Assess deal health and identify at-risk opportunities using engagement signals, stakeholder mapping, and velocity analysis
npx skills add https://github.com/guia-matthieu/clawfu-skills --skill deal-risk-scoring
> Evaluate individual deal health through multi-signal analysis to prioritize coaching, intervention, and resource allocation.
Based on Gong's Deal Intelligence research and Winning by Design's Revenue Architecture, analyzing:
| Claude Does | You Decide |
|-------------|------------|
| Scores deals on risk factors | Which deals to save vs. let go |
| Identifies missing elements | Resource allocation priorities |
| Suggests intervention actions | Executive sponsor assignments |
| Tracks velocity trends | Final stage/probability updates |
| Flags competitive threats | Win strategy adjustments |
Assess the risk for this deal:
Deal: [Company Name]
Value: $X
Stage: [Current Stage]
Close Date: [Target Date]
Days in Stage: X
Recent Activity:
- [List emails, meetings, calls with dates]
Stakeholders:
- [Name, Title, Role in deal, Engagement level]
Competition: [Known competitors]
Champion: [Name and strength assessment]
| Criteria | Points |
|----------|--------|
| Meeting in last 7 days | +10 |
| Email response in last 3 days | +5 |
| Multiple contacts engaged | +5 |
| Prospect initiating contact | +5 |
| No activity 14+ days | -15 |
| Criteria | Points |
|----------|--------|
| Economic Buyer identified | +10 |
| Champion confirmed | +10 |
| Technical evaluator engaged | +5 |
| Only 1 contact | -10 |
| No C-level access | -5 |
| Criteria | Points |
|----------|--------|
| Clear next step scheduled | +10 |
| Mutual action plan agreed | +10 |
| Decision timeline confirmed | +5 |
| Close date pushed 2+ times | -15 |
| No defined process | -10 |
| Criteria | Points |
|----------|--------|
| No competition | +15 |
| Differentiation clear | +10 |
| Incumbent advantage | -10 |
| Price pressure | -5 |
| Unknown competitive status | -5 |
| Score | Health | Action |
|-------|--------|--------|
| 75-100 | 🟢 Green | Monitor, standard process |
| 50-74 | 🟡 Yellow | Intervention needed |
| 25-49 | 🟠 Orange | Escalate, major action |
| 0-24 | 🔴 Red | Rescue or disqualify |
Input:
Deal: TechCorp Global
Value: $250K ARR
Stage: 3 - Proposal
Close Date: Feb 28 (pushed from Jan 31)
Days in Stage: 28
Recent Activity:
- Jan 15: Proposal sent to John (Dir of Ops)
- Jan 22: Follow-up email (no response)
- Jan 29: Called, voicemail
- Feb 5: Email asking for update (no response)
Stakeholders:
- John Smith, Director of Ops, Champion (was engaged)
- No other contacts
Competition: Competitor X mentioned in discovery
Champion: John - went silent
Output:
## Deal Risk Assessment: TechCorp Global
### Overall Score: 28/100 🔴 RED - HIGH RISK
### Score Breakdown
| Factor | Score | Issues |
|--------|-------|--------|
| Engagement | 0/25 | No response in 14+ days |
| Stakeholders | 5/25 | Single-threaded, no EB |
| Process | 5/25 | Pushed once, no clear next step |
| Competition | 18/25 | Competitor known but not blocking |
| **Total** | **28/100** | |
### Critical Risks
1. **🔴 Champion Gone Dark** - John hasn't responded in 14 days
- Possible: Left company, lost internal support, chose competitor
2. **🔴 Single-Threaded** - No other relationships
- If John is out, deal is dead
3. **🟠 No Economic Buyer** - Never met decision maker
- John may not have authority to close
### Recommended Actions
**This Week:**
1. Research John on LinkedIn - still at company?
2. Find another contact via LinkedIn/referral
3. Send "breakup email" to force response
4. Check if Competitor X is in active eval
**If No Response by Friday:**
- Move to Stage 2 or Closed-Lost
- Free up forecast slot
### Red Flags to Watch
- If proposal was forwarded to competitor
- If budget was reallocated
- If project was deprioritized
### Save Probability: 25%
Without new contact access, this deal is likely lost.
Input:
Deal: GrowthCo Inc
Value: $85K ARR
Stage: 4 - Negotiation
Close Date: Feb 15
Days in Stage: 7
Recent Activity:
- Feb 1: Demo to full team (8 attendees)
- Feb 3: Pricing discussion with CFO
- Feb 5: Legal reviewing MSA
- Feb 7: Call scheduled for Feb 10
Stakeholders:
- Maria Lopez, VP Sales (Champion, highly engaged)
- Tom Chen, CFO (Economic Buyer, positive)
- Legal team (reviewing contract)
- 8 end users attended demo
Competition: None identified
Champion: Maria - actively selling internally
Output:
## Deal Risk Assessment: GrowthCo Inc
### Overall Score: 88/100 🟢 GREEN - HEALTHY
### Score Breakdown
| Factor | Score | Status |
|--------|-------|--------|
| Engagement | 25/25 | Daily activity, prospect-driven |
| Stakeholders | 23/25 | EB + Champion + Users confirmed |
| Process | 22/25 | Clear timeline, legal in motion |
| Competition | 18/25 | No competition identified |
| **Total** | **88/100** | |
### Strengths
1. **✅ Multi-threaded** - Champion, EB, and end users engaged
2. **✅ Process momentum** - Legal reviewing = serious intent
3. **✅ Executive access** - CFO in pricing discussions
4. **✅ Champion active** - Maria driving internally
### Minor Risks
1. **🟡 Legal review** - Could surface unexpected blockers
- Mitigation: Pre-review common redlines
2. **🟡 No competition confirmed** - May be unknown
- Mitigation: Ask directly in next call
### Recommended Actions
**Feb 10 Call Prep:**
1. Prepare redline responses for common legal issues
2. Confirm decision process post-legal
3. Ask: "Is anyone else in consideration?"
4. Get verbal commit from Maria
### Close Probability: 85%
Deal is on track. Focus on removing legal friction.
## Deal: [Name] | Score: X/100 [Status Emoji]
### Quick Stats
- Value: $X | Stage: X | Days: X | Close: [Date]
### Scores
| Factor | Score | Key Issue |
|--------|-------|-----------|
| Engagement | /25 | |
| Stakeholders | /25 | |
| Process | /25 | |
| Competition | /25 | |
### Top 3 Actions
1.
2.
3.
pipeline-forecasting - Aggregate deal health into forecastlead-qualification-meddic - Deep qualification frameworkaccount-health - Post-sale relationship scoringIntegration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take guia-matthieu/deal-risk-scoring from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.