agencyzoom-automation

Automate Agencyzoom tasks via Rube MCP (Composio). Always search tools first for current schemas.

12.50x

Quality

63%

Does it follow best practices?

Impact

100%

12.50x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./composio-skills/agencyzoom-automation/SKILL.md

Quality

Content

72%Weight 40%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 body is lean, well-structured, and gives concrete tool-call templates with a clear discover-check-execute sequence. Its main weakness is the absence of validation/verification checkpoints around the batch RUBE_MULTI_EXECUTE_TOOL call, which caps workflow clarity.

Suggestions

Add an explicit validation checkpoint after RUBE_MULTI_EXECUTE_TOOL (e.g. inspect each result for errors, retry failed tool calls, and confirm ACTIVE connection before re-running) to establish a feedback loop for batch execution.

Replace template placeholders (TOOL_SLUG_FROM_SEARCH, your_session_id) with a worked example using a real discovered slug and a generated session id to move actionability toward copy-paste ready.

Tighten redundancy such as the repeated 'Always discover available tools' preamble and remove the trailing 'Powered by Composio' line to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, with tight sections and no padding about what MCP or Composio are; it is not a 5 only because a few phrases like the repeated 'Always discover available tools' and the closing 'Powered by Composio' line could be trimmed.	4 / 5
Actionability	Concrete code blocks for RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS, and RUBE_MULTI_EXECUTE_TOOL give mostly executable guidance; it stops short of 5 because placeholders like TOOL_SLUG_FROM_SEARCH and your_session_id are template rather than copy-paste-ready, and 'schema-compliant args' is pseudocode-like.	4 / 5
Workflow Clarity	The Core Workflow Pattern sequences discover -> check connection -> execute, but RUBE_MULTI_EXECUTE_TOOL is a batch operation with no validation or verification checkpoint before/after execution; the feedback-loops scoring note caps batch operations without validation at 3.	3 / 5
Progressive Disclosure	As a simple single-purpose skill under 50 lines of substantive content with no bundle files, it is well-organized into clearly signaled sections with only a one-level-deep external toolkit link, satisfying the simple-skill exception for a 5.	5 / 5
	Total	16 / 20 Passed

Description

53%Weight 40%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 is concrete and narrowly scoped to Agencyzoom automation via Rube MCP, but it omits any "Use when..." trigger guidance and offers few natural keyword variations. Adding explicit when-to-use phrasing and synonyms would lift completeness and trigger-term quality.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when automating Agencyzoom workflows, executing Agencyzoom tool calls, or integrating Agencyzoom via Composio/Rube'.

Include natural synonyms a user might say (e.g. 'Agencyzoom workflows', 'Composio Agencyzoom', 'Rube tool calls') to improve trigger-term coverage.

Optionally list 1-2 more concrete actions (e.g. 'run Agencyzoom tool calls, manage connections') to move specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	"Automate Agencyzoom tasks via Rube MCP (Composio)" names the domain and a concrete action (automate tasks) but lists no further specific actions, matching the score-3 anchor of domain plus 1-2 actions without comprehensive coverage.	3 / 5
Completeness	The what is clear (automate Agencyzoom tasks via Rube MCP) but there is no "Use when..." clause or equivalent trigger guidance, which the guidelines explicitly cap at 3; it is not a 2 because the what is concrete rather than vague.	3 / 5
Trigger Term Quality	It surfaces "Agencyzoom tasks" as a relevant keyword but offers no synonyms, related phrasings, or natural variations a user might actually say, landing on the anchor with some relevant keywords but missing common variations.	3 / 5
Distinctiveness Conflict Risk	The pairing of "Agencyzoom" with "Rube MCP (Composio)" carves a clear niche with minimal overlap risk; it is not a 5 because the description lacks explicit trigger phrases that would fully disambiguate it.	4 / 5
	Total	13 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: ComposioHQ/awesome-claude-skills
Path: composio-skills/agencyzoom-automation/SKILL.md
Commit: be2a406

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.