sales-coaching
AI sales coach composite. Analyzes all available sales data — email campaigns, call recordings/transcripts, reply patterns, pipeline outcomes — to identify what the user does well, where they struggle, and how to improve. Finds patterns in top-performing emails, winning call techniques, successful objection handles, and deal progression. Produces personalized coaching recommendations based on their specific product, market, and selling style. Tool-agnostic.
npx skills add gooseworks-ai/goose-skills --skill sales-coaching --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
An AI coach that studies your sales activity across emails, calls, and deals, identifies patterns from your best and worst performances, and produces personalized coaching to improve your selling skills. It focuses on your data rather than generic advice, using your top emails, winning call techniques, and common objection handling to generate a tailored coaching plan.
How it works
- Loads the composite when user intents indicate a desire to improve sales or seek coaching (examples include phrases like those listed in the frontmatter under "When to Auto-Load").
- Step 0 configuration collects a user profile (role, experience, product description, average deal size, sales cycle) and data source choices (email tool, call tool, CRM, transcripts availability, analysis window). Stored fields include:
user_role,experience_level,product_description,avg_deal_size,sales_cycle_days,self_assessed_weakness,email_tool,call_tool,crm_tool,transcripts_available,analysis_window. - Step 1 gathers data from all configured sources for the specified window, including email campaigns and replies, call transcripts/recordings, pipeline deals, meeting notes, and calendar data. Output includes a collected_data object with email_data, call_data, pipeline_data, data_richness, and data_summary.
- Step 2 analyzes email performance to identify top-performing emails and worst performers, extracting patterns for subject lines, openers, body structure, personalization, CTAs, tone, frameworks, and proof points. It also generates comparisons between winners and losers, analyzes objection patterns and sentiment, and rates overall email skill quality with a summary.
- Step 3 analyzes call performance when data exists, including structural metrics (talk-to-listen ratio, longest monologue, question count/depth, filler words, call duration) and discovery quality (pain discovery, impact quantification, decision process, current state, compelling event, next steps). It also assesses objection handling during calls and, if available, demo effectiveness and patterns distinguishing winning vs losing calls.
When to use it
Load and run when the user requests coaching, wants to review selling style, asks for patterns in sales activity, or seeks to diagnose personal performance after a poor period. Triggers include phrases like "how can I improve my sales", "coach me", "review my selling style", or after a bad quarter/month.
What it can touch
- Data sources as configured: email campaigns, email replies, call transcripts/recordings, pipeline deals, meeting notes, calendar data.
- The analysis results are produced as structured outputs (e.g., email_patterns, call_patterns). The skill references tools in its analysis contracts but does not execute external tool actions beyond data interpretation.
Caveats
- The review is based on the data available from configured sources and described in the output contracts; results depend on data richness (full, partial, minimal).
- It provides coaching recommendations derived from the user’s own data, not generic advice.
# Sales Coaching An AI coach that studies everything you do in sales — your emails, your calls, your deals — finds the patterns in what works and what doesn't, and gives you specific, actionable coaching to get better. This isn't generic sales advice ("always be closing"). It's coaching derived from YOUR data: your top-performing emails, your winning calls, your successful deal patterns, your most common objection fumbles, and your specific product's market. **What makes this different from `sequence-performance`:** | Composite | Focus | Output | |-----------|-------|--------| | `sequence-performance` | How is this campaign doing? | Campaign metrics + copy diagnosis | | `sales-coaching` | How can THIS person sell better? | Personal skill assessment + coaching plan | The other composite analyzes the work. This one coaches the worker. ## When to Auto-Load Load this composite when: - User says "how can I improve my sales", "coach me", "what am I doing wrong", "sales coaching", "help me sell better" - User says "review my selling style", "analyze my calls", "what patterns do you see in my sales" - User asks "why am I losing deals", "why aren't people responding", "what are my best emai
- When to Auto-Load
- Step 0: Configuration (One-Time Setup)
- User Profile
- Data Sources
- Step 1: Collect Sales Data
- Input Contract
- Data Collection Matrix
- Output Contract
- Human Checkpoint
- Step 2: Analyze Email Performance Patterns
- Process
- Step 3: Analyze Call Performance Patterns
- Step 4: Analyze Deal Patterns
- Step 5: Build Skill Assessment & Coaching Plan
What does the sales-coaching skill do?
AI sales coach composite. Analyzes all available sales data — email campaigns, call recordings/transcripts, reply patterns, pipeline outcomes — to identify what the user does well, where they struggle, and how to improve. Finds patterns in top-performing emails, winning call techniques, successful objection handles, and deal progression. Produces personalized coaching recommendations based on their specific product, market, and selling style. Tool-agnostic.
How do I install it?
Run `npx skills add gooseworks-ai/goose-skills --skill sales-coaching --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From gooseworks-ai/goose-skills, a repository with 1,091 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.