cloudflare-deploy
Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare. Do NOT use for deploying to Vercel, Netlify, or Render (use their respective skills).
83
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Failed to scan
The risk profile of this skill
Optimize this skill with Tessl
npx tessl skill review --optimize ./packages/skills-catalog/skills/(cloud)/cloudflare-deploy/SKILL.mdQuality
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 clearly defines its scope, includes natural trigger terms, explicitly states when to use it, and proactively disambiguates from competing deployment skills. The 'Do NOT use' clause is a particularly strong addition that minimizes conflict risk in a multi-skill environment.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions ('deploy applications and infrastructure') and names specific Cloudflare services ('Workers, Pages, and related platform services'), giving a clear picture of what the skill does. | 3 / 3 |
Completeness | Clearly answers both 'what' (deploy applications and infrastructure to Cloudflare using Workers, Pages, etc.) and 'when' (explicit 'Use when' clause with trigger actions, plus a 'Do NOT use' clause for disambiguation). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'deploy', 'host', 'publish', 'set up', 'Cloudflare', 'Workers', 'Pages'. These cover common variations of how users would phrase deployment requests. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit negative boundaries ('Do NOT use for deploying to Vercel, Netlify, or Render') that directly prevent conflicts with similar deployment skills. The Cloudflare-specific services further narrow the niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels as a navigation hub with well-structured decision trees and comprehensive product indexing that enables quick routing to the right Cloudflare product. However, it lacks concrete deployment workflows with validation steps—the actual 'how to deploy' is entirely deferred to reference files. The product index tables, while comprehensive, add significant token cost and largely duplicate the decision tree information.
Suggestions
Add a minimal end-to-end deployment example for the most common case (e.g., Workers deploy) with validation steps like checking deployment status after `wrangler deploy`.
Consider removing or significantly condensing the product index tables since the decision trees already route users to the correct references—this would save ~80 lines of tokens.
Add a post-deploy verification step (e.g., `curl <deployed-url>` or checking wrangler output) to create a proper feedback loop for deployment operations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The decision trees and product index tables are useful but the product index is extremely long and largely duplicates information already in the decision trees. The troubleshooting section repeats the sandbox_permissions guidance from prerequisites. Some trimming would improve token efficiency. | 2 / 3 |
Actionability | The authentication section provides a concrete command (`npx wrangler whoami`) and clear next steps, but the skill mostly serves as a routing/navigation document pointing to reference files rather than providing executable deployment steps itself. The actual deploy commands and configurations are deferred to references. | 2 / 3 |
Workflow Clarity | There's a clear first step (authenticate), then use decision trees to find the right product, then load references. However, there's no explicit end-to-end deployment workflow with validation checkpoints—no 'verify deployment succeeded' step, no error recovery loop for failed deploys, and the actual deployment sequence is entirely deferred to reference files. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure: a concise overview with decision trees for quick navigation, followed by well-organized product index tables with clear one-level-deep references to detailed documentation. The references are clearly signaled and consistently formatted. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- tech-leads-club/agent-skills
- Commit
906a57d
- 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.