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.

49

Quality

54%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/close-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

38%Scale 1-5

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

The skill covers Close CRM operations comprehensively but suffers from significant verbosity through repetitive per-workflow structures that each describe a single tool call. It lacks executable examples showing actual tool invocation syntax, and the destructive delete operation has no validation checkpoint. The content would benefit greatly from condensation and splitting into a concise overview with detailed references.

Suggestions

Consolidate the six nearly identical workflow sections into the quick reference table with a single annotated example showing actual tool call syntax, moving detailed pitfalls to a separate PITFALLS.md file.

Add a concrete, copy-paste ready example of a RUBE_SEARCH_TOOLS call and at least one full tool invocation (e.g., CLOSE_CREATE_LEAD) with actual parameter JSON structure.

Add an explicit validation/confirmation step before the CLOSE_DELETE_CALL workflow (e.g., retrieve the call first, confirm details, then delete) since deletion is permanent.

Remove the vacuous 'When to Use' footer section and trim repeated information between individual workflow pitfalls and the 'Known Pitfalls' section.

DimensionReasoningScore

Conciseness

The skill is noticeably verbose with repetitive patterns across all six workflows (each has the same 'When to use / Tool sequence / Key parameters / Pitfalls' structure for what are essentially single-tool calls). The 'Common Patterns' section with pseudo-diagrams and the 'Known Pitfalls' section repeat information already stated in individual workflow sections. The 'When to Use' footer is vacuous. Much of this could be condensed significantly.

2 / 5

Actionability

The skill provides tool names and parameter lists, which is somewhat concrete, but lacks executable code examples or copy-paste ready tool invocations with actual parameter structures. The ID resolution and activity logging patterns are described in pseudocode/prose rather than concrete examples showing actual tool call syntax. The instruction to 'always call RUBE_SEARCH_TOOLS first' is good but the skill never shows what that call looks like.

3 / 5

Workflow Clarity

The setup sequence is clear (verify → connect → authenticate → confirm). However, the delete workflow lacks validation/confirmation steps despite being a destructive, permanent operation ('Deletion is permanent and cannot be undone' is noted but no verification step is included). Bulk operations are mentioned in Known Pitfalls but no feedback loop or validation pattern is provided. Per rubric rules, missing validation for destructive operations caps this at 3.

3 / 5

Progressive Disclosure

All content is inlined in a single monolithic file with no references to supporting files. The ~200 lines of workflow details, pitfalls, and reference tables could benefit from being split into separate files (e.g., a quick reference card, detailed pitfalls doc). There are no bundle files and no references to external documentation, making this a wall of repetitive content.

2 / 5

Total

10

/

20

Passed

Description

70%Scale 1-5

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 does a good job specifying concrete CRM actions and naming the specific platform (Close CRM via Rube MCP/Composio), making it distinctive. However, it lacks an explicit 'Use when...' clause, which weakens its completeness for skill selection purposes. Adding trigger guidance and a few more natural user terms would strengthen it.

Suggestions

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

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

DimensionReasoningScore

Specificity

Lists several specific actions: create leads, manage calls/SMS, handle tasks, track notes. These are concrete CRM operations, though 'manage' and 'handle' are slightly generic. Also includes the operational guidance to search tools first for current schemas.

4 / 5

Completeness

The 'what' is clearly stated (automate Close CRM tasks with specific actions listed), but there is no explicit 'when' clause. The description lacks a 'Use when...' trigger phrase, which caps this dimension at 3 per the rubric guidelines.

3 / 5

Trigger Term Quality

Includes good natural keywords like 'Close CRM', 'leads', 'calls', 'SMS', 'tasks', 'notes', and 'Composio'. However, it could include more synonyms or variations users might say, such as 'contacts', 'pipeline', 'deals', or 'follow-up'.

4 / 5

Distinctiveness Conflict Risk

Highly distinctive due to the specific platform references: 'Close CRM', 'Rube MCP', and 'Composio'. These are niche enough that this skill is unlikely to conflict with other CRM or general automation skills.

5 / 5

Total

16

/

20

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
administrakt0r/AI-Agents-Safe-Coding-Skills
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.