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".
76
71%
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 does (generates team 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', 'build skill package', 'v4 skill architecture' to improve discoverability.
Consider rephrasing triggers using a 'Use when...' clause format for consistency, e.g., 'Use when the user asks to design a team skill, create a multi-role skill package, or mentions team-designer.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'generating team skills', 'produces complete skill packages with SKILL.md router, coordinator, worker roles, specs, and templates'. These are concrete deliverables and actions. | 3 / 3 |
Completeness | Clearly answers both what ('generates team skills following v4 architecture pattern, produces complete skill packages with router, coordinator, worker roles, specs, and templates') and when ('Triggers on team-designer, design team'), providing explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes explicit trigger terms 'team-designer' and 'design team', but these are narrow and somewhat technical. Missing natural variations a user might say like 'create a team skill', 'build a multi-agent skill', 'v4 architecture', or 'skill package'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — a meta-skill for generating team skills with v4 architecture pattern is very specific and unlikely to conflict with other skills. The domain of 'team-designer' and multi-role skill package generation is clearly delineated. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%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 well-structured architectural overview with good progressive disclosure to phase-specific documents. Its main weaknesses are redundant representations of the same 4-phase pipeline (architecture diagram, execution flow, and data flow all overlap significantly) and a lack of concrete, executable examples — the actual generation logic lives entirely in referenced phase files. Adding intermediate validation checkpoints and reducing the duplicated flow descriptions would strengthen it.
Suggestions
Consolidate the Architecture Overview, Execution Flow, and Data Flow sections into a single representation — they convey the same information three times, wasting tokens.
Add a concrete, minimal example showing what a generated SKILL.md router file actually looks like (even a 10-line snippet) to make the skill more actionable without requiring phase document reads.
Add intermediate validation checkpoints between phases (e.g., validate teamConfig schema before proceeding to Phase 2) rather than deferring all validation to Phase 4.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content has some redundancy — the execution flow, data flow, and architecture overview all describe essentially the same 4-phase pipeline in slightly different formats. The ASCII diagrams, while visually helpful, repeat information. However, it avoids explaining basic concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides structural guidance (directory layouts, phase references, input format) but lacks executable code or concrete file content examples. The actual generation logic is deferred to phase reference documents, so the SKILL.md itself reads more like an architectural description than copy-paste-ready instructions. The input processing section shows a template but no concrete example with filled values. | 2 / 3 |
Workflow Clarity | The 4-phase workflow is clearly sequenced with auto-continue rules and progressive loading. However, validation is only in Phase 4 at the end — there are no intermediate validation checkpoints between phases (e.g., validating teamConfig before scaffold generation). The error handling section lists error types but doesn't specify recovery loops (detect → fix → retry). | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure: SKILL.md serves as a clear router/overview with well-signaled one-level-deep references to four phase documents. The table linking phases to their reference documents is clean and navigable. Content is appropriately split between the overview and detailed phase files. | 3 / 3 |
Total | 9 / 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
0f8e801
- 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.