render-deploy
Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks. Use when the user wants to deploy, host, publish, or set up their application on Render's cloud platform. Do NOT use for deploying to Vercel, Netlify, or Cloudflare (use their respective skills).
87
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It provides specific concrete actions, includes natural trigger terms users would say, explicitly addresses both what and when, and proactively reduces conflict risk by naming competing skills to avoid. The negative trigger guidance is a particularly strong differentiator.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'analyzing codebases', 'generating render.yaml Blueprints', and 'providing Dashboard deeplinks'. These are precise, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (analyzing codebases, generating render.yaml Blueprints, providing Dashboard deeplinks) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios). Also includes explicit negative triggers ('Do NOT use for...') which further clarifies scope. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'deploy', 'host', 'publish', 'set up', 'Render', 'cloud platform'. These are terms users would naturally use when wanting to deploy to Render. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (Render-specific deployment) and explicitly differentiates itself from competing skills (Vercel, Netlify, Cloudflare) with a 'Do NOT use' clause, minimizing conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability, workflow clarity, and progressive disclosure—it provides executable commands, well-sequenced steps with validation checkpoints, and appropriate delegation to reference files. However, it is significantly too verbose: security requirements, MCP setup instructions for multiple tools, repeated guidance about Git remotes, and explanatory text that Claude doesn't need inflate the token cost substantially. The content could likely be cut by 40-50% without losing any actionable information.
Suggestions
Drastically condense the 'Security Requirements for API Keys and Secrets' section to 3-4 bullet points—Claude already understands credential hygiene and doesn't need 6 numbered sub-sections with examples.
Move MCP setup instructions (Cursor, Claude Code, Other Tools) to a reference file like references/mcp-setup.md and link to it, since these are one-time setup steps that bloat the main skill.
Eliminate repeated instructions that appear multiple times (e.g., 'stop and ask the user to create/push a remote' appears at least 3 times; 'MCP does not support image-backed services' appears twice).
Remove explanatory text Claude already knows, such as what service types mean ('HTTP services, APIs, web applications (publicly accessible)') and the SSH-to-HTTPS conversion pattern explanation—a simple table suffices.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~350+ lines. It over-explains concepts Claude already knows (what Git remotes are, what service types mean), repeats instructions across sections (e.g., 'stop and ask the user to create/push a remote' appears 3+ times), includes lengthy MCP setup instructions for multiple tools, and has extensive security guidance that could be condensed significantly. The prerequisite checks alone span dozens of lines with redundant verification steps. | 1 / 3 |
Actionability | The skill provides concrete, executable commands throughout—bash commands for CLI operations, specific MCP function calls, complete YAML examples for render.yaml, exact deeplink URL formats with conversion tables, and JSON configuration blocks for MCP setup. Nearly everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | Both deployment methods have clearly numbered, sequenced steps with explicit validation checkpoints (Step 2.5 immediate checklist, Step 3 validate configuration, Step 7 verify deployment). The post-deploy triage section includes a feedback loop for fixing and redeploying. Decision heuristics for method selection are clearly structured with conditions. | 3 / 3 |
Progressive Disclosure | The skill effectively delegates detailed content to reference files (references/codebase-analysis.md, references/blueprint-spec.md, references/direct-creation.md, references/troubleshooting-basics.md, etc.) while keeping the main file as an orchestration overview. References are one level deep and clearly signaled with descriptive labels. | 3 / 3 |
Total | 10 / 12 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (531 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- tech-leads-club/agent-skills
- Commit
81e7e0d
- 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.