team-brainstorm
Unified team skill for brainstorming team. Uses team-worker agent architecture with role directories for domain logic. Coordinator orchestrates pipeline, workers are team-worker agents. Triggers on "team brainstorm".
57
48%
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-brainstorm/SKILL.mdQuality
Discovery
25%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 almost entirely on internal implementation details (agent architecture, role directories, coordinator/worker patterns) rather than describing what the skill does for the user. It lacks concrete actions, natural trigger terms, and a clear explanation of when Claude should select it. The description reads more like a developer's architecture note than a skill selection guide.
Suggestions
Replace implementation details with concrete user-facing actions (e.g., 'Generates creative ideas, explores multiple perspectives, and produces structured brainstorm outputs for a given topic or problem').
Expand trigger terms to include natural user phrases like 'brainstorm ideas', 'generate ideas', 'ideation session', 'creative thinking', 'explore options', 'think of solutions'.
Add a proper 'Use when...' clause with diverse trigger scenarios, e.g., 'Use when the user wants to brainstorm ideas, explore multiple angles on a problem, or generate creative solutions collaboratively.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, architectural language ('team-worker agent architecture', 'role directories for domain logic', 'Coordinator orchestrates pipeline') without describing any concrete user-facing actions. It never explains what the skill actually does for the user beyond 'brainstorming'. | 1 / 3 |
Completeness | It partially addresses 'what' (brainstorming with a team architecture) and has a minimal 'when' clause ('Triggers on team brainstorm'), but the 'what' is described in implementation terms rather than user-facing capabilities, and the 'when' is extremely narrow. The presence of an explicit trigger clause prevents a score of 1. | 2 / 3 |
Trigger Term Quality | The only trigger term is 'team brainstorm', which is narrow and unnatural. Users are unlikely to say 'team brainstorm' verbatim. Terms like 'team-worker agent architecture', 'role directories', and 'pipeline' are internal jargon, not natural user language. | 1 / 3 |
Distinctiveness Conflict Risk | The mention of 'team brainstorm' and the specific architecture gives it some distinctiveness, but 'brainstorming' is a broad activity that could overlap with other ideation or creative skills. The description doesn't clearly carve out a unique niche in terms of user-facing functionality. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
72%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 with strong actionability through concrete spawn templates, clear delegation rules, and good progressive disclosure via role directories. Its main weaknesses are some redundancy in spawn templates and timeout instructions, and the lack of a single cohesive end-to-end numbered workflow with explicit validation checkpoints between pipeline phases (e.g., verifying ideator outputs before spawning challenger).
Suggestions
Add a single numbered end-to-end workflow showing the complete pipeline sequence (analyze -> spawn ideators -> validate outputs -> spawn challenger -> ... -> final evaluation) with explicit validation checkpoints between each phase.
Consolidate the duplicated worker spawn template and timeout cascade into a single canonical template, with a brief note about the parallel ideator variation (just the differences like task_name and agent_name).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly dense with useful information, but includes some redundancy (the worker spawn template is shown twice with minor variations for parallel ideators, and the timeout cascade instructions are duplicated verbatim). The JavaScript-style pseudocode in the v4 Agent Coordination section partially repeats the spawn template. Some tables could be tighter. | 2 / 3 |
Actionability | Provides concrete spawn_agent templates with exact parameter names, a clear delegation lock table with allowed/blocked verdicts, specific timeout values, exact file paths, and executable patterns for agent coordination. The worker spawn template is copy-paste ready with clear placeholder variables. | 3 / 3 |
Workflow Clarity | The architecture diagram and role registry clearly show the pipeline flow, and the timeout cascade (STATUS_CHECK -> FINALIZE -> close) is explicit. However, the overall multi-step orchestration sequence (analyze -> dispatch -> spawn -> wait -> collect -> next phase) lacks a single numbered end-to-end workflow with validation checkpoints between pipeline phases. The error handling table is present but doesn't integrate into the workflow as explicit checkpoints. | 2 / 3 |
Progressive Disclosure | Excellent structure: SKILL.md serves as a router/overview, with clear one-level-deep references to role files (roles/coordinator/role.md, roles/ideator/role.md, etc.) and specs (specs/pipelines.md). The role registry table provides a clean navigation index. Content is appropriately split between the coordinator overview here and domain logic in role directories. | 3 / 3 |
Total | 10 / 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.