team-ultra-analyze
Deep collaborative analysis team skill. All roles route via this SKILL.md. Beat model is coordinator-only (monitor.md). Structure is roles/ + specs/. Triggers on "team ultra-analyze", "team analyze".
62
53%
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 ./.codex/skills/team-ultra-analyze/SKILL.mdQuality
Discovery
22%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 focuses heavily on internal implementation details (roles, specs, coordinator patterns) rather than communicating what the skill does for the user or when it should be selected. It lacks concrete actions, natural trigger terms, and explicit use-case guidance, making it very difficult for Claude to appropriately select this skill from a pool of alternatives.
Suggestions
Replace internal architecture details with concrete actions the skill performs (e.g., 'Performs multi-perspective analysis of complex problems by coordinating specialized analytical roles including X, Y, Z').
Add an explicit 'Use when...' clause describing real user scenarios and needs (e.g., 'Use when the user needs in-depth analysis from multiple angles, such as strategic planning, risk assessment, or complex decision-making').
Include natural keywords users would actually say when needing this capability (e.g., 'deep analysis', 'multi-angle review', 'comprehensive evaluation', 'team analysis') rather than relying solely on artificial command triggers.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'deep collaborative analysis' without listing any concrete actions. It describes internal architecture ('roles/ + specs/', 'coordinator-only') rather than what the skill actually does for the user. | 1 / 3 |
Completeness | The 'what' is extremely vague ('deep collaborative analysis') and the 'when' is limited to artificial trigger commands rather than describing real use cases. There is no explicit 'Use when...' clause describing scenarios or user needs. | 1 / 3 |
Trigger Term Quality | It includes explicit trigger phrases ('team ultra-analyze', 'team analyze'), but these are artificial command-style triggers rather than natural keywords a user would organically say. The term 'analyze' is relevant but overly generic without domain context. | 2 / 3 |
Distinctiveness Conflict Risk | The specific trigger phrases 'team ultra-analyze' and 'team analyze' provide some distinctiveness, but the core concept of 'analysis' is extremely broad and could overlap with many other analytical skills. The internal architecture details don't help with disambiguation from a user perspective. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
85%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 orchestration skill that provides highly actionable, concrete guidance for a complex multi-agent analysis pipeline. The progressive disclosure is excellent, with SKILL.md serving as a clear router to role-specific files. The main weakness is moderate verbosity — some sections (agent coordination examples, ASCII diagrams) could be tightened without losing clarity, though the complexity of the multi-agent system partially justifies the length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long and includes some sections that could be tightened (e.g., the architecture ASCII diagram is helpful but verbose, the agent coordination section repeats patterns). However, most content is genuinely instructive for a complex multi-agent orchestration skill, so the verbosity is partially justified by complexity. | 2 / 3 |
Actionability | Provides concrete spawn_agent templates with exact parameter structures, specific tool call allowlists/blocklists, executable coordination patterns with wait_agent/close_agent, session directory layouts, and completion action flows with request_user_input schemas. Highly copy-paste ready. | 3 / 3 |
Workflow Clarity | The pipeline modes (Quick/Standard/Deep) are clearly sequenced with explicit phase ordering. The Delegation Lock table provides a validation checkpoint before every tool call. Agent health checks, error handling with specific resolutions, and the parallel phase coordination pattern with batch spawn + wait provide clear feedback loops. | 3 / 3 |
Progressive Disclosure | SKILL.md acts as a router/overview, with role-specific details properly delegated to roles/<name>/role.md files (one level deep, clearly linked in the Role Registry table). Specs are referenced via a single link. The structure cleanly separates coordination logic (here) from domain instructions (role files). | 3 / 3 |
Total | 11 / 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.