churn-lost-deal-analysis
Read lost deals and churned accounts from your CRM, extract reasons clustered by theme (missing features, pricing, competitors, UX), and write a prioritized weekly analysis with product improvement recommendations. Use before roadmap planning or to build the case for prioritizing retention work.
79
75%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./analytics-skills/skills/churn-lost-deal-analysis/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly articulates specific capabilities (CRM data reading, theme-based clustering, weekly analysis writing), includes rich natural trigger terms across the sales/product domain, and provides explicit guidance on when to use it. The description is concise yet comprehensive, with a well-defined niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: reading lost deals and churned accounts from CRM, extracting reasons clustered by theme (with examples: missing features, pricing, competitors, UX), and writing a prioritized weekly analysis with product improvement recommendations. | 3 / 3 |
Completeness | Clearly answers both 'what' (read lost deals/churned accounts, extract reasons by theme, write prioritized weekly analysis with recommendations) and 'when' ('Use before roadmap planning or to build the case for prioritizing retention work'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'lost deals', 'churned accounts', 'CRM', 'missing features', 'pricing', 'competitors', 'UX', 'roadmap planning', 'retention', 'product improvement'. These cover a good range of terms a user working in this domain would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining CRM churn/loss analysis with product improvement recommendations. The specific focus on lost deals, churned accounts, and themed clustering makes it unlikely to conflict with general CRM, analytics, or product management skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured prompt template for churn analysis with clear thematic categories and a useful ARR-weighted ranking approach. Its main weaknesses are the lack of concrete tool invocations (no MCP tool calls, API examples, or executable code), missing validation checkpoints in the workflow, and some unnecessary introductory context. It reads more like a prompt recipe than an actionable skill with verifiable steps.
Suggestions
Add concrete MCP tool invocation examples (e.g., specific HubSpot MCP calls to fetch lost deals, Google Drive MCP calls to write the output file) instead of relying on natural language instructions.
Add validation checkpoints: verify CRM data was retrieved (e.g., 'If 0 records returned, check filter criteria and report to user'), verify clustering produced at least N themes before proceeding to ranking, and confirm file was written successfully.
Remove the introductory paragraph explaining what lost deal notes are — Claude already understands this context. Start directly with the prompt template or a brief one-line purpose statement.
Consider providing a concrete example output snippet showing what the final ChurnAnalysis markdown file should look like, so Claude has a clear target format.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The opening paragraph explains what lost deal notes are and why they matter — context Claude doesn't need. The prompt template itself is reasonably efficient, but the introductory framing and some tips are padding. Could be tightened by ~30%. | 2 / 3 |
Actionability | The prompt template provides a structured multi-step workflow with specific fields to collect and output formats, which is good. However, there are no concrete code snippets, API calls, or MCP tool invocations — it's a natural language prompt template rather than executable guidance. Claude would need to figure out how to actually query HubSpot/Attio/Salesforce and write to Google Drive. | 2 / 3 |
Workflow Clarity | The five steps are clearly sequenced and logically ordered. However, there are no validation checkpoints — no step to verify CRM data was actually retrieved, no check that the clustering is reasonable, no validation before writing the final report. For a batch data-processing workflow writing output files, this lack of verification caps the score. | 2 / 3 |
Progressive Disclosure | The content is reasonably structured with sections (Prompt Template, Setup, Placeholders, Tips) and references competitor-monitoring as a related skill. However, there are no bundle files and no external references for advanced topics like CRM-specific query patterns or output format templates. The prompt template itself is quite long and could benefit from being split or having detailed sections referenced externally. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- amplitude/builder-skills
- Commit
221ffaa
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.