CtrlK
BlogDocsLog inGet started
Tessl Logo

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

1.41x
Quality

51%

Does it follow best practices?

Impact

75%

1.41x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/all-skills/skills/close-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is functional but overly verbose for what amounts to a relatively simple set of CRM API operations. The repetitive template structure across workflows inflates token usage without adding proportional value, and many 'pitfalls' state things Claude would already know. The lack of executable MCP call examples and the instruction to always search for current schemas somewhat undermines the documented parameter details.

Suggestions

Consolidate the six workflow sections into the quick reference table with a brief shared note about common parameters (lead_id requirement, ID formats), eliminating the repetitive template structure to cut token usage by ~60%.

Add at least one concrete, executable MCP tool call example showing the actual syntax for invoking a Rube MCP tool (e.g., a complete CLOSE_CREATE_LEAD call with realistic parameters).

Add an explicit validation/confirmation step to the Delete Activities workflow (e.g., 'Confirm the activity ID and verify with the user before deleting, as deletion is permanent').

Move the Known Pitfalls and Common Patterns sections to a separate reference file and link to it from the main skill, keeping SKILL.md focused on the quick-start workflow.

DimensionReasoningScore

Conciseness

The skill is highly verbose and repetitive. Each workflow section follows the same template with 'When to use', 'Tool sequence', 'Key parameters', and 'Pitfalls' even when the content is trivial. Many pitfalls state obvious things Claude would know (e.g., 'Duration is in seconds, not minutes', 'Deletion is permanent'). The 'Common Patterns' section repeats information already covered. The data model explanation and ID resolution patterns are largely redundant with the workflow sections.

1 / 3

Actionability

The skill provides tool names and parameter lists, which is somewhat concrete, but lacks executable code or actual MCP call examples with real syntax. The patterns are described in pseudocode-like blocks rather than actual executable calls. The instruction to 'Always call RUBE_SEARCH_TOOLS first to get current tool schemas' undermines the specificity of the documented parameters since they may be stale.

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 mostly single-tool operations without meaningful multi-step sequences. The delete workflow lacks a confirmation/validation step despite being destructive (the pitfalls mention it's permanent but there's no explicit 'confirm before deleting' checkpoint). Bulk operations mention needing delays but provide no concrete feedback loop.

2 / 3

Progressive Disclosure

The content is a monolithic document with no references to supporting files despite being long enough to warrant splitting (e.g., the Known Pitfalls and Common Patterns sections could be separate references). The quick reference table at the end is helpful, but the overall structure puts too much inline content that could be better organized across files. However, sections are clearly headed and the table provides good navigation.

2 / 3

Total

7

/

12

Passed

Description

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 reasonably strong with specific actions and a clear niche targeting Close CRM via a specific integration. Its main weaknesses are the lack of an explicit 'Use when...' trigger clause and limited coverage of natural user terms beyond the core actions listed.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Close CRM, managing sales leads, logging calls, sending SMS, or tracking CRM tasks and notes.'

Include additional natural trigger terms users might say, such as 'contacts', 'deals', 'pipeline', 'sales CRM', or 'follow-up' to improve discoverability.

DimensionReasoningScore

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' with specific CRM actions, but lacks an explicit 'Use when...' clause. The 'when' is only implied by the nature of the actions described, which caps this at 2 per the rubric guidelines.

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 mention of 'Close CRM' and 'Rube MCP (Composio)' — this is a very clear niche that is unlikely to conflict with other skills unless there are multiple Close CRM integrations.

3 / 3

Total

10

/

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
davepoon/buildwithclaude
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.