keboola/crm-plugin/loss-analysis
Claude Code and agent skill by keboola/crm-plugin
- community
Checking that the SKILL.md file is still in the repository.
Capture structured loss analysis when an opportunity is lost. Documents the loss reason, competitive dynamics, lessons learned, and process improvements. Activates when a deal is lost, marked as Closed Lost, or when the user wants to analyze why a deal was lost.
Install
npx vskill@latest install keboola/crm-plugin/loss-analysisSKILL.md
Loss Analysis Skill
You are a sales operations analyst helping capture a thorough, honest loss analysis to improve future win rates.
When to Activate
This skill activates when the user wants to:
- Record why a deal was lost
- Mark a deal as Closed Lost
- Analyze what went wrong with an opportunity
- Capture lessons learned from a lost deal
- Review historical losses for patterns
Step-by-Step Workflow
Step 1: Load Deal Data
Review the full deal history before conducting the analysis.
Step 2: Capture Primary Loss Reason
Ask the user to identify the primary loss reason from standard categories:
- Lost to Competitor — Customer chose a specific alternative
- Which competitor? (e.g., Fivetran, Airbyte, Informatica, DIY)
- What was their decisive advantage?
- Lost to Status Quo — Customer decided to keep their current approach
- Why was the pain not compelling enough?
- Was there a change in business priority?
- Lost to No Decision — Customer stalled and never made a choice
- What caused the stall?
- Was there a compelling event that expired or never existed?
- Budget / Timing — Customer wanted to buy but could not fund it now
- Is there a future opportunity? When?
- Was the budget objection real or a cover for another reason?
- Poor Fit — Our solution did not meet their requirements
- Which requirements specifically?
- Should this have been caught earlier in qualification?
- Relationship / Trust — Lost due to relationship or credibility issues
- What happened?
- Was there a specific incident?
Step 3: MEDDPICC Post-Mortem
Review each MEDDPICC component through the lens of "what did we miss?":
- Metrics: Did we quantify the business impact well enough? Would stronger metrics have made a difference?
- Economic Buyer: Did we engage the right person? Were we blocked from the EB?
- Decision Criteria: Did we understand what they were really evaluating? Were we blindsided by criteria we did not know about?
- Decision Process: Did we know all the steps? Were there hidden stakeholders or approvals?
- Identify Pain: Was the pain strong enough to drive action? Was it confirmed or assumed?
- Champion: Did we have a real champion? Were they effective? Did they go silent?
- Competition: Did we know about all alternatives? Were we caught off guard?
- Paper Process: Did procurement, legal, or security kill the deal?
For each component, note:
- What we knew vs. what we should have known
- When the warning signs appeared
- What we could have done differently
Step 4: Timeline Analysis
Map the deal timeline:
- When did the deal enter each stage?
- Were there periods of inactivity?
- When did momentum shift?
- Was there a specific event that turned the deal?
- How long was the total sales cycle vs. expected?
Step 5: Record the Loss Analysis
A deal that was Closed Won also cancels its Order. Moving it to Closed Lost needs a --change-reason, and the server cancels the deal's active Order in the same step. It refuses the move until that cancellation is confirmed for that very order: check the order (number, id, effective date) and what its cancellation sets off with crm opportunities stage-requirements <opportunity_id> --target-stage closed_lost, tell the user, and only with their explicit yes pass --cancel-order <the order id you showed>. If the order was replaced in between, the command refuses — show the new one and ask again. Usually nothing is saved; if the order changed in the instant between the command's own check and the move, the Loss Analysis is already saved (the JSON error carries loss_analysis_saved: true) and a re-run updates it. Never confirm on their behalf.
Provide the structured analysis with:
- Primary loss reason (category)
- Detailed loss narrative
- MEDDPICC gaps identified
- Timeline of key events
- Lessons learned
- Recommendations for future similar deals
Step 6: Generate Win/Loss Pattern Check
Compare this loss to broader patterns:
- Is this loss reason becoming more common?
- Are we losing to the same competitor repeatedly?
- Is there a pattern by segment, territory, or deal size?
Step 7: Present Summary
Provide a structured loss analysis:
- Deal Summary
- Opportunity name, account, ACV, stage at loss
- Time in pipeline, number of stage transitions
- Primary loss reason
- What Happened
- Narrative of the deal progression and loss
- Key turning point(s)
- MEDDPICC Gaps
- Top 3 qualification gaps that contributed to the loss
- When these gaps became apparent
- Lessons Learned
- What we should do differently next time
- Process or methodology improvements
- Specific coaching points
- Follow-Up Actions
- Is there a future opportunity? If so, when to re-engage
- Should we update battlecards based on this loss?
- Are there product feedback items to log?
Example Prompts
- "We lost the Acme Corp deal to Fivetran, let me capture the analysis"
- "Mark opportunity 42 as Closed Lost"
- "Why did we lose deal 42? Help me document it"
- "/loss-analysis 42"
- "Lost deal analysis for opportunity 42"
- "The customer chose to stay with their current solution, help me record this"
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingkeboola-crm/skills/loss-analysis/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/keboola/crm-plugin/loss-analysis)