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.

58

Quality

67%

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 ./plugins/all-skills/skills/render-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 highly actionable, with concrete tool sequences, parameters, and formats that cover the common Render workflows, but it loses conciseness to a 'Known Pitfalls' section that largely restates inline per-workflow pitfalls.

Suggestions

Collapse the standalone 'Known Pitfalls' section into the per-workflow 'Pitfalls' blocks (or keep only genuinely cross-cutting items) to remove the repeated srv- prefix, enum, async, and pagination content.

Add a brief failure-recovery loop for deployments (e.g. on 'build_failed': inspect logs, optionally retry with clearCache:true) to complete the feedback loop.

Include one full sample MCP tool call payload (e.g. RENDER_TRIGGER_DEPLOY with serviceId and clearCache) to make the guidance fully copy-paste ready.

DimensionReasoningScore

Conciseness

It largely assumes Claude's intelligence (no preamble on what Render/deployments are), but the 'Known Pitfalls' section substantially duplicates per-workflow pitfalls already stated inline (srv- prefix, service-type enums, async deploy behavior, cursor pagination), adding avoidable tokens.

3 / 5

Actionability

Provides concrete tool slugs, exact parameter names, ID formats ('srv-...', 'dep-...'), enum values, status strings, polling intervals, and numbered tool sequences plus a quick-reference table — highly executable with only the minor gap of no full sample call payload.

4.5 / 5

Workflow Clarity

Workflows are clearly sequenced with 'When to use', 'Tool sequence', and checkpoints (confirm connection ACTIVE before workflows, poll RETRIEVE_DEPLOY until terminal state), but failure-recovery actions for build_failed/update_failed are stated as detection only, not corrective loops.

4 / 5

Progressive Disclosure

Clean single-file structure with well-organized sections (Prerequisites, Setup, Core Workflows, Common Patterns, Known Pitfalls, Quick Reference) and no nested external references; the only external link is the appropriate toolkit docs URL. Minor organization gap from the duplicated pitfalls section.

4.5 / 5

Total

16

/

20

Passed

Description

61%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 is specific and distinctive, carving out a clear Render-via-Composio niche, but it lacks an explicit 'Use when...' trigger clause and leans on a single generic verb with a few missing natural synonyms.

Suggestions

Add an explicit trigger clause, e.g. 'Use when managing Render cloud services, triggering or monitoring deployments, or listing Render projects.'

Surface more natural trigger terms like 'deploy/redeploy to Render', 'cron jobs', and 'static sites' so user phrasings map to this skill.

Replace the single generic verb 'Automate' with a couple of distinct concrete actions (e.g. 'list, deploy, and monitor') to lift specificity.

DimensionReasoningScore

Specificity

Names the domain ('Render tasks via Rube MCP (Composio)') and enumerates three concrete target object types ('services, deployments, projects'), but relies on a single generic verb 'Automate' rather than multiple distinct concrete actions.

3 / 5

Completeness

The 'what' is clear (automate Render services/deployments/projects via Rube MCP), but there is no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Includes natural terms users would say ('Render', 'services', 'deployments', 'projects') but omits common synonyms and variations such as 'deploy'/'redeploy', 'cron job', or 'static site'.

3.5 / 5

Distinctiveness Conflict Risk

Targets a clear niche (the Render cloud platform specifically via Composio's Rube MCP), making it highly distinguishable from other skills with minimal conflict risk.

5 / 5

Total

14.5

/

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
davepoon/buildwithclaude
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.