autom-automation

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

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

68%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 a well-structured, mostly lean overview with concrete tool-call skeletons and a clear discover-connect-execute sequence. Its main weakness is workflow_clarity: batch/bulk execution lacks validation or error-recovery checkpoints, which caps that dimension at 3.

Suggestions

Add an explicit validation/verification checkpoint before RUBE_MULTI_EXECUTE_TOOL for batch or destructive operations (e.g. dry-run, confirm argument schema, check row counts) plus an error-recovery loop on failure.

Remove the duplicated RUBE_SEARCH_TOOLS example by merging the standalone Tool Discovery section into Step 1 to tighten conciseness.

Provide at least one fully-populated executable example (with a realistic tool_slug and arguments) so the actionability reaches copy-paste-ready.

Dimension	Reasoning	Score
Conciseness	The body is largely lean, assumes Claude knows MCP/Composio concepts, and uses a compact Quick Reference table; only minor trimming is needed (the Tool Discovery block duplicates Step 1's RUBE_SEARCH_TOOLS, and a few explanatory lines like 'This returns available tool slugs...' could go). Not a 5 because of that duplicated search example and small padded sentences.	4 / 5
Actionability	Concrete code blocks name the exact tools and argument shapes for a discover->connect->execute flow. Placeholders like 'TOOL_SLUG_FROM_SEARCH' and 'your_session_id' are explicitly justified by the dynamic-schema design ('Always search tools first'), so this is mostly executable guidance with minor gaps rather than pseudocode. Not a 5 because no block is copy-paste runnable end-to-end with real values.	4 / 5
Workflow Clarity	A clear Step 1/2/3 sequence exists with an ACTIVE-connection checkpoint, but the skill drives batch/bulk execution (RUBE_MULTI_EXECUTE_TOOL, RUBE_REMOTE_WORKBENCH 'Bulk ops') with no pre-execution validation, dry-run, or error-recovery feedback loop. Per the batch/destructive cap this cannot exceed 3; not a 2 because the sequence and one checkpoint are genuinely present.	3 / 5
Progressive Disclosure	Single-file skill (no references/scripts/assets bundle) with well-organized sections (Prerequisites, Setup, Tool Discovery, Core Workflow, Pitfalls, Quick Reference) and no nested references. Good structure with minor gaps (the Tool Discovery / Step 1 redundancy); not a 5 because at ~85 lines with that redundancy it is not maximally tight, and no external reference split is signaled.	4 / 5
	Total	15 / 20 Passed

Description

48%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 names a specific product and infrastructure clearly but is thin on concrete capabilities and omits any explicit 'Use when...' trigger. It is distinctive enough to avoid most conflicts yet too generic in action language.

Suggestions

Add 2-3 concrete Autom actions (e.g. 'create and update Autom workflows, trigger runs, fetch execution status') to lift specificity above generic 'automate tasks'.

Append a 'Use when...' clause stating when Claude should invoke this skill (e.g. 'Use when the user wants to run or manage Autom operations via Composio').

Include a natural synonym or phrasing variation alongside 'Autom' to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	"Automate Autom tasks" names the domain but the action is generic ("automate... tasks") with no concrete enumerated capabilities; the second sentence is a process instruction, not a capability. Not a 3 because there are no specific concrete actions listed (e.g. create, update, fetch), only the minimal/generic 'Automate Autom tasks'.	2 / 5
Completeness	Has a clear 'what' ("Automate Autom tasks via Rube MCP (Composio)") but no 'when'/'Use when...' trigger clause; the "Always search tools first" sentence is procedural, not a usage trigger. Capped at 3 per the missing-trigger guidance; not a 4 because there is no explicit when at all.	3 / 5
Trigger Term Quality	"Autom" is the natural product-name keyword a user would say, but there are no synonyms, variations, or file extensions. Not a 4 because coverage is limited to the single product name plus MCP/Composio infrastructure jargon rather than natural user phrases.	3 / 5
Distinctiveness Conflict Risk	Naming the specific product "Autom" plus the Rube/Composio MCP gives a clear niche with low conflict risk. Not a 5 because there are no explicit distinct trigger phrases (no 'Use when...'), so overlap with other Composio/Rube automation skills is possible.	4 / 5
	Total	12 / 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/autom-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.