team-designer
Meta-skill for generating team skills following the v4 architecture pattern. Produces complete skill packages with SKILL.md router, coordinator, worker roles, specs, and templates. Triggers on "team-designer", "design team".
73
67%
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 ./.claude/skills/team-designer/SKILL.mdQuality
Discovery
85%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 solid description that clearly communicates what the skill produces (complete skill packages with specific components) and when to use it (explicit trigger terms). Its main weakness is the limited set of trigger terms, which are somewhat technical and may not cover all natural ways a user might request this functionality.
Suggestions
Expand trigger terms to include natural variations like 'create a team skill', 'multi-agent skill', 'skill architecture', 'generate skill package', or 'build a skill team'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'generating team skills', 'following the v4 architecture pattern', 'produces complete skill packages with SKILL.md router, coordinator, worker roles, specs, and templates'. These are detailed and concrete outputs. | 3 / 3 |
Completeness | Clearly answers both 'what' (generates team skills with SKILL.md router, coordinator, worker roles, specs, and templates following v4 architecture) and 'when' (explicit triggers: 'team-designer', 'design team'). | 3 / 3 |
Trigger Term Quality | Includes some trigger terms ('team-designer', 'design team') but these are narrow and somewhat technical. Missing natural variations a user might say like 'create a team skill', 'multi-agent skill', 'skill architecture', or 'generate skill package'. | 2 / 3 |
Distinctiveness Conflict Risk | Very clear niche — meta-skill for generating team skills with a specific architecture pattern (v4). The combination of 'team-designer', 'v4 architecture', and the specific deliverables (router, coordinator, worker roles) makes it highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 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 demonstrates solid architectural thinking with a clear 4-phase workflow and good use of progressive disclosure via phase reference documents. However, it suffers from significant redundancy (the same pipeline described three different ways), lacks concrete executable examples of generated output, and has weak validation/error recovery guidance. The skill tells Claude *about* the process more than it *instructs* Claude how to execute it.
Suggestions
Consolidate the Architecture Overview, Execution Flow, and Data Flow sections into a single representation — all three describe the same 4-phase pipeline redundantly.
Add a concrete example of generated output for at least one file type (e.g., a sample SKILL.md router or role.md with correct YAML frontmatter) to make the skill actionable rather than descriptive.
Expand the Validation phase and Error Handling sections with explicit feedback loops: what specific checks are performed, what triggers REVIEW vs FAIL, and what corrective actions to take before re-validating.
Clarify the golden sample reference path — '~ or <project>/.claude/skills/team-lifecycle-v4/' is ambiguous; specify a resolution order or detection logic.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content has significant redundancy — the execution flow, data flow, and architecture overview all describe essentially the same 4-phase pipeline three times in slightly different formats. The ASCII diagrams add visual weight but repeat information. However, it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides structural guidance (directory layouts, naming conventions, phase references) but lacks executable code or concrete file content examples. The golden sample shows directory structure but never shows actual generated SKILL.md content, role.md YAML frontmatter, or template content. Input processing shows a format but no parsing logic. | 2 / 3 |
Workflow Clarity | The 4-phase sequence is clearly defined with phase references and auto-continue rules. However, Phase 4 (Validation) mentions PASS/REVIEW/FAIL outcomes but provides no validation criteria, error recovery steps, or feedback loops for what to do when validation fails. The 'Core Rules' section adds useful constraints but the error handling section is superficial. | 2 / 3 |
Progressive Disclosure | The skill correctly references 4 phase documents for on-demand loading, which is good progressive disclosure design. However, no bundle files were provided, so the referenced phase documents (phases/01-04) don't actually exist in the evaluation context. The SKILL.md itself contains redundant representations of the same flow that could be consolidated, and the golden sample reference path uses an ambiguous '~ or <project>' pattern. | 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 | |
- Repository
- catlog22/Claude-Code-Workflow
- Commit
227244f
- 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.