agenty-automation

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

4.40x

Quality

64%

Does it follow best practices?

Impact

97%

4.40x

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/agenty-automation/SKILL.md

Quality

Content

75%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, concise, and actionable, with real tool-call templates and an explicit connection-validation checkpoint in the core workflow. The main gaps are placeholder-filled examples and implicit rather than explicit error-recovery feedback loops.

Suggestions

Add an explicit error-recovery feedback loop (e.g. if a tool call fails or schema validation errors, re-run RUBE_SEARCH_TOOLS and retry) to lift workflow clarity.

Replace generic placeholders ('your specific Agenty task') with a concrete end-to-end worked example covering one real Agenty operation.

Tighten the minor duplicated lead-ins (e.g. 'Always discover available tools before executing workflows') that restate the section heading.

Dimension	Reasoning	Score
Conciseness	The body is lean, assumes Claude knows what MCP/Composio are, and avoids padding, with only minor instances of over-explanation (e.g. the 'Always discover available tools before executing workflows' lead-in duplicates the section title), placing it at 'efficient; minor instances of over-explanation' rather than the fully lean 5.	4 / 5
Actionability	Concrete code blocks with real tool slugs, parameters, and a Quick Reference table provide mostly executable guidance; minor gaps remain where placeholders like 'your specific Agenty task' and 'TOOL_SLUG_FROM_SEARCH' must be filled in, so it is just below copy-paste-ready.	4 / 5
Workflow Clarity	The Core Workflow Pattern gives a clear 3-step sequence with an explicit connection-validation checkpoint (confirm ACTIVE before executing) and a Known Pitfalls feedback section, but error-recovery feedback loops are implicit rather than spelled out, fitting 'clear sequence with most checkpoints; minor validation gaps' instead of 5.	4 / 5
Progressive Disclosure	The skill is a single self-contained file with well-organized sections and a clear Quick Reference table; with no bundle files present it is appropriately flat, but at ~90 lines and without the simple-skill under-50-line exception it sits at 'good structure' rather than the maximal 5.	4 / 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 clearly identifies the product niche and one key behavioral directive (search tools first), but lacks an explicit 'when to use' trigger clause and leans on technical product names rather than natural user phrasings. It is distinct but not yet comprehensive on trigger terms or actions.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases, e.g. 'Use when the user wants to run Agenty scraping workflows, manage agents, or extract data via Agenty.'

Expand the action list beyond 'Automate Agenty tasks' with concrete operations (e.g. 'create and run scraping agents, manage agent runs, extract scraped data').

Add user-facing synonyms and file/extension terms where relevant so the description triggers on natural phrasings, not just product names.

Dimension	Reasoning	Score
Specificity	Names the domain ('Agenty tasks', 'Rube MCP (Composio)') and one concrete action ('Always search tools first for current schemas'), but the lead action ('Automate Agenty tasks') is generic; not a comprehensive list of specific actions, so it sits at the anchor for 'domain plus 1-2 concrete actions' rather than the level above.	3 / 5
Completeness	The description states a clear 'what' (automate Agenty tasks via Rube MCP) but has no 'Use when...' or equivalent trigger clause, so per the judging guidelines a missing explicit trigger caps completeness at 3 rather than allowing 4.	3 / 5
Trigger Term Quality	Includes product-specific keywords ('Agenty', 'Rube MCP', 'Composio') and 'search tools', but these are technical product names rather than the natural phrases a user would say; common synonyms and user-facing variations are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The 'Agenty' product niche gives it clear, distinct triggers with only minor overlap risk against other Composio/Rube-MCP toolkit skills, fitting the 'mostly distinct; minor overlap risk' anchor better than the fully-conflict-free 5.	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/agenty-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.