Meta-skill for designing orchestrator+phases structured workflow skills. Creates SKILL.md coordinator with progressive phase loading, TodoWrite patterns, and data flow. Triggers on "design workflow skill", "create workflow skill", "workflow skill designer".
78
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/workflow-skill-designer/SKILL.mdQuality
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 description that clearly communicates a specific, niche capability — designing structured workflow skills with orchestrator and phase patterns. It provides explicit trigger terms and covers both what the skill does and when to use it. The technical terminology is appropriate for the target audience and helps distinguish it from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'designing orchestrator+phases structured workflow skills', 'Creates SKILL.md coordinator with progressive phase loading, TodoWrite patterns, and data flow'. These are concrete, specific capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (meta-skill for designing orchestrator+phases structured workflow skills, creates SKILL.md coordinator with progressive phase loading, TodoWrite patterns, and data flow) and 'when' (explicit triggers: 'design workflow skill', 'create workflow skill', 'workflow skill designer'). | 3 / 3 |
Trigger Term Quality | Includes explicit trigger phrases that users would naturally say: 'design workflow skill', 'create workflow skill', 'workflow skill designer'. Also includes domain-specific terms like 'orchestrator', 'phases', 'TodoWrite patterns' that help with matching. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — a meta-skill specifically for designing workflow skills with orchestrator+phases patterns. The combination of 'workflow skill designer', 'orchestrator+phases', 'TodoWrite patterns', and 'SKILL.md' makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive meta-skill for designing workflow skills, with excellent workflow clarity and a well-thought-out phase structure. However, it suffers significantly from verbosity — the inline content is far too long, with patterns like Compact Recovery explained in exhaustive detail with bilingual annotations, multiple representation formats, and concepts Claude would already understand. The actionability is moderate: templates and patterns are provided but rely on pseudocode and invented APIs rather than fully executable examples.
Suggestions
Reduce content by 50-60%: move Pattern 9 (Compact Recovery) details, the full SKILL.md template, and the Phase File template into separate referenced files (e.g., templates/orchestrator-template.md, patterns/compact-recovery.md), keeping only 2-3 line summaries inline.
Remove bilingual Chinese/English explanations — pick one language. The mixed annotations (e.g., '双重保险', '预防', '恢复') add redundancy without clarity for a skill document.
Add one complete, concrete worked example showing a simple 3-phase workflow skill being generated from a text description input, with actual file contents rather than placeholder templates.
Replace pseudocode JavaScript (AskUserQuestion, Read(), Skill()) with either real executable code or explicit notes that these are Claude tool invocations with links to their specifications.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Extensive explanations of patterns Claude already understands (TodoWrite lifecycle, compact behavior, data flow concepts). The bilingual Chinese/English mix adds redundancy. Many patterns are over-explained with multiple representations (text + table + code + diagram) of the same concept. The compact recovery section alone is massively over-detailed for what could be a 5-line pattern description. | 1 / 3 |
Actionability | Provides concrete templates (SKILL.md template, Phase File template) and specific patterns with code examples, but much of the code is pseudocode/illustrative rather than truly executable. The JavaScript examples use invented APIs (AskUserQuestion, Skill(), Read()) without clear specification. The templates have placeholder syntax ({skill-name}, {tools}) but lack a complete worked example showing a real skill being generated end-to-end. | 2 / 3 |
Workflow Clarity | The 4-phase execution flow is clearly sequenced with explicit Ref: markers, a Phase Reference Documents table, and well-defined inputs/outputs for each phase. Validation is explicitly Phase 4. The Design Decision Framework provides a clear checklist. The TodoWrite attachment/collapse pattern provides explicit state management checkpoints. | 3 / 3 |
Progressive Disclosure | References 4 phase files (phases/01-04) appropriately for on-demand loading, which is good structure. However, the SKILL.md itself is monolithic — Pattern 9 (Compact Recovery) alone spans ~100 lines that could be in a separate reference doc. The core design patterns section contains enormous detail that should be split into referenced files rather than inlined. No bundle files are provided to verify the referenced phase docs exist. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
227244f
Table of Contents
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.