brainstorming
This skill should be used before implementing features, building components, or making changes. It guides exploring user intent, approaches, and design decisions before planning. Triggers on "let's brainstorm", "help me think through", "what should we build", "explore approaches", ambiguous feature requests, or when the user's request has multiple valid interpretations that need clarification.
83
79%
Does it follow best practices?
Impact
85%
1.34xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/compound-engineering/skills/brainstorming/SKILL.mdQuality
Discovery
82%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 is a solid description with excellent trigger term coverage and clear completeness in answering both what and when. The main weaknesses are moderate specificity (could list more concrete actions) and some potential overlap with planning or architecture skills. The explicit trigger phrases are a strong point that will help Claude select this skill appropriately.
Suggestions
Add 2-3 more concrete actions to improve specificity, e.g., 'generates design alternatives, surfaces tradeoffs, clarifies requirements'
Strengthen distinctiveness by explicitly contrasting with related skills, e.g., 'Use this BEFORE detailed planning or architecture design'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (pre-implementation exploration) and some actions ('exploring user intent, approaches, and design decisions'), but lacks concrete specific actions like 'generate design alternatives' or 'create decision matrices'. | 2 / 3 |
Completeness | Clearly answers both what ('guides exploring user intent, approaches, and design decisions before planning') and when ('before implementing features', 'Triggers on...' with explicit trigger phrases and conditions). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would actually say: 'let's brainstorm', 'help me think through', 'what should we build', 'explore approaches', plus the conceptual trigger of 'ambiguous feature requests'. | 3 / 3 |
Distinctiveness Conflict Risk | Reasonably specific to pre-implementation brainstorming, but could overlap with planning skills, architecture skills, or general conversation skills. The phrase 'before planning' helps distinguish it but boundaries with planning/design skills remain somewhat fuzzy. | 2 / 3 |
Total | 10 / 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 well-structured brainstorming skill with strong actionability and clear workflow phases. The main weaknesses are verbosity (explaining concepts Claude already knows like YAGNI principles) and keeping all content inline rather than splitting advanced topics into separate files. The concrete templates and anti-pattern tables are particularly effective.
Suggestions
Trim the YAGNI section to 1-2 lines or remove entirely—Claude knows these principles
Condense 'When to Use This Skill' section; the Phase 0 assessment already covers this
Consider moving the detailed 'Key Topics to Explore' table and 'Anti-Patterns' table to a separate reference file
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains useful content but is verbose in places. Tables and structured formats help, but explanations like 'Brainstorming is valuable when' and 'Brainstorming can be skipped when' explain concepts Claude can infer. The YAGNI section restates well-known principles. | 2 / 3 |
Actionability | Provides concrete, actionable guidance throughout: specific question techniques with good/avoid examples, structured templates for approaches and design docs, clear exit conditions, and explicit output location. The markdown templates are copy-paste ready. | 3 / 3 |
Workflow Clarity | Clear four-phase process with explicit sequencing (Phase 0-4). Each phase has defined entry/exit conditions, the incremental validation section provides feedback loops, and the handoff phase offers clear next-step options. Anti-patterns table reinforces correct behavior. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections and tables, but everything is inline in one file. The skill references '/ce:plan' for handoff but doesn't link to external reference materials. For a skill of this length (~180 lines), some content could be split into separate files. | 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
- EveryInc/compound-engineering-plugin
- Commit
269fa55
- 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.