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.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

65%Weight 40%Scale 1-3

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

Highly actionable and well-organized CLI reference, but it is a large monolithic body that duplicates config shapes and lacks validation checkpoints for destructive/batch operations. Splitting per-product detail into reference files and adding explicit pre-flight checks would lift the weaker dimensions.

Suggestions

Move per-product command/config detail into separate reference files under references/ (e.g. references/kv.md, references/d1.md) and keep SKILL.md as an overview with one-level-deep links, improving progressive_disclosure and conciseness.

Add explicit validation checkpoints before destructive or batch remote operations — e.g. run `wrangler deploy --dry-run` or `wrangler check` before `migrations apply --remote` and `delete` commands — to raise workflow_clarity.

De-duplicate the config examples: show each binding shape once in a consolidated reference rather than repeating it in both the full-config block and every per-product "Config Binding" section.

Dimension	Reasoning	Score
Conciseness	The body is largely lean, command-focused reference material with little conceptual padding, but at ~900 lines it is large and somewhat redundant — the full-config block and per-product "Config Binding" snippets repeat the same shapes. Not level 3 because it could be tightened/split; not level 1 because it avoids explaining concepts Claude already knows.	2 / 3
Actionability	It provides extensive copy-paste-ready commands and complete JSON config examples for every product (e.g. `wrangler d1 migrations apply my-database --remote`, full `wrangler.jsonc` bindings). Not level 2 because the guidance is fully executable, not pseudocode.	3 / 3
Workflow Clarity	A sequence is implied (install → configure → `wrangler dev` → `wrangler check` → `wrangler deploy`) with some `--dry-run` validation, but destructive and batch remote operations (delete, `migrations apply --remote`, `secret bulk`) lack explicit validate-before-execute checkpoints. Per the rubric, missing validation in destructive/batch workflows caps this at 2.	2 / 3
Progressive Disclosure	Headers and sections are well organized, but the skill is monolithic — no references/ or scripts/ bundle files exist, and per-product reference content that should live in separate files is inline in SKILL.md. Not level 3 because it is not under 50 lines and content is not split; not level 1 because it is not a disorganized wall of text.	2 / 3
	Total	9 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 names a clear niche, concrete actions, a comprehensive product list, and an explicit load trigger. It answers both what and when without verbosity.

Dimension	Reasoning	Score
Specificity	The description lists concrete actions ("deploying, developing, and managing") applied across a comprehensive, named product set ("Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store"), matching the multiple-specific-actions anchor. It is not level 2 because the coverage is broad and explicit rather than partial.	3 / 3
Completeness	It states what it does (CLI for deploying/developing/managing the listed products) and gives explicit when-trigger guidance ("Load before running wrangler commands to ensure correct syntax and best practices"). The presence of an explicit trigger means it is not capped at level 2.	3 / 3
Trigger Term Quality	It includes natural terms users say ("Cloudflare Workers CLI", "wrangler commands") plus every product name a user would mention, giving good coverage. Not level 2 because it spans the common variations rather than just a single keyword.	3 / 3
Distinctiveness Conflict Risk	"Cloudflare Workers CLI" / wrangler is a clear, narrow niche with distinct triggers, unlikely to fire for unrelated skills. Not level 2 because the domain and tool are unambiguous.	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 (898 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/cloudflare/skills/wrangler/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.