Unified team skill for frontend development. Pure router — all roles read this file. Beat model is coordinator-only in monitor.md. Built-in ui-ux-pro-max design intelligence. Triggers on "team frontend".
36
32%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/team-frontend/SKILL.mdQuality
Discovery
7%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 dominated by internal architectural jargon ('pure router', 'beat model', 'coordinator-only in monitor.md') that describes how the skill is structured rather than what it does for the user. It lacks concrete actions, natural trigger terms, and explicit 'use when' guidance, making it nearly useless for skill selection from a pool of available skills.
Suggestions
Replace internal architecture jargon with concrete actions the skill performs, e.g., 'Builds React components, styles pages with CSS, implements responsive layouts, creates interactive UI elements.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about frontend development, React components, CSS styling, HTML markup, web UI, responsive design, or building web pages.'
Remove implementation details like 'pure router', 'beat model', 'coordinator-only in monitor.md' that describe internal mechanics rather than user-facing capabilities.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, jargon-heavy language like 'pure router', 'beat model', 'built-in ui-ux-pro-max design intelligence' without listing any concrete actions the skill performs. No specific capabilities like 'build components', 'style pages', or 'create layouts' are mentioned. | 1 / 3 |
Completeness | The 'what' is essentially absent — it says it's for 'frontend development' but lists no concrete actions. The 'when' is limited to 'triggers on team frontend' which is a narrow, unnatural trigger phrase rather than explicit guidance on when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | The only trigger term mentioned is 'team frontend', which is not a natural phrase a user would say. Terms like 'pure router', 'beat model', 'coordinator-only', and 'monitor.md' are internal jargon, not user-facing keywords. Missing natural terms like 'React', 'CSS', 'HTML', 'UI', 'component', 'web page', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The phrase 'team frontend' and the internal architecture references (router, monitor.md, coordinator) give it some distinctiveness from generic skills, but 'frontend development' is broad enough to overlap with any web development or UI skill. | 2 / 3 |
Total | 5 / 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 is a well-structured routing/architecture skill that effectively delegates to role-specific files with clear navigation. Its main weakness is that as a router document, it lacks direct actionable guidance and validation checkpoints — the actual executable instructions live in referenced files that aren't provided. The spawn template and error handling table add practical value, but the workflow could benefit from explicit validation steps between phases.
Suggestions
Add explicit validation checkpoints to the workflow — e.g., verify task-analysis.json is valid before dispatching workers, confirm worker spawn success before proceeding.
Consider trimming the session directory tree and spawn template to essential elements, moving full details to a referenced spec file to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably structured and avoids explaining basic concepts, but includes some verbose sections like the full ASCII architecture diagram and the worker spawn template that could be more compact. The session directory tree and multiple tables add bulk but are mostly justified. | 2 / 3 |
Actionability | The role router logic is concrete ('Has --role <name> → Read roles/<name>/role.md'), the spawn template is copy-paste ready, and CLI tools are named. However, the skill is primarily a routing/architecture document — actual executable guidance lives in the referenced role.md files which aren't provided, making this file more descriptive than directly actionable. | 2 / 3 |
Workflow Clarity | The architecture diagram and role registry clearly show the flow from coordinator to workers, and the error handling table covers failure scenarios. However, there are no explicit validation checkpoints in the workflow — e.g., no step to verify worker spawn success, no validation between coordinator analysis and dispatch, and the QA feedback loop is only mentioned as an error case rather than an explicit workflow step. | 2 / 3 |
Progressive Disclosure | The file is a clean router that delegates to role-specific specs via well-signaled one-level-deep references (roles/coordinator/role.md, roles/analyst/role.md, etc.) and links to specs/pipelines.md. The role registry table provides clear navigation to each role's detailed instructions. | 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 | |
5ff5e86
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.