CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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).

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 highly actionable and workflow clarity is excellent, with explicit validation loops and prerequisite ordering. The main weaknesses are notable redundancy (the Git-remote requirement and method-selection logic each restated several times) and a broken assets/ reference that the body and reference files both point to.

Suggestions

Consolidate the Git-remote requirement and the 'MCP cannot create image-backed services' note into the single 'Prerequisites Check' section, and state them once; remove the repetitions in 'Choose Your Source Path', Method 1 Step 4, and the Direct Creation prerequisites.

Merge the three method-selection discussions ('Choose Your Deployment Method', 'Method Selection Heuristic', 'When to Use Direct Creation') into one decision section to cut duplicated guidance and tokens.

Fix the broken 'assets/' references: either include the assets directory with the template YAML files that references/service-types.md and blueprint-spec.md link to, or remove the 'Template examples: [assets/](assets/)' line from the body.

DimensionReasoningScore

Conciseness

The body is command-dense with no concept tutorials, but repeats key guidance many times: the Git-remote requirement appears at the intro, 'Choose Your Source Path', Prerequisite 1, Method 1 Step 4, and Direct Creation prerequisites; 'MCP cannot create image-backed services' appears three times; and the Blueprint-vs-Direct selection logic is given in three separate sections. This is more than the 'minor instances that could be trimmed' of the 4 anchor, fitting 'could be tightened'.

3 / 5

Actionability

Fully executable throughout: 'git remote -v', 'render whoami -o json', 'render blueprints validate', 'claude mcp add --transport http render ...', a complete render.yaml example, a concrete SSH-to-HTTPS conversion table with the general pattern ('Replace git@<host>: with https://<host>/ and remove .git suffix'), and the formatted deeplink 'https://dashboard.render.com/blueprint/new?repo=<REPOSITORY_URL>'.

5 / 5

Workflow Clarity

Both methods are explicitly sequenced with validation checkpoints and feedback loops: an ordered 6-step prerequisite check, 'Fix any validation errors before proceeding', 'Verify the file is in your remote repository before proceeding', and a post-deploy checklist ('If any check fails, fix it before redeploying') with a triage escalation path.

5 / 5

Progressive Disclosure

Good structure with clearly signaled one-level-deep references (e.g. 'Complete specification: references/blueprint-spec.md', 'Use the detailed checklists in references/codebase-analysis.md'), and inline content like service types is appropriately summarized with a pointer to the full reference. Not 5 because the body advertises 'Template examples: [assets/](assets/)' and reference files link '../assets/*.yaml', but the assets directory does not exist in the bundle — a broken navigation path.

4 / 5

Total

17

/

20

Passed

Description

87%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.

A strong description: it names concrete capabilities, provides an explicit 'Use when...' trigger clause with natural user phrasing, and actively disambiguates against competing deployment platforms. The only gaps are unmentioned capabilities (Direct Creation via MCP, database/cron provisioning) and a few missing natural trigger synonyms.

DimensionReasoningScore

Specificity

Quotes: 'analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks' — four concrete, specific actions. Falls short of the 5 anchor because the Direct Creation (MCP) method and database/cron resource creation covered in the body are absent, leaving minor gaps in coverage.

4 / 5

Completeness

Clearly answers 'what' ('Deploy applications to Render by analyzing codebases, generating render.yaml Blueprints, and providing Dashboard deeplinks') and 'when' with the explicit trigger clause 'Use when the user wants to deploy, host, publish, or set up their application on Render's cloud platform', matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Quotes: 'deploy, host, publish, or set up their application on Render's cloud platform' plus 'render.yaml' and negative triggers 'Vercel, Netlify, or Cloudflare'. Good natural-verb and synonym coverage, but a few natural phrases users might say ('launch', 'Render.com', 'go live') are missing, so it does not fully match the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

Clear Render niche with explicit negative triggers ('Do NOT use for deploying to Vercel, Netlify, or Cloudflare') that redirect competing platforms to their own skills, giving minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (531 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 1 missing

Warning

Total

14

/

16

Passed

Repository

tech-leads-club/agent-skills

Path

packages/skills-catalog/skills/(cloud)/render-deploy/SKILL.md

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.