CtrlK
BlogDocsLog inGet started
Tessl Logo

apex27-automation

Automate Apex27 tasks via Rube MCP (Composio). Always search tools first for current schemas.

56

Quality

63%

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 ./composio-skills/apex27-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 content is well-structured, lean, and actionable with concrete MCP tool-call templates and a clear discover->connect->execute workflow. Main gaps are repeated 'search first' guidance and the absence of an explicit error-recovery feedback loop around tool execution.

Suggestions

Consolidate the 'always search first' rule into a single stated location instead of repeating it across Prerequisites, Tool Discovery, and Known Pitfalls.

Add an explicit execute-failure feedback loop (e.g., if RUBE_MULTI_EXECUTE_TOOL returns an error, re-run RUBE_SEARCH_TOOLS, fix arguments, and retry).

Drop the 'Powered by Composio' footer line to remove a non-instructional token.

DimensionReasoningScore

Conciseness

The body is efficient with sectioned tool-call templates and minimal concept explanation, but repeats the 'search first' rule across Prerequisites, Tool Discovery, and Known Pitfalls and includes a 'Powered by Composio' footer, fitting 'Efficient; minor instances of over-explanation that could be trimmed'. It is below 5 due to that redundancy and above 3 because padding is limited.

4 / 5

Actionability

Concrete MCP tool-call templates (RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS, RUBE_MULTI_EXECUTE_TOOL) with field structures give mostly executable guidance, though arguments use placeholders like 'TOOL_SLUG_FROM_SEARCH', matching 'Mostly executable guidance; concrete code or commands with minor gaps'. It is above 3 because the templates are concrete, not pseudocode.

4 / 5

Workflow Clarity

The Core Workflow Pattern sequences Discover -> Check Connection (with ACTIVE validation) -> Execute, and Pitfalls act as checkpoints, fitting 'Clear sequence with most checkpoints present; minor validation gaps'. It is below 5 because there is no explicit execute-failure feedback loop (validate -> fix -> retry) and above 3 because connection validation precedes execution.

4 / 5

Progressive Disclosure

No bundle files exist, and the ~50-line body is well-organized into Prerequisites, Setup, Tool Discovery, Core Workflow Pattern, Known Pitfalls, and Quick Reference sections with clear navigation, satisfying the under-50-lines/no-external-references exception for a score of 5.

5 / 5

Total

17

/

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 niche (Apex27) and its automation mechanism but stays generic about actions and omits any 'Use when...' trigger guidance. Adding concrete Apex27 operations and an explicit trigger clause would lift specificity and completeness.

Suggestions

List concrete Apex27 operations (e.g., 'create and update leads, manage stock, generate invoices') instead of the generic 'Automate Apex27 tasks'.

Add a 'Use when...' clause, e.g., 'Use when the user asks to automate or query Apex27 records via Composio/Rube.'

Include natural trigger phrases and synonyms (e.g., 'Apex27 records, Apex27 API, Apex27 CRM') alongside the tool names.

DimensionReasoningScore

Specificity

The phrase 'Automate Apex27 tasks via Rube MCP' names the domain (Apex27) and a mechanism but the action ('Automate tasks') is minimal and generic, matching the anchor 'Names the domain but actions are minimal or generic'. It does not reach 3 because no concrete Apex27 operations (e.g., create/lookup/update records) are enumerated.

2 / 5

Completeness

It gives a clear 'what' ('Automate Apex27 tasks via Rube MCP') but no 'when'/Use-when trigger guidance, so per the rubric cap it cannot exceed 3. It is above 2 because the 'what' is explicit rather than vague.

3 / 5

Trigger Term Quality

'Apex27 tasks' is a relevant keyword a user might say, but 'Rube MCP (Composio)' is tooling jargon and common variations or synonyms are missing, fitting 'Some relevant keywords but missing common variations'. It is above 2 because at least one natural term is present, but below 4 due to thin coverage.

3 / 5

Distinctiveness Conflict Risk

'Apex27' carves a clear niche with distinct triggers, but the shared 'Rube MCP (Composio)' framing creates minor overlap risk with sibling Composio toolkit skills, matching 'Mostly distinct; minor overlap risk'. It is below 5 because of that overlap and below 3 because Apex27 is genuinely specific.

4 / 5

Total

12

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
ComposioHQ/awesome-claude-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.