close-automation
Automate Close CRM tasks via Rube MCP (Composio): create leads, manage calls/SMS, handle tasks, and track notes. Always search tools first for current schemas.
63
51%
Does it follow best practices?
Impact
75%
1.41xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/close-automation/SKILL.mdQuality
Discovery
67%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is strong in specificity and distinctiveness, clearly naming the platform (Close CRM) and listing concrete actions. However, it lacks an explicit 'Use when...' clause which limits its completeness score, and the trigger terms could better cover natural user language variations beyond the technical tool names.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Close CRM, managing leads, logging calls or SMS, or tracking sales activities.'
Include more natural user-facing trigger terms like 'contacts', 'deals', 'pipeline', 'sales CRM', or 'follow-ups' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'create leads, manage calls/SMS, handle tasks, and track notes.' Also includes the operational guidance to 'search tools first for current schemas.' | 3 / 3 |
Completeness | Clearly answers 'what does this do' (automate Close CRM tasks with specific actions), but lacks an explicit 'Use when...' clause. The 'when' is only implied by the domain context rather than stated with trigger guidance. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Close CRM', 'leads', 'calls', 'SMS', 'tasks', 'notes', and 'Rube MCP (Composio)', but misses common user variations like 'contacts', 'deals', 'pipeline', 'follow-up', or 'CRM automation'. Users might not naturally say 'Rube MCP' or 'Composio'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific platform references ('Close CRM', 'Rube MCP', 'Composio'). Unlikely to conflict with other skills given the narrow, well-defined niche. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a comprehensive catalog of Close CRM operations with useful parameter details and pitfall warnings, but suffers from significant verbosity and repetitive structure. It lacks executable examples showing actual tool invocations, and the destructive delete operation has no validation/confirmation step. Much of the content (CRM data models, rate limiting concepts, ID format patterns) is general knowledge that Claude doesn't need explained.
Suggestions
Cut the content by ~50%: remove 'When to use' descriptions, the CRM data model explanation, rate limiting basics, and consolidate per-workflow pitfalls into the single 'Known Pitfalls' section.
Add at least one concrete, executable tool invocation example showing actual RUBE_SEARCH_TOOLS and CLOSE_CREATE_LEAD calls with realistic parameters.
Add an explicit confirmation/validation step to the delete workflow (e.g., retrieve the call first to verify the ID, confirm with user before deletion).
Consolidate the quick reference table as the primary content and move detailed per-tool parameters to a separate reference file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Significant verbosity throughout. The skill repeats patterns extensively (every workflow section has the same structure with 'When to use', 'Tool sequence', 'Key parameters', 'Pitfalls' even when most are single-tool operations). The 'Common Patterns' section restates information already covered. Claude already understands CRM data models, ID formats, and rate limiting concepts. The content could be cut by 50%+ without losing actionable information. | 1 / 3 |
Actionability | Tool names and parameter lists are concrete and useful, but there are no executable code examples or actual API call demonstrations. The 'ID Resolution' and 'Activity Logging Pattern' sections use pseudocode-style numbered lists rather than actual tool invocation examples. The instruction to 'always call RUBE_SEARCH_TOOLS first' is good but no example invocation is shown. | 2 / 3 |
Workflow Clarity | The setup section has a clear 4-step sequence with a validation checkpoint (confirm ACTIVE status). However, the core workflows are all single-tool operations presented as 'sequences' which is misleading. The delete workflow lacks a confirmation/validation step despite being destructive ('Deletion is permanent and cannot be undone' is noted as a pitfall but no verification step is included). Missing feedback loops for destructive operations caps this at 2. | 2 / 3 |
Progressive Disclosure | The content is structured with clear headers and a quick reference table, which aids navigation. However, it's monolithic — all content is inline in one file with no references to separate detailed docs. The 'Known Pitfalls' section and per-workflow pitfalls could be consolidated or split out. The external link to Composio toolkit docs is good but underutilized. | 2 / 3 |
Total | 7 / 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
- davepoon/buildwithclaude
- Commit
7cc63f3
- 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.