adrapid-automation

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

6.46x

Quality

51%

Does it follow best practices?

Impact

97%

6.46x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

61%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 well-structured and actionable with concrete Rube MCP calls and a useful quick-reference table, but it duplicates tool-discovery content and omits an execution-error feedback loop for its batch tool. Tightening the redundancy and adding retry guidance would lift it.

Suggestions

Merge the standalone 'Tool Discovery' section into 'Step 1: Discover Available Tools' to remove the near-duplicate content.

Add an explicit feedback loop after RUBE_MULTI_EXECUTE_TOOL (e.g., 'If a tool returns an error, review the message, adjust arguments per the schema, and re-run').

Collapse or trim the Quick Reference table where it restates steps already covered, keeping it as a true quick-lookup.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the 'Tool Discovery' section and 'Step 1: Discover Available Tools' near-duplicate each other, and the Quick Reference table reiterates earlier content, so it could be tightened.	3 / 5
Actionability	Concrete tool calls (RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS, RUBE_MULTI_EXECUTE_TOOL) are given with parameter structures and a Quick Reference table; only minor gaps remain from inherent placeholders like 'your specific Adrapid task' and 'TOOL_SLUG_FROM_SEARCH'.	4 / 5
Workflow Clarity	The three-step Core Workflow is clearly sequenced with a connection-ACTIVE checkpoint, but the batch RUBE_MULTI_EXECUTE_TOOL step lacks an explicit execute->error->fix->retry feedback loop, which the rubric caps at 3 for batch operations.	3 / 5
Progressive Disclosure	No bundle files exist and content is well-sectioned (Prerequisites, Setup, Tool Discovery, Core Workflow, Known Pitfalls, Quick Reference) with a navigation table; structure is good with only minor organization gaps from the duplicated discovery section.	4 / 5
	Total	14 / 20 Passed

Description

41%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 identifies a clear niche but is thin on concrete capabilities and lacks an explicit use-when trigger clause, capping completeness and trigger quality. It reads more like a setup reminder than a capability statement.

Suggestions

Add a 'Use when...' clause naming concrete Adrapid operations (e.g., 'Use when automating Adrapid ad workflows, campaign operations, or bulk Adrapid tasks').

List 2-3 specific Adrapid actions the skill performs instead of the generic 'Automate Adrapid tasks'.

Include natural user phrasing and synonyms (e.g., 'Adrapid automation', 'Adrapid tasks', 'Composio Adrapid') to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Automate Adrapid tasks via Rube MCP") but lists no concrete Adrapid actions; "Always search tools first" is a behavioral instruction rather than a capability, leaving actions minimal and generic.	2 / 5
Completeness	There is a clear "what" (automate Adrapid tasks via Rube MCP) but no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines.	3 / 5
Trigger Term Quality	"Adrapid" is a relevant keyword, but the rest ("Rube MCP", "Composio", "schemas") is technical jargon, and common natural-phrased variations users might say are absent.	2 / 5
Distinctiveness Conflict Risk	The named Adrapid toolkit via Rube MCP/Composio is a distinct niche with clear triggers; minor overlap risk exists only with sibling Composio/Rube toolkit skills sharing the same pattern.	4 / 5
	Total	11 / 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/adrapid-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.