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".
45
47%
Does it follow best practices?
Impact
—
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
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 almost entirely on internal implementation architecture (agent patterns, role directories, coordinators, workers) rather than describing what the skill does for the user. It lacks concrete actions, meaningful trigger terms, and clear guidance on when to use it. A user or Claude reading this would struggle to understand what outcomes this skill produces.
Suggestions
Replace architectural details with concrete actions the skill performs, e.g., 'Generates creative ideas, evaluates feasibility, and organizes brainstorming outputs into structured plans.'
Add a clear 'Use when...' clause with natural trigger terms like 'brainstorm ideas', 'ideation session', 'generate concepts', 'creative thinking', 'idea generation'.
Specify the domain or type of brainstorming (e.g., product features, marketing campaigns, problem-solving) to improve distinctiveness and help Claude select it appropriately.
| 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 actions the skill performs. There are no specific capabilities listed—only internal implementation details. | 1 / 3 |
Completeness | The 'what' is extremely weak—it says it's for 'brainstorming' but doesn't explain what kind of brainstorming or what outputs it produces. The 'when' is limited to 'Triggers on team brainstorm' which is minimal and not framed as explicit guidance. Most of the description is about internal architecture rather than purpose or usage. | 1 / 3 |
Trigger Term Quality | It includes 'team brainstorm' as a trigger term, which is somewhat relevant, but misses natural variations users might say like 'brainstorm ideas', 'ideation', 'generate ideas', 'brainstorming session', etc. The term 'brainstorming team' is also present but ambiguous. | 2 / 3 |
Distinctiveness Conflict Risk | The 'team brainstorm' trigger is somewhat distinctive, but the description is so vague about what it actually does that it could overlap with any brainstorming, ideation, or team collaboration skill. The architectural details don't help distinguish its functional niche. | 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 that provides concrete, actionable templates for multi-agent brainstorming coordination. Its main strengths are the clear delegation lock, spawn templates, and progressive disclosure to role files. Its weaknesses are some redundancy in spawn/timeout instructions and the lack of a single cohesive end-to-end workflow sequence with explicit validation checkpoints between pipeline phases.
Suggestions
Add a single numbered end-to-end workflow showing the coordinator's full sequence from topic analysis through final evaluation, with explicit validation checkpoints between each pipeline phase (e.g., 'Verify ideator outputs exist before spawning challenger').
Deduplicate the timeout cascade instructions — define it once as a named procedure and reference it from both the regular and parallel spawn sections.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly detailed and well-structured, but includes some redundancy (e.g., the timeout cascade instructions are repeated verbatim for both regular and parallel ideator spawns, and the JavaScript-style pseudocode examples appear in multiple forms). Some sections like Model Selection Guide and Message Semantics could be tightened. | 2 / 3 |
Actionability | The skill provides concrete spawn_agent templates with exact parameter names, a clear delegation lock table with allowed/blocked tool calls, specific session directory structures, timeout cascade procedures, and named agent targeting examples. The guidance is specific and directly executable. | 3 / 3 |
Workflow Clarity | The architecture diagram and role registry clearly show the pipeline flow (generate -> challenge -> synthesize -> evaluate), and the timeout cascade has explicit steps. However, the overall orchestration workflow lacks a single clear numbered sequence showing the full end-to-end coordinator flow with validation checkpoints between phases. The error handling table helps but doesn't integrate into a cohesive workflow with feedback loops. | 2 / 3 |
Progressive Disclosure | The SKILL.md serves as a clear router/overview, with role-specific logic delegated to individual role.md files under roles/, pipeline definitions referenced in specs/pipelines.md, and the content is well-organized with tables and sections. References are one level deep and clearly signaled with relative paths. | 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
5ff5e86
- 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.