CtrlK
BlogDocsLog inGet started
Tessl Logo

workflow

Vercel Workflow DevKit (WDK) expert guidance. Use when building durable workflows, long-running tasks, API routes or agents that need pause/resume, retries, step-based execution, or crash-safe orchestration with Vercel Workflow.

61

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/vercel/skills/workflow/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

A thorough, highly actionable reference with excellent executable code covering the Workflow DevKit's main surfaces. Its weaknesses are verbosity in the namespaced-streams section, the absence of explicit validation/feedback loops, and a monolithic structure that fails to route readers to the existing reference file.

Suggestions

Link the existing references/durable-agent-patterns.md from the DurableAgent section (e.g. 'See [durable-agent-patterns.md](references/durable-agent-patterns.md) for fan-out and human-in-the-loop patterns') so the bundle file is discoverable.

Collapse the four near-identical namespaced-stream step functions into one parameterized example plus a short list of namespaces, cutting significant redundant tokens.

Add an explicit validation checkpoint to at least one workflow (e.g. after serialization or before resuming a hook) so multi-step processes show a verify→fix→retry loop.

DimensionReasoningScore

Conciseness

Mostly dense, actionable code with little basic-concept padding, but the namespaced-streams section repeats four near-identical step functions (logDebug, logInfo, emitAgentThought, emitAgentResult) and prose like 'Benefits:'/'Key points:' callouts could be trimmed. Not a 4 because the redundancy is noticeable rather than minor; not a 2 because the bulk earns its place.

3 / 5

Actionability

Fully executable, copy-paste-ready TypeScript across directives, imports, steps, hooks, streaming, error handling, and testing, plus concrete CLI commands ('npx workflow health', 'npx workflow inspect run <run_id>'). Examples cover the common cases end-to-end.

5 / 5

Workflow Clarity

Clear instructional patterns (e.g. 'Put logic in steps, orchestrate in workflow') with concrete gotchas, but the body is reference-oriented with no explicit validation checkpoints or fix→retry feedback loops for risky operations. Not a 4 because no sequence carries an explicit verification step.

3 / 5

Progressive Disclosure

Clear section headers organize the content, but the body is a monolithic ~550-line reference that could be split (serialization, streaming, debugging, testing), and the provided bundle file references/durable-agent-patterns.md is never linked or signaled from the body. Not a 4 because references are not clearly signaled and inline content that should be separate remains.

3 / 5

Total

14

/

20

Passed

Description

83%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.

A strong, well-structured description that pairs a clear capability statement with an explicit 'Use when…' trigger clause enumerating concrete scenarios. It is specific and largely distinct, held back only by a few missing natural synonyms and minor generic-'workflow' overlap risk.

DimensionReasoningScore

Specificity

Lists several concrete capabilities ('durable workflows, long-running tasks, API routes or agents that need pause/resume, retries, step-based execution, or crash-safe orchestration') rather than vague language, with only minor coverage gaps. Not a 5 because 'expert guidance' is abstract and the actions are conditions/capabilities rather than a comprehensive set of distinct concrete operations.

4 / 5

Completeness

Explicitly answers both 'what' ('Vercel Workflow DevKit (WDK) expert guidance') and 'when' ('Use when building durable workflows, long-running tasks, API routes or agents that need pause/resume, retries, step-based execution, or crash-safe orchestration with Vercel Workflow') with concrete trigger phrases. Clearly a 5, not a 4, because the 'when' clause enumerates specific triggering scenarios.

5 / 5

Trigger Term Quality

Good coverage of natural terms users would say ('durable workflows', 'long-running tasks', 'pause/resume', 'retries', 'crash-safe orchestration', 'step-based execution'). Not a 5 because common synonyms and bare phrasings like 'step functions', 'pipelines', or 'human-in-the-loop' are absent from the description itself.

4 / 5

Distinctiveness Conflict Risk

Scoped to 'Vercel Workflow' with durable/step-based triggers, giving it a clear niche. Not a 5 because the generic word 'workflow' carries overlap risk with CI/GitHub-Actions/AWS-Step-Functions skills, which the description text does not disambiguate.

4 / 5

Total

17

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (881 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

13

/

16

Passed

Repository
openai/plugins
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.