wrangler

Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Use when editing wrangler.jsonc, running wrangler commands, bumping compatibility dates, or maintaining a Cloudflare Workers deployment. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Quality

86%

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

Quality

Content

72%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 a model of progressive disclosure and conciseness — a lean index pointing to 22 real, one-level-deep reference files. Its weakness is that the body itself carries no executable guidance or explicit workflow/validation steps, delegating all actionability and sequencing into the reference files.

Suggestions

Add a brief 'Quick start' block in the body with one or two copy-paste commands (e.g., `npx wrangler init` and `npx wrangler deploy`) so the skill is actionable without first opening a reference file.

Include a short explicit workflow in the body (e.g., 1) check wrangler is installed, 2) retrieve latest flags/config from docs, 3) edit wrangler.jsonc, 4) validate locally, 5) deploy) with a validation checkpoint before deploy, lifting workflow_clarity above 3.

Surface the 'retrieve latest before writing/reviewing' feedback loop directly in the body rather than only in references/retrieval-sources.md, so the validation habit is visible at the top level.

Dimension	Reasoning	Score
Conciseness	The body is extremely lean: one retrieval-bias directive plus a flat reference index, with no padding or explanation of concepts Claude already knows; every token earns its place. Not 4 because there are no noticeable instances of over-explanation to trim.	5 / 5
Actionability	The body itself gives no executable code or commands; its only directive is 'Prefer retrieval over pre-training' plus descriptive reference titles that point to where actions live. Not 2 because the reference titles (Quick Start, Core Commands, Deployment) are concrete pointers to actionable content, but not 4 because the body lacks copy-paste-ready guidance of its own.	3 / 5
Workflow Clarity	No explicit multi-step sequence or validation checkpoints appear in the body; sequencing is only implicit via reference ordering and the 'FIRST: Check if Wrangler is installed' title. Not 2 because a rough ordering is signaled through reference titles, but not 4 because no explicit validation checkpoints are present in the body for deployment operations.	3 / 5
Progressive Disclosure	Clear overview with well-signaled one-level-deep references; all 22 referenced files exist and none nest further references, content is appropriately split, and navigation is easy. Not 4 because the structure cleanly matches the one-level-deep reference anchor with no organization gaps.	5 / 5
	Total	16 / 20 Passed

Description

100%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 exemplary: third-person voice, concrete product-level capabilities, an explicit 'Use when...' trigger clause with natural terms and a file extension, and a clear niche. It also adds a useful retrieval-bias directive without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('deploying, developing, and managing') across a comprehensive enumeration of specific Cloudflare products (Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, Secrets Store), matching the comprehensive-coverage anchor. Not 4 because coverage is broad and product-specific rather than having only minor gaps.	5 / 5
Completeness	Explicitly answers both 'what' (CLI for deploying/developing/managing the listed products) and 'when' ('Use when editing wrangler.jsonc, running wrangler commands, bumping compatibility dates, or maintaining a Cloudflare Workers deployment') with concrete trigger phrases. Not 4 because the 'when' clause is explicit and specific, not merely present.	5 / 5
Trigger Term Quality	Includes natural user phrases and the file extension ('editing wrangler.jsonc', 'running wrangler commands', 'bumping compatibility dates', 'Cloudflare Workers deployment'), covering synonyms and the .jsonc extension as the anchor-5 example does. Not 4 because keyword coverage is comprehensive rather than missing a few natural terms.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (the Wrangler CLI) with distinct triggers (wrangler.jsonc, wrangler commands, compatibility dates) and minimal conflict risk against non-Cloudflare skills. Not 4 because the niche is distinct and triggers are specific rather than having notable overlap with closely related skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: joe-bell/cva
Path: .agents/skills/wrangler/SKILL.md
Commit: b06a7c8

Reviewed: 7 days 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.