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.
65
54%
Does it follow best practices?
Impact
74%
1.17xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/brainstorming/SKILL.mdQuality
Discovery
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 extreme breadth and vagueness. It attempts to position itself as a mandatory pre-implementation planning/discovery skill but fails to describe concrete actions it performs and uses triggers so broad they would conflict with nearly every development-related skill. The imperative 'You MUST use this' tone is also unusual and doesn't help with skill selection clarity.
Suggestions
Narrow the scope by listing specific concrete actions the skill performs, e.g., 'Generates requirements documents, creates design specifications, produces architecture diagrams, and writes user stories before implementation begins.'
Replace the overly broad trigger clause with specific, distinguishable triggers, e.g., 'Use when the user asks to plan a feature, write a spec, gather requirements, create a design document, or discuss architecture before coding.'
Reduce conflict risk by clearly defining the skill's niche — is it for requirements gathering, design exploration, or project planning? Pick a focused domain rather than claiming all pre-implementation work.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language like 'creative work', 'creating features', 'building components', 'adding functionality', and 'modifying behavior' without listing concrete actions the skill performs. 'Explores user intent, requirements and design' is similarly abstract. | 1 / 3 |
Completeness | The 'when' is addressed ('before any creative work - creating features, building components, adding functionality, or modifying behavior'), and the 'what' is weakly stated ('Explores user intent, requirements and design before implementation'). However, the 'what' is too vague to be truly complete, and the 'when' clause is overly broad rather than providing explicit, useful triggers. | 2 / 3 |
Trigger Term Quality | It includes some relevant terms like 'features', 'components', 'functionality', 'requirements', and 'design' that users might mention, but these are extremely broad and not distinctive trigger terms. Missing natural phrases users would say like 'plan', 'spec', 'requirements gathering', 'design doc', 'architecture'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is extremely broad — 'creating features, building components, adding functionality, or modifying behavior' covers nearly all development tasks. This would conflict with virtually any coding or development skill, making it very difficult to distinguish from other skills. | 1 / 3 |
Total | 6 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong process-oriented skill with excellent workflow clarity, multiple validation gates, and highly actionable guidance. Its main weakness is moderate verbosity — several sections explain design principles and reasoning that Claude already knows (isolation, YAGNI, exploring existing codebases), and the dot graph duplicates the checklist. The hard gate and anti-pattern sections effectively prevent the most common failure mode (skipping design).
Suggestions
Trim the 'Design for isolation and clarity' section significantly — Claude already understands modular design principles. A single sentence like 'Break the system into units with clear purposes and well-defined interfaces' would suffice.
Remove or condense the dot graph since it duplicates the checklist; alternatively, keep only one of the two representations to save tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some verbose sections that could be tightened. The 'Anti-Pattern' section, the detailed explanation of visual companion decision-making, and the 'Design for isolation and clarity' section explain concepts Claude already understands well. The dot graph is a nice touch but duplicates the checklist, adding token cost. | 2 / 3 |
Actionability | The skill provides highly concrete, actionable guidance: a specific checklist with ordered steps, exact file paths for spec output, specific message templates (e.g., the visual companion offer and user review gate), clear decision criteria for when to use browser vs terminal, and explicit self-review steps. The guidance is specific enough to follow without ambiguity. | 3 / 3 |
Workflow Clarity | The workflow is exceptionally clear with explicit sequencing (numbered checklist), multiple validation gates (user approves design, spec self-review, user reviews spec), feedback loops (revise design if not approved, re-run spec review if changes requested), and a hard gate preventing premature implementation. The process flow diagram reinforces the sequence with decision diamonds. | 3 / 3 |
Progressive Disclosure | The skill references one external file (`skills/brainstorming/visual-companion.md`) appropriately, and mentions other skills by name (writing-plans, elements-of-style). However, the main file is quite long (~200 lines of content) and some sections like 'Design for isolation and clarity' and 'Working in existing codebases' could potentially be split out. No bundle files were provided to verify the referenced path exists, but the structure is reasonable for a single-file skill of this complexity. | 2 / 3 |
Total | 10 / 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.
- Repository
- lucianghinda/superpowers-ruby
- Commit
7500b1f
- 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.