From solo
This skill should be used when the user asks to 'analyze diagnostic', 'diagnostic results', or 'review assessment scores'.
npx claudepluginhub jamon8888/cc-suite --plugin SoloThis skill uses the workspace's default tool permissions.
A single diagnostic response tells you about one person. Ten responses tell you about a pattern. The analyzer surfaces what the pattern reveals โ about your ICP, your messaging, your offer, and your pipeline.
Provides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Analyzes multiple pages for keyword overlap, SEO cannibalization risks, and content duplication. Suggests differentiation, consolidation, and resolution strategies when reviewing similar content.
Share bugs, ideas, or general feedback.
A single diagnostic response tells you about one person. Ten responses tell you about a pattern. The analyzer surfaces what the pattern reveals โ about your ICP, your messaging, your offer, and your pipeline.
diagnostic-monitor-agent)For each diagnostic, show:
## Score Distribution: [Diagnostic Name]
**Total responses:** [N] | **Period:** [date range]
| Band | Respondents | % | Avg score |
|------|-------------|---|-----------|
| ๐ข High (66โ100) | [N] | [X%] | [avg] |
| ๐ก Medium (36โ65) | [N] | [X%] | [avg] |
| ๐ด Low (0โ35) | [N] | [X%] | [avg] |
**Overall average:** [X] / 100
**Median:** [X]
**Range:** [min] โ [max]
What to flag:
For each dimension, show the average score across all respondents:
## Dimension Averages
| Dimension | Avg score | % of max | Interpretation |
|-----------|-----------|----------|---------------|
| [Dim 1] | [X]/[max] | [X%] | ๐ข Healthy across respondents |
| [Dim 2] | [X]/[max] | [X%] | ๐ก Mixed โ worth watching |
| [Dim 3] | [X]/[max] | [X%] | ๐ด Consistently weak |
| [Dim 4] | [X]/[max] | [X%] | |
What consistently low dimensions reveal:
| Diagnostic type | Low dimension | Likely interpretation |
|---|---|---|
| Lead | Problem Clarity | Your marketing is attracting too-early buyers โ they haven't defined the problem yet |
| Lead | Budget Reality | Wrong ICP segment โ targeting too small or too early-stage |
| Client | Goal Progress | Delivery gap โ something about how you work needs examining |
| Client | Value Perception | Communication gap โ results aren't being attributed to your work |
| Product | Willingness to Pay | Problem exists but isn't painful enough to pay for |
| Self | Differentiation | Positioning work needed before growing |
Group respondents by band and look for patterns within each group:
## High-Band Respondents ([N] people)
Common characteristics:
- [Dimension X] average: [X%] (highest across all segments)
- [Dimension Y] average: [X%]
- Most common answer on [key question]: "[Option]"
What this tells you: [2-3 sentence interpretation]
โ ICP match: [High / Medium / Low] โ [brief reason]
## Low-Band Respondents ([N] people)
Common characteristics:
- [Dimension X] average: [X%] (lowest)
- Most common answer on [key question]: "[Option]"
What this tells you: [2-3 sentence interpretation]
โ These respondents need: [education / different service / different timing]
Show which specific questions are getting the strongest/weakest answers:
## Question Heatmap
| Question | Avg score | % picking score 0 | % picking score 4 |
|----------|-----------|-------------------|-------------------|
| [Q1 text abbreviated] | [X]/4 | [X%] | [X%] |
| [Q2] | | | |
[...]
**Most revealing questions (highest variance):**
[List questions where answers are most spread โ these are the real discriminators]
**Least revealing questions (everyone scores the same):**
[Questions where 80%+ of respondents picked the same option โ consider replacing]
For lead diagnostics, connect score to pipeline outcomes:
## Pipeline Impact
| Cohort | Respondents | Proposals sent | Converted | Conversion rate |
|--------|-------------|----------------|-----------|----------------|
| ๐ข High band | [N] | [N] | [N] | [X%] |
| ๐ก Medium band | [N] | [N] | [N] | [X%] |
| ๐ด Low band | [N] | [N] | [N] | [X%] |
**Key finding:** [What the conversion data reveals about which band is worth pursuing]
**Recommendation:** [Adjust pipeline stage routing / change CTA for medium band / etc.]
Note: Requires cross-referencing response files with pipeline.md. Run automatically by diagnostic-monitor-agent weekly.
When 3+ weeks of data exist, show trend:
## Score Trend Over Time
| Week | Responses | Avg score | Band distribution |
|------|-----------|-----------|-------------------|
| [W1] | [N] | [X] | ๐ด[N] ๐ก[N] ๐ข[N] |
| [W2] | [N] | [X] | |
| [W3] | [N] | [X] | |
**Trend:** [Improving / Declining / Stable] โ [interpretation]
If improving: Your diagnostic is reaching a better-fit audience over time,
or respondents' actual situations are improving.
If declining: Traffic source quality may be degrading, or seasonal effects.
Always end with 2โ3 concrete actions:
## What This Data Suggests
**Finding 1:** [The most important pattern]
โ Action: [Specific thing to change or do]
**Finding 2:** [Second pattern]
โ Action: [Specific action]
**Finding 3:** [Third pattern, if applicable]
โ Action: [Specific action]
## Recommended Diagnostic Updates
Based on [N] responses, consider updating:
- [ ] Replace [Q] โ [X%] of respondents picked the same option (not discriminating)
- [ ] Adjust [band] threshold โ most [high/medium] scorers are [behaving differently than expected]
- [ ] Add a [dimension] โ several respondents mentioned [theme] in the notes that isn't captured
Primary question: Are high-scoring leads converting better than low-scoring ones?
If yes โ the diagnostic is working. Consider tightening the CTA for Medium to filter further. If no โ either the questions aren't measuring fit, or the score threshold is wrong.
Secondary question: Which dimension best predicts conversion?
The dimension with the highest correlation to Closed Won is the one to weight more heavily in the next iteration.
Primary question: What do low-scoring clients have in common?
Look for patterns: industry, project type, engagement length, contract size, how they came in. The pattern reveals the clients to be more selective about accepting.
Secondary question: Are you running health checks early enough?
If churn is happening before the diagnostic reveals it, the cadence is too infrequent or the questions aren't detecting the right early signals.
Primary question: Is the average score above 55?
60 across 30+ respondents โ strong signal to build
Secondary question: Which dimension scores are lowest โ and why?
If Willingness to Pay is low even when Pain Acuity is high โ price sensitivity issue, not demand issue. If Current Solution Dissatisfaction is low โ alternatives are working well enough. These are different problems with different solutions.
Analysis report: data/1-Projets/diagnostics/[slug]/analysis-[date].md
diagnostic-monitor-agent: runs this skill weekly for all active diagnosticsmonday-morning-agent: receives diagnostic summary in Monday briefing if configuredsales-pipeline: cross-reference lead scores with pipeline outcomesbusiness-health-advisor: client health diagnostic data feeds into overall health scandiagnostic-builder: analysis recommendations feed into next diagnostic iteration