create-workflow-command
Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts
47
36%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/customaize-agent/skills/create-workflow-command/SKILL.mdQuality
Discovery
17%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 is overly abstract and jargon-heavy, making it difficult for Claude to determine when to select this skill. It lacks a 'Use when...' clause and natural trigger terms that users would employ. While it hints at a specific orchestration pattern, the language is too technical and vague to be effective for skill selection.
Suggestions
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user wants to break a complex task into multiple steps, run parallel sub-tasks, or orchestrate a multi-step workflow.'
Replace jargon like 'sub-agents' and 'file-based task prompts' with more natural language, and include common user phrases like 'run steps in sequence', 'automate multi-step process', 'parallel tasks'.
List specific concrete actions the skill performs, such as 'generates task prompt files, spawns sub-agent processes, collects and merges results, handles step dependencies'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names a domain (workflow orchestration) and describes some actions ('create a workflow command', 'orchestrates multi-step execution'), but the language is fairly abstract and doesn't list multiple concrete actions like creating task files, spawning sub-agents, or collecting results. | 2 / 3 |
Completeness | The description addresses 'what' at a high level but completely lacks any 'when' clause or explicit trigger guidance. There is no 'Use when...' or equivalent, which per the rubric caps completeness at 2, and the 'what' is also weak enough to warrant a 1. | 1 / 3 |
Trigger Term Quality | The description uses technical jargon like 'orchestrates multi-step execution', 'sub-agents', and 'file-based task prompts' which are not natural terms a user would say. Users would more likely say 'run multiple steps', 'automate tasks', or 'workflow'. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'sub-agents' and 'file-based task prompts' provides some specificity, but 'workflow command' and 'multi-step execution' are broad enough to overlap with general automation, scripting, or task-running skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with excellent concrete templates and a clear multi-step workflow with validation, but it suffers severely from verbosity and poor progressive disclosure. At 300+ lines with everything inlined, it consumes excessive context window space. The content would benefit enormously from splitting the execution patterns, full example, and reference tables into separate files while keeping the main skill as a lean overview.
Suggestions
Cut the skill body to ~100 lines by moving execution patterns (A/B/C), the full feature-impl example, capability tables, and known limitations into separate referenced files (e.g., PATTERNS.md, EXAMPLE.md, REFERENCE.md).
Remove explanatory content Claude already knows: the 'Context Isolation' rationale section, the sub-agent capabilities table, and the model selection guidance are all unnecessary padding.
Trim the task file template to just the structure headings without the verbose explanations of each section—Claude can infer what 'Goal', 'Instructions', and 'Constraints' mean.
Add a concise quick-start section at the top showing the minimal 3-file creation (one orchestrator + one task file + directory) before diving into the full architecture.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines. It over-explains concepts Claude already understands (sub-agent capabilities, context isolation rationale, what sequential vs parallel execution means). The architecture overview table, capability matrix, and extensive known limitations section add significant token cost with marginal instructional value. Much of this could be cut by 60%+ while preserving all actionable content. | 1 / 3 |
Actionability | The skill provides fully concrete, copy-paste-ready templates for orchestrator commands, task files, directory structures, and frontmatter configuration. The feature implementation example is a complete, executable workflow with specific file paths, naming conventions, and structured output formats. | 3 / 3 |
Workflow Clarity | The implementation process is clearly sequenced (gather requirements → create directories → create task files → create orchestrator command) with a comprehensive validation checklist at the end. The step-by-step process includes explicit checkpoints and the checklist covers error handling, portability, and self-containment of task files. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no bundle files to reference. The architecture overview, three execution patterns, a full worked example with task file content, capability tables, and known limitations are all inlined. Much of this content (execution patterns, the full feature-impl example, known limitations) should be in separate referenced files to keep the main skill lean. | 1 / 3 |
Total | 8 / 12 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.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- NeoLabHQ/context-engineering-kit
- Commit
dedca19
- 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.