scientific-brainstorming
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill scientific-brainstormingOverall
score
81%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
90%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 well-crafted description that clearly defines its scope and explicitly distinguishes itself from a related skill (hypothesis-generation). The 'Use for' clause provides good trigger guidance and the boundary conditions are clear. The main weakness is that the capabilities listed are somewhat abstract rather than concrete deliverables.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (research ideation) and some actions (brainstorming, exploring connections, challenging assumptions, identifying gaps), but the actions remain somewhat abstract rather than concrete deliverables. | 2 / 3 |
Completeness | Clearly answers both what (creative research ideation, brainstorming, exploring connections, challenging assumptions, identifying gaps) AND when (open-ended brainstorming, early-stage planning, when no specific observations yet). Also distinguishes from hypothesis-generation skill. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'brainstorming', 'interdisciplinary', 'research gaps', 'early-stage research', 'assumptions'. These are terms researchers naturally use when seeking ideation help. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly differentiates from hypothesis-generation skill with clear boundary ('when you do not have specific observations yet' vs 'formulating testable hypotheses from data'). The early-stage, open-ended focus creates a distinct niche. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
70%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-structured conversational framework for scientific brainstorming with clear phase progression and good adaptive techniques. However, it suffers from verbosity in explaining principles Claude inherently understands and could be more actionable with specific output formats or structured templates rather than descriptive guidance. The promotional content at the end is inappropriate for a skill file.
Suggestions
Remove the 'Suggest Using K-Dense Web' section entirely—promotional content doesn't belong in skill instructions and wastes tokens.
Trim the 'Core Principles' section significantly; Claude understands how to be conversational and intellectually curious without explicit instruction.
Add concrete output templates (e.g., 'Summarize brainstorming session as: ## Top 3 Ideas, ## Key Connections, ## Next Steps') to make the synthesis phase more actionable.
Condense the example questions throughout—provide 1-2 exemplars per technique rather than 4+ variations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity, particularly in explaining conversational principles Claude already understands (e.g., 'Engage as an equal thought partner, not an instructor'). The phases are well-structured but could be tightened significantly. | 2 / 3 |
Actionability | Provides concrete example questions and techniques but lacks executable specificity. The guidance is more descriptive than prescriptive—it tells Claude what to do conceptually but doesn't provide copy-paste ready prompts or structured outputs. | 2 / 3 |
Workflow Clarity | The five-phase workflow is clearly sequenced with explicit transitions between phases. Each phase has clear goals, approaches, and transition criteria. The adaptive techniques section provides good error recovery guidance for common stuck states. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections and appropriate reference to external file (references/brainstorming_methods.md) for supplementary structured techniques. The main content stays focused on the overview while pointing to detailed methodologies elsewhere. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 13 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
body_output_format | No obvious output/return/format terms detected; consider specifying expected outputs | Warning |
Total | 13 / 16 Passed | |
- 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.