief to push winners and clear slow movers. Accepts optional lookback window of 30, 60, or 90 days. allowed-tools Read, WebFetch, Bash Run the sales analysis and content brief. Pull what sold (and what didn't), explain why, and produce a ready-to-use content plan that acts on the data. Parse arguments: --lookback (default: 30d ) — 30d , 60d , or 90d lookback window Step 1 — Sales breakdown Using the content-strategy skill workflow for sales analysis: Pull PayPal transactions for the lookback period grouped by item/service/SKU. Pull QuickBooks revenue by product/service category. Rank products by: total revenue, unit volume, and margin (if available in QB). Calculate each product's share of total revenue vs. prior equivalent period. Top sellers: products that grew share or maintained top-3 rank. Bottom sellers: products with declining volume or below 5% of revenue. Step 2 — Seasonality check Compare current period to same period in prior year (if QB history available). Flag any items with a seasonal pattern (e.g., spikes in Q4, slow summers). Note any new products with insufficient history to detect seasonality. Step 3 — Why analysis For each top and bottom seller, explain the likely driver: Price change, promo, new channel, seasonal demand, competitor move Cross-reference with HubSpot campaign activity for the period Note where attribution is inferred vs. confirmed Step 4 — 2-week content brief Produce a ready-to-use content brief: 2-Week Content Brief — {date range} PUSH THESE (winners) • {product}: {suggested angle} — {channel: email|social|both} • {product}: {suggested angle} — {channel} CLEAR THESE (slow movers) • {product}: {promo angle or bundle suggestion} — {channel} CONTENT CALENDAR Week 1: Mon: {post/email concept} Wed: {post/email concept} Fri: {post/email concept} Week 2: Mon: {post/email concept} Wed: {post/email concept} Fri: {post/email concept} Connector failures If both QuickBooks and PayPal are unreachable, stop — sales analysis requires at least one revenue source. If only one is connected, run from that source and note "QuickBooks not connected — revenue data from PayPal only" (or vice versa). If HubSpot is missing, skip campaign cross-reference in the "why analysis" and note it. Approval gates Never auto-schedule or publish content. The brief is for owner review only. Never create Canva assets automatically — offer to generate them after owner approves the brief. Output Present the sales analysis, then the content brief. Ask the owner if they'd like to generate Canva assets for any of the planned posts.
このスキルを起動するキーワード。クリックでコピーできます。

このスキルにはトリガーワードがありません。

ダウンロードした .skill に含まれるフィールド。
フィールド 説明
formatフォーマット識別子(skill/v1)
skill_idスキル固有 ID
nameスキル名
versionバージョン
description説明
categoryカテゴリ(配列)
trigger_wordsトリガーワード
tagsタグ
sourceソース
source_urlソース URL(本ページ)
exported_atエクスポート日時(ダウンロード毎)
system_promptシステムプロンプト本文
model_configモデル設定:provider / model / temperature / max_tokens / top_p
examplesサンプル
install_guide各プラットフォームの導入説明(Coze / Dify / Claude / カスタム)
同じスキルを各プラットフォーム形式で出力できます。
.skill 標準形式。system_prompt と model_config を収録し、任意の Agent で利用可能 ダウンロード
.skillpro 拡張形式。scripts / tools / dependencies / hooks を含む ダウンロード
.json 純粋な JSON 出力。system_prompt とモデル設定のみ ダウンロード
Coze frontmatter 付き Markdown。Coze へのインポート用 ダウンロード
Dify Dify DSL。アプリ作成後にそのままインポート ダウンロード

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。

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。