CtrlK
BlogDocsLog inGet started
Tessl Logo

workflows

Framework for building durable workflows with orchestrated activities, used for background jobs, multi-step pipelines, scheduled tasks, LLM agents, or any process requiring fault tolerance, retries, and long-running execution. This skill provides comprehensive documentation and guidance for working with the Mistral Workflows framework.

48

2.94x
Quality

33%

Does it follow best practices?

Impact

100%

2.94x

Average score across 2 eval scenarios

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./template/.agents/skills/workflows/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%

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

This skill reads more like a README or documentation index than an actionable skill file. It spends significant tokens on describing what the framework is and listing features rather than teaching Claude how to use it effectively. The strongest parts are the SDK import conventions and testing guidance, but the core workflow development process lacks concrete, executable examples and clear step-by-step workflows.

Suggestions

Replace the 'About Workflows', 'When to Use This Skill', and 'Key Features' sections with a single concise quick-start example showing a complete workflow with an activity definition, execution, and error handling — Claude doesn't need marketing copy about the framework.

Add a concrete step-by-step workflow for the most common use case (e.g., 'Creating a workflow with activities') including validation steps like running the test script and checking for determinism violations.

Prioritize the reference links by adding a 'Start here' section with the 3-4 most important references, rather than listing 25+ files with equal weight.

Remove redundant descriptions — e.g., 'durable, fault-tolerant' is stated in the description, the About section, the When to Use section, and the Key Features section.

DimensionReasoningScore

Conciseness

The content is highly verbose with extensive explanations of what the framework is, lists of features Claude already understands conceptually, and repeated descriptions (e.g., 'durable, fault-tolerant' appears multiple times). The 'When to Use This Skill' and 'Key Features' sections largely restate information already covered. The 'About Workflows' section explains basic concepts Claude doesn't need.

1 / 3

Actionability

The SDK import example and test script command are concrete and executable, and the timeout table provides specific values. However, most of the content is a directory listing of reference files rather than actionable guidance. There's no complete workflow example showing a real activity definition, execution, or error handling pattern.

2 / 3

Workflow Clarity

The testing section has a clear sequence with timeout recommendations, and the import conventions are well-specified. However, there's no step-by-step workflow for the primary use case (building a workflow with activities), no validation checkpoints for workflow development, and no error recovery feedback loops for the core development process.

2 / 3

Progressive Disclosure

The documentation structure section provides well-organized references to external files with brief descriptions, which is good. However, no bundle files were provided to verify these references exist, the SKILL.md itself is a monolithic listing that mixes overview content with detailed tables and feature lists that could be separated, and the sheer number of references (25+) without clear prioritization makes navigation harder.

2 / 3

Total

7

/

12

Passed

Description

32%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description provides a reasonable high-level overview of the domain but suffers from lack of concrete actions and a missing 'Use when...' clause. The second sentence ('provides comprehensive documentation and guidance') is filler that adds no discriminative value. The description would benefit from listing specific actions and adding explicit trigger conditions.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Mistral Workflows, durable execution, orchestrating activities, or building fault-tolerant background jobs.'

Replace the vague second sentence with concrete actions like 'Define workflow functions, configure activity retries, set up scheduled triggers, and manage long-running executions.'

Include additional natural trigger terms users might say, such as 'task queue', 'job orchestration', 'durable execution', or the specific package/import name for Mistral Workflows.

DimensionReasoningScore

Specificity

Names the domain (durable workflows) and lists several use cases (background jobs, multi-step pipelines, scheduled tasks, LLM agents), but doesn't describe concrete actions the skill enables (e.g., 'create workflows', 'configure retries', 'define activities'). The second sentence is vague fluff about 'comprehensive documentation and guidance.'

2 / 3

Completeness

Describes 'what' at a high level (framework for building durable workflows) but completely lacks an explicit 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'when' is not even implied clearly enough to warrant a 2.

1 / 3

Trigger Term Quality

Includes some relevant keywords like 'workflows', 'background jobs', 'pipelines', 'scheduled tasks', 'retries', 'fault tolerance', and 'Mistral Workflows'. However, it misses common user phrasings like 'cron jobs', 'task queue', 'job scheduling', 'workflow orchestration', or file extensions/package names users might reference.

2 / 3

Distinctiveness Conflict Risk

The mention of 'Mistral Workflows' framework provides some distinctiveness, but terms like 'workflows', 'pipelines', 'background jobs', and 'scheduled tasks' are broad enough to overlap with other workflow/orchestration skills (e.g., Temporal, Celery, Airflow-related skills).

2 / 3

Total

7

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
mistralai/workflows-starter-app
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.