cloudflare

Guide for building applications on Cloudflare's edge platform. Use when implementing serverless functions (Workers), edge databases (D1), storage (R2, KV), real-time apps (Durable Objects), AI features (Workers AI, AI Gateway), static sites (Pages), or any edge computing solutions.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./claude/skills/cloudflare/SKILL.md

Quality

Content

53%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 well-sectioned, but it is a monolithic 1100-line reference with no progressive disclosure to bundle files, notable redundancy, and missing validation checkpoints for destructive/batch operations.

Suggestions

Split per-product detail (setup/usage/key features), framework-specific guides, troubleshooting, and common patterns into separate reference files under references/ and link to them one level deep, keeping SKILL.md as a concise overview with a quick-start and decision matrix.

Add explicit validation/feedback steps to destructive and batch workflows (e.g. after `wrangler d1 execute`, run a read-back query to verify rows; after `wrangler deploy`, verify via `wrangler deployments list` before declaring success).

Dedupe the wrangler command surface — consolidate the repeated install/init/deploy/d1/kv/r2 commands into a single CLI reference section instead of restating them in Getting Started and each product setup.

Dimension	Reasoning	Score
Conciseness	The 1104-line body is mostly dense, high-value reference code rather than concept padding, but it carries real redundancy — wrangler commands recur across 'Getting Started', 'Wrangler CLI Essentials', and per-product setups, the intro restates the description, and overlapping 'Best Practices'/'Common Patterns'/'Framework-Specific Guides'/'Implementation Checklist' sections add length that could be tightened.	3 / 5
Actionability	Core product examples (D1, KV, R2, Durable Objects, Queues, Workers AI) are concrete and copy-paste ready, but the Integration Patterns section relies on undefined helpers (verifyJWT, createJWT, verifyPassword, fetchFromOrigin, processMessage), leaving minor gaps.	4 / 5
Workflow Clarity	Sequencing is present via the implementation checklists and ordered 'Getting Started' commands, but there are no explicit validation/feedback checkpoints, and destructive/batch operations (D1 batch, Queues, DB writes) lack verify-before-proceed loops, which caps workflow clarity at 3.	3 / 5
Progressive Disclosure	The skill is monolithic: no references/, scripts/, or assets/ directories exist and the entire per-product API reference, framework guides, troubleshooting, and patterns are inlined in SKILL.md — content that clearly belongs in separate one-level-deep reference files — with no reference links at all.	2 / 5
	Total	12 / 20 Passed

Description

92%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, specific activation description that pairs natural trigger phrases with Cloudflare product names and explicitly answers both what and when. Minor synonym coverage gaps keep trigger term quality just below the top anchor.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple specific concrete capability areas with named products — 'serverless functions (Workers)', 'edge databases (D1)', 'storage (R2, KV)', 'real-time apps (Durable Objects)', 'AI features (Workers AI, AI Gateway)', 'static sites (Pages)' — giving comprehensive coverage rather than minor gaps.	5 / 5
Completeness	It clearly states what ('Guide for building applications on Cloudflare's edge platform') and explicitly when ('Use when implementing serverless functions (Workers)...') with concrete trigger phrases, matching the anchor that requires both.	5 / 5
Trigger Term Quality	Natural trigger phrases ('serverless functions', 'edge databases', 'real-time apps', 'static sites') are paired with their product names, providing good synonym coverage, but a few natural variations are missing (e.g. Queues/cron jobs, CDN, edge functions) so it stops short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	Cloudflare-specific product names (Workers, D1, R2, KV, Durable Objects, Pages, Workers AI) form a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

Warnings & errors only

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

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1105 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: einverne/dotfiles
Path: claude/skills/cloudflare/SKILL.md
Commit: 651d4ea

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.