agent-workflow
Agent skill for workflow - invoke with $agent-workflow
51
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 95%
↑ 2.43xAgent success when using this skill
Validation for skill structure
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically deficient across all dimensions. It provides no information about what the skill does, when to use it, or what distinguishes it from other skills. The description reads more like a label than a functional description that would help Claude select the appropriate skill.
Suggestions
Add specific concrete actions describing what this workflow skill does (e.g., 'Orchestrates multi-step tasks, manages sequential operations, coordinates between tools').
Include a 'Use when...' clause with explicit trigger conditions (e.g., 'Use when the user needs to automate a sequence of steps, manage complex multi-stage processes, or coordinate multiple actions').
Add natural keywords users would actually say when needing this skill (e.g., 'automation', 'multi-step process', 'task sequence', 'pipeline').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for workflow' is completely abstract with no indication of what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no 'Use when...' clause and no explanation of capabilities. | 1 / 3 |
Trigger Term Quality | The only potential trigger term is 'workflow' which is extremely generic. '$agent-workflow' is a command syntax, not a natural keyword users would say when needing this skill. | 1 / 3 |
Distinctiveness Conflict Risk | 'Workflow' is extremely generic and could conflict with virtually any task-oriented skill. There are no distinct triggers to differentiate this from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable overview of workflow automation capabilities with useful MCP tool examples, but suffers from being more descriptive than instructive. It lists capabilities and patterns without providing concrete, executable guidance for implementing them. The workflow design approach lacks validation checkpoints critical for complex automation tasks.
Suggestions
Replace descriptive lists (core responsibilities, quality standards) with concrete examples showing input -> workflow definition -> expected output for each workflow pattern
Add explicit validation steps to the workflow design approach, e.g., 'After step creation, validate with workflow_status to confirm step registration before proceeding'
Provide a complete, copy-paste ready example of creating and executing a simple workflow end-to-end with error handling
Move detailed workflow patterns and advanced features to a separate reference file, keeping SKILL.md focused on quick-start guidance
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Contains some unnecessary verbosity like listing 'Your core responsibilities' and 'Quality standards' that Claude already understands. The workflow patterns section is descriptive rather than instructive, but the code examples are reasonably efficient. | 2 / 3 |
Actionability | Provides concrete JavaScript code examples for the MCP tools which is good, but the examples are illustrative rather than fully executable in context. Missing actual input/output examples and the workflow patterns section describes rather than instructs. | 2 / 3 |
Workflow Clarity | Lists a 6-step 'workflow design approach' but lacks explicit validation checkpoints or error recovery feedback loops. The steps are high-level descriptions rather than actionable sequences with verification points. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but everything is inline in one file. For a skill of this complexity with multiple workflow patterns and advanced features, some content could be split into reference files. | 2 / 3 |
Total | 8 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.