CtrlK
BlogDocsLog inGet started
Tessl Logo

render-automation

Automate Render tasks via Rube MCP (Composio): services, deployments, projects. Always search tools first for current schemas.

44

Quality

46%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/render-automation/SKILL.md

The canonical home for this skill is render-automation in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

48%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 skill provides a reasonably well-structured guide to Render automation via Rube MCP with clear workflow sequences and useful parameter documentation. However, it suffers from significant redundancy—key facts like ID formats and pagination patterns are repeated many times across sections. It lacks executable examples with actual tool call syntax and response parsing, relying instead on pseudocode-style numbered lists.

Suggestions

Eliminate redundancy by consolidating pitfalls into a single section and referencing it from workflows, rather than repeating ID formats, pagination details, and deployment behavior in every section.

Add at least one concrete, copy-paste-ready tool call example showing actual arguments and a sample response structure (e.g., a RUBE_SEARCH_TOOLS call with toolkit='render').

Remove the vacuous 'When to Use' section at the bottom and trim explanations of concepts Claude already knows (e.g., what async means, what ISO 8601 is).

Consider showing a complete end-to-end example for the most common workflow (deploy and monitor) with actual tool invocations and response parsing.

DimensionReasoningScore

Conciseness

Significant verbosity throughout. Many pitfalls are repeated across sections (e.g., service ID format 'srv-xxxxxxxxxxxx' is stated at least 5 times, cursor-based pagination explained 3+ times). The 'Known Pitfalls' section largely duplicates per-workflow pitfalls. The 'When to Use' footer is vacuous. Claude doesn't need explanations like 'Projects group related services together' or 'Deployments are asynchronous'.

2 / 5

Actionability

Tool sequences and parameter names are concrete and useful, but there's no executable code—only pseudocode-style numbered steps. The skill instructs to 'always call RUBE_SEARCH_TOOLS first' but never shows an actual tool call with example arguments or expected response shapes. The deploy-and-monitor pattern is described but not shown with concrete invocations.

3 / 5

Workflow Clarity

Workflows are clearly sequenced with labeled steps (Required/Optional/Prerequisite). The deploy-and-monitor pattern includes a polling loop with terminal state checks. However, there's no explicit error recovery or validation beyond checking deploy status—e.g., no guidance on what to do if LIST_SERVICES returns no match, or how to handle auth failures. The connection setup has a reasonable verification flow.

4 / 5

Progressive Disclosure

Content is structured with headers and a quick reference table, which is good. However, with no bundle files, all content is inlined in a single file that runs quite long (~170 lines). The repeated pitfalls sections and the duplicated information between per-workflow pitfalls and the consolidated 'Known Pitfalls' section suggest content that should be reorganized or deduplicated rather than split into separate files.

3 / 5

Total

12

/

20

Passed

Description

45%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 specific platform (Render) and integration method (Rube MCP/Composio) which helps with distinctiveness, but it lacks concrete action verbs describing what can be done and has no 'Use when...' clause to guide skill selection. The listing of 'services, deployments, projects' as bare nouns without associated actions leaves the capabilities underspecified.

Suggestions

Add a 'Use when...' clause with trigger phrases like 'Use when the user asks to deploy to Render, manage Render services, check deployment status, or create Render projects'.

Replace the vague 'automate tasks' with specific actions such as 'create and manage web services, trigger deployments, list projects, check deployment logs, and configure environment variables on Render'.

Include natural user terms and synonyms like 'deploy', 'hosting', 'web service', 'static site', 'Render dashboard' to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain (Render via Rube MCP/Composio) and lists a few concrete nouns (services, deployments, projects) but doesn't describe specific actions beyond 'automate tasks'. The instruction to 'search tools first' is a procedural note rather than a capability description.

3 / 5

Completeness

Has a partial 'what' (automate Render tasks) but no explicit 'when' clause. The note about searching tools first is operational guidance, not a trigger condition. Missing a 'Use when...' clause caps this at 3, and the weak 'what' brings it to 2.

2 / 5

Trigger Term Quality

Includes relevant keywords like 'Render', 'services', 'deployments', 'projects', 'Composio', and 'Rube MCP', but misses natural user phrases like 'deploy to Render', 'hosting', 'web service', 'static site', or specific Render actions users might request.

3 / 5

Distinctiveness Conflict Risk

The mention of 'Render' as a specific platform and 'Rube MCP (Composio)' as the integration mechanism makes this fairly distinct. Minor overlap risk with general deployment or infrastructure skills, but the specific platform name reduces conflict.

4 / 5

Total

12

/

20

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.