brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Install with Tessl CLI
npx tessl i github:projectbluefin/dakota --skill brainstorming74
Quality
58%
Does it follow best practices?
Impact
75%
1.44xAverage score across 10 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.opencode/skills/brainstorming/SKILL.mdDiscovery
32%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 suffers from being overly broad and vague. While it attempts to establish when to use the skill, the triggers are so generic ('any creative work', 'creating features') that it would conflict with most development-related skills. The actual capabilities ('explores user intent, requirements and design') are abstract and don't convey concrete actions.
Suggestions
Replace vague capability statement with specific actions (e.g., 'Conducts requirements gathering sessions, creates user stories, drafts technical specifications, identifies edge cases')
Narrow the trigger scope to specific scenarios rather than 'any creative work' (e.g., 'Use when starting a new feature, when requirements are unclear, or when the user asks for help planning implementation')
Add distinctive terminology that separates this from general coding skills (e.g., 'requirements analysis', 'design exploration', 'specification drafting')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Uses vague, abstract language like 'creative work', 'features', 'components', 'functionality' without describing concrete actions. 'Explores user intent, requirements and design' is generic and doesn't specify what the skill actually does. | 1 / 3 |
Completeness | Has a 'when' clause ('before any creative work - creating features, building components...') but the 'what' is weak ('Explores user intent, requirements and design'). The when clause is overly broad rather than providing explicit, useful triggers. | 2 / 3 |
Trigger Term Quality | Contains some relevant terms like 'features', 'building components', 'adding functionality', 'modifying behavior' that users might say, but these are very broad and could apply to almost any development task. Missing specific natural language triggers. | 2 / 3 |
Distinctiveness Conflict Risk | Extremely generic scope - 'creative work', 'features', 'components', 'functionality', 'modifying behavior' would conflict with virtually any development or coding skill. No clear niche or distinct triggers. | 1 / 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 skill with excellent workflow clarity and appropriate progressive disclosure. The content is concise and respects Claude's intelligence. The main weakness is the lack of concrete examples - showing a sample question sequence or a design section template would make the guidance more immediately actionable.
Suggestions
Add 2-3 example questions (both multiple choice and open-ended) to illustrate the questioning style
Include a brief example of what a 200-300 word design section looks like in practice
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, with no unnecessary explanations of concepts Claude already knows. Every section serves a clear purpose and the bullet points are tight and actionable. | 3 / 3 |
Actionability | Provides clear process guidance and principles, but lacks concrete examples of questions to ask, sample design section outputs, or specific file path patterns. The guidance is instructional rather than executable. | 2 / 3 |
Workflow Clarity | Clear multi-step workflow with explicit phases (understanding → exploring → presenting → documentation → implementation). Includes validation checkpoints ('ask after each section whether it looks right') and feedback loops ('go back and clarify'). | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections and appropriate references to other skills (elements-of-style, superpowers:using-git-worktrees, superpowers:writing-plans). Content is appropriately scoped for a SKILL.md overview. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- 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.