cloudflare-workflows
Build durable workflows with Cloudflare Workflows (GA April 2025). Features step.do, step.sleep, waitForEvent, Vitest testing, automatic retries, and state persistence for long-running tasks. Prevents 12 documented errors. Use when: creating workflows, implementing retries, or troubleshooting NonRetryableError, I/O context, serialization errors, waitForEvent timeouts, getPlatformProxy failures.
Install with Tessl CLI
npx tessl i github:jezweb/claude-skills --skill cloudflare-workflowsOverall
score
87%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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 excels across all dimensions. It provides specific technical capabilities, includes an explicit 'Use when:' clause with concrete trigger scenarios, and uses distinctive terminology (Cloudflare-specific methods and error names) that clearly differentiates it from other workflow-related skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and features: 'step.do, step.sleep, waitForEvent, Vitest testing, automatic retries, and state persistence for long-running tasks' along with specific error prevention claims. | 3 / 3 |
Completeness | Clearly answers both what (build durable workflows with specific features) AND when (explicit 'Use when:' clause covering creation, implementation, and troubleshooting scenarios with specific error types). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'workflows', 'retries', 'NonRetryableError', 'I/O context', 'serialization errors', 'waitForEvent timeouts', 'getPlatformProxy failures' - these are specific error names and concepts developers would search for. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with 'Cloudflare Workflows' as a clear niche, specific API methods (step.do, step.sleep, waitForEvent), and named error types that are unique to this platform - unlikely to conflict with generic workflow or retry skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a highly actionable and well-structured skill with excellent executable examples and clear workflow guidance. The 12 documented Known Issues section is particularly valuable for preventing common errors. However, the skill is verbose for its scope - it could benefit from splitting advanced content (testing, known issues) into separate files and tightening some explanatory sections that repeat similar concepts.
Suggestions
Split Known Issues into a separate KNOWN-ISSUES.md file and reference it from the main skill - this alone would reduce the skill by ~40%
Consolidate similar Known Issues (e.g., #6, #8, #9, #10, #11 all relate to 'code outside step.do()' problems) into a single 'Rules of step.do()' section with a summary table
Move the detailed Vitest testing section to a separate TESTING.md file, keeping only a brief example in the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some redundancy (e.g., repeated explanations of serialization rules, multiple similar code examples for the same concept). The 'Known Issues' section is valuable but could be more condensed - some issues share similar root causes that could be grouped. | 2 / 3 |
Actionability | Excellent actionability with fully executable code examples throughout. Quick Start is copy-paste ready, step methods have complete signatures with working examples, error handling patterns are concrete, and testing setup includes real vitest configuration. | 3 / 3 |
Workflow Clarity | Clear multi-step workflows with explicit validation checkpoints. The Quick Start has numbered steps, Known Issues include prevention patterns with before/after examples, and the idempotency section (Issue #12) shows proper validation-before-action patterns for risky operations. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but the skill is monolithic (~700 lines) with all content inline. The 'Related Documentation' section provides external links but no internal file references for advanced topics like testing patterns or error handling that could be split out. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (868 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 12 / 16 Passed | |
- 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.