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.
82
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/wrangler/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 a strong skill description that clearly identifies its domain (Cloudflare Workers CLI/wrangler), lists comprehensive specific services it covers, and provides explicit guidance on when to use it. The description is concise yet thorough, with excellent trigger term coverage across all major Cloudflare developer platform services.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete services and actions: 'deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store.' This is highly specific about what the skill covers. | 3 / 3 |
Completeness | Clearly answers both what ('CLI for deploying, developing, and managing Workers and related services') and when ('Load before running wrangler commands to ensure correct syntax and best practices'). The 'when' trigger is explicit and actionable. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Cloudflare Workers', 'wrangler', 'KV', 'R2', 'D1', 'Vectorize', 'Hyperdrive', 'Workers AI', 'Containers', 'Queues', 'Workflows', 'Pipelines', 'Secrets Store'. These are all terms a developer would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around Cloudflare Workers CLI and wrangler commands. The enumeration of specific Cloudflare services (KV, R2, D1, Vectorize, etc.) makes it very unlikely to conflict with other skills. | 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.
The skill excels at actionability with comprehensive, copy-paste ready commands and config examples covering the full Wrangler ecosystem. However, it suffers from being a monolithic reference document (~500 lines) that should be split into a concise overview with links to per-service reference files. Multi-step workflows also lack explicit validation checkpoints and feedback loops.
Suggestions
Split per-service sections (KV, R2, D1, Vectorize, Hyperdrive, Queues, Containers, Workflows, Pipelines, Secrets Store) into separate reference files and link to them from a concise overview in SKILL.md.
Add explicit multi-step workflow sequences with validation checkpoints, e.g., for deployment: 'wrangler types → wrangler types --check → wrangler deploy --dry-run → wrangler deploy → wrangler tail --status error' with a feedback loop on errors.
Add a validation step to the D1 migrations workflow: apply locally first, verify, then apply remotely, with explicit error recovery guidance.
Trim the main SKILL.md to focus on retrieval-first guidance, key guidelines, quick start, and core commands — keeping it under 150 lines with clear pointers to detailed reference files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic concepts, but it's quite long (~500 lines) with extensive command listings that could be split into separate reference files. Some sections (like the full config with bindings) are verbose but arguably necessary as reference material. | 2 / 3 |
Actionability | Excellent actionability throughout — every section provides copy-paste ready commands and complete JSONC config snippets. Commands include specific flags, and config examples show exact binding shapes with placeholder IDs. | 3 / 3 |
Workflow Clarity | Individual commands are clear, but multi-step workflows lack explicit validation checkpoints. For example, the deployment flow doesn't sequence 'types → dry-run → deploy → verify', and D1 migrations don't include a 'validate locally before applying remotely' feedback loop. The Quick Start is just two commands with no verification step. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with no references to separate files. All service-specific details (KV, R2, D1, Vectorize, Hyperdrive, Queues, Containers, Workflows, Pipelines, Secrets Store, Pages) are inline rather than split into dedicated reference files. The skill would benefit enormously from a concise overview linking to per-service docs. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 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 | 10 / 11 Passed | |
- Repository
- cloudflare/skills
- Commit
22a32f5
- 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.