Name: wrangler
Rating: 86.6 (1 reviews)
Author: cloudflare

wrangler

Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

1.34x

Quality

—

Does it follow best practices?

Impact

93%

1.34x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, copy-paste-ready Wrangler reference, but it is a long monolithic document with command repetition and no progressive disclosure via separate files. Destructive/remote batch operations also lack validation feedback loops.

Suggestions

Add explicit validation/confirmation checkpoints before destructive and remote batch operations (e.g. list-then-confirm before `wrangler delete`, `r2 bucket delete`, `d1 execute --remote --file`), with a fix-and-retry loop.

Split the per-product reference sections (KV, R2, D1, Vectorize, Hyperdrive, etc.) into separate files under references/ and keep SKILL.md as a concise overview with one-level-deep links.

De-duplicate repeated commands (`wrangler check startup`, `wrangler types`, `wrangler dev --test-scheduled`) and trim the full-config example to only the bindings not already shown, to tighten the token budget.

Dimension	Reasoning	Score
Conciseness	The body is dense, mostly executable commands and config rather than concept explanation, but it runs ~900 lines with repeated commands (e.g. `wrangler check startup`, `wrangler types`, `wrangler dev --test-scheduled` appear multiple times) and an oversized full-config example that could be trimmed.	2 / 3
Actionability	Provides extensive copy-paste-ready bash commands and complete jsonc config blocks for every product area, fully executable with specific flags and examples.	3 / 3
Workflow Clarity	Sequences and a dry-run validation step exist ('wrangler deploy --dry-run') plus a troubleshooting table, but destructive and remote batch operations (delete worker/bucket/namespace/database, `d1 execute --remote`) lack explicit validate/confirm feedback loops, capping this dimension at 2.	2 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the skill is a single monolithic ~900-line file with no bundle files (references/, scripts/, assets/ absent) and no one-level-deep references, so per-product reference content that should be split out lives inline.	2 / 3
	Total	9 / 12 Passed

Description

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.

A strong, third-person description that is specific, well-triggered, and clearly scoped to Wrangler/Cloudflare Workers. It answers both what the skill does and when to load it without fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('deploying, developing, and managing') alongside a long enumerated set of specific Cloudflare products (Workers, KV, R2, D1, Vectorize, etc.), matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	States what it does (CLI for deploying/developing/managing the listed products) and gives explicit trigger guidance ('Load before running wrangler commands'), satisfying both the what and the when.	3 / 3
Trigger Term Quality	Uses natural terms a user would actually say — 'Cloudflare Workers CLI', 'wrangler commands', and the common product names (KV, R2, D1) — giving good coverage of likely trigger phrasing.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear, narrow niche — the Wrangler CLI for Cloudflare Workers and its bindings — with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (923 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: cloudflare/skills
Commit: 27ce0c0

Reviewed: 9 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.