scientific-brainstorming · diff
git:20260611.1b8fae3 to v1.1
224 added, 130 removed. Audit A to A.
---
name: scientific-brainstorming
- description: 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.
- license: MIT license
- metadata: {"version": "1.0", "skill-author": "K-Dense Inc."}
+ description: Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial review, and decision logs. Use for early-stage research brainstorming or prioritizing candidate directions; hand off empirical validation, study design, ethics or regulatory review, and clinical questions to appropriate experts or skills.
+ license: MIT
+ compatibility: Core guidance works in any Agent Skills-compatible host. Optional bundled CLIs require Python 3.11+ and use only the standard library; they make no network or LLM calls and require no credentials.
+ metadata:
+ version: "1.1"
+ skill-author: "K-Dense Inc."
---
# Scientific Brainstorming
- ## Overview
+ ## Purpose and boundaries
- Scientific brainstorming is a conversational process for generating novel research ideas. Act as a research ideation partner to generate hypotheses, explore interdisciplinary connections, challenge assumptions, and develop methodologies. Apply this skill for creative scientific problem-solving.
+ Use this skill to create, organize, challenge, and transparently prioritize
+ candidate research directions. Treat every output as a **proposal**, not a
+ finding. Creativity methods can alter participation and idea yield, but no
+ method universally improves originality, usefulness, or scientific validity.
+ The evidence base and its limits are summarized in
+ `references/sources.md`.
- ## When to Use This Skill
+ Keep these activities separate:
- This skill should be used when:
- - Generating novel research ideas or directions
- - Exploring interdisciplinary connections and analogies
- - Challenging assumptions in existing research frameworks
- - Developing new methodological approaches
- - Identifying research gaps or opportunities
- - Overcoming creative blocks in problem-solving
- - Brainstorming experimental designs or study plans
+ - **Ideation** creates questions, mechanisms, alternatives, or study concepts.
+ - **Evidence assessment** checks what reliable literature and data support.
+ - **Hypothesis validation** requires observations, predictions, suitable
+ designs, analyses, and independent scrutiny; brainstorming cannot validate a
+ hypothesis.
+ - **Ethics, biosafety, dual-use, regulatory, and institutional review** require
+ the relevant authorized reviewers. A brainstorm is never approval.
+ - **Clinical advice** requires qualified clinicians and patient-specific
+ context. Do not turn research ideas into diagnosis or treatment guidance.
- ## Core Principles
+ For an observation-led testable hypothesis, hand off to
+ `hypothesis-generation`. For study architecture, use `experimental-design`;
+ for sample size, `statistical-power`; for existing evidence,
+ `literature-review`; and for analysis, `statistical-analysis`.
- When engaging in scientific brainstorming:
+ ## Operating rules
- 1. **Conversational and Collaborative**: Engage as an equal thought partner, not an instructor. Ask questions, build on ideas together, and maintain a natural dialogue.
+ 1. Label claims as **idea**, **assumption**, **prediction**, **located
+ evidence**, or **decision**. Never blur these categories.
+ 2. Generate independently before exposing participants to other people's or
+ AI-generated ideas. Face-to-face turn-taking can block production, and
+ examples can anchor later output.
+ 3. Preserve minority views, negative evidence, uncertainty, and abstentions.
+ Consensus is not truth and vote counts are not effect sizes.
+ 4. Record provenance without exposing confidential, personal, controlled, or
+ unpublished information.
+ 5. Define evaluation criteria and directions before scoring. Keep raw ratings,
+ reasons, ranges, and disagreement visible.
+ 6. Search the literature **after an initial independent round** when practical,
+ then deliberately reopen ideation. This reduces early anchoring without
+ mistaking an incomplete search for a research gap.
+ 7. Do not automatically select a “winner.” Scores are traceable decision aids;
+ qualitative judgment, uncertainty, feasibility, and ethics gates remain
+ controlling.
- 2. **Intellectually Curious**: Show genuine interest in the scientist's work. Ask probing questions that demonstrate deep understanding and help uncover new angles.
+ ## Reproducible workflow
- 3. **Creatively Challenging**: Push beyond obvious ideas. Challenge assumptions respectfully, propose unconventional connections, and encourage exploration of "what if" scenarios.
+ ### 1. Scope the session
- 4. **Domain-Aware**: Demonstrate broad scientific knowledge across disciplines to identify cross-pollination opportunities and relevant analogies from other fields.
+ Write one focal question and record:
- 5. **Structured yet Flexible**: Guide the conversation with purpose, but adapt dynamically based on where the scientist's thinking leads.
+ - purpose, audience, decision owner, and time horizon;
+ - in-scope and out-of-scope topics;
+ - constraints that are real, assumed, negotiable, or unknown;
+ - current knowledge, unresolved observations, and prohibited outputs;
+ - whether human participants, animals, clinical care, sensitive data,
+ pathogens, controlled technologies, or environmental release could be
+ implicated.
- ## Brainstorming Workflow
+ If the request seeks patient-specific care, evasion of oversight, harmful
+ optimization, or operationally enabling dual-use details, stop ideation and
+ route to the appropriate professional or institutional process.
- ### Phase 1: Understanding the Context
+ ### 2. Diversify perspectives deliberately
- Begin by deeply understanding what the scientist is working on. This phase establishes the foundation for productive ideation.
+ Invite relevant methodological, domain, implementation, statistical, safety,
+ ethics, stakeholder, and lived-experience perspectives. Diversity is not a
+ guarantee of creativity: explain whose perspective is represented, missing, or
+ structurally disadvantaged. Use accessible participation modes and
+ pseudonymous participant IDs where appropriate.
- **Approach:**
- - Ask open-ended questions about their current research, interests, or challenge
- - Understand their field, methodology, and constraints
- - Identify what they're trying to achieve and what obstacles they face
- - Listen for implicit assumptions or unexplored angles
+ The facilitator should disclose conflicts, avoid offering a preferred answer
+ first, prevent senior members from dominating, and ask leaders to contribute
+ after the independent round.
- **Example questions:**
- - "What aspect of your research are you most excited about right now?"
- - "What problem keeps you up at night?"
- - "What assumptions are you making that might be worth questioning?"
- - "Are there any unexpected findings that don't fit your current model?"
+ ### 3. Generate independently
- **Transition:** Once the context is clear, acknowledge understanding and suggest moving into active ideation.
+ Give everyone the same neutral prompt, constraints, and fixed time window.
+ Participants write ideas privately and in parallel before discussion. For each
+ idea, capture:
- ### Phase 2: Divergent Exploration
+ - a stable ID and one-sentence statement;
+ - contributor ID(s) and stage (`independent`, `discussion`, or `post-check`);
+ - origin (`human`, `AI-assisted`, `literature-inspired`, `mixed`, or `other`);
+ - assumptions, predicted observations, uncertainties, and possible
+ disconfirming evidence;
+ - source identifiers for literature-inspired ideas and tool/purpose disclosure
+ for AI assistance.
- Help the scientist generate a wide range of ideas without judgment. The goal is quantity and diversity, not immediate feasibility.
+ Do not show example solutions before this round unless examples are necessary;
+ if they are, record them as potential anchors.
- **Techniques to employ:**
+ ### 4. Share without immediate evaluation
- 1. **Cross-Domain Analogies**
- - Draw parallels from other scientific fields
- - "How might concepts from [field X] apply to your problem?"
- - Connect biological systems to social networks, physics to economics, etc.
+ Use round-robin or pooled silent sharing. Clarify wording without advocacy.
+ Permit a private or anonymous channel. Ask each participant what is missing,
+ what contradicts the dominant framing, and which idea became less obvious
+ after hearing the group.
- 2. **Assumption Reversal**
- - Identify core assumptions and flip them
- - "What if the opposite were true?"
- - "What if you had unlimited resources/time/data?"
+ ### 5. Cluster structurally
- 3. **Scale Shifting**
- - Explore the problem at different scales (molecular, cellular, organismal, population, ecosystem)
- - Consider temporal scales (milliseconds to millennia)
+ Group ideas by an explicit relation such as shared outcome, mechanism,
+ population, scale, or method. Keep original IDs and text. Record merges and
+ splits. Similar wording is not proof of semantic equivalence; retain distinct
+ ideas when their assumptions, intervention, population, or predictions differ.
+ See `references/facilitation_workflows.md`.
- 4. **Constraint Removal/Addition**
- - Remove apparent constraints: "What if you could measure anything?"
- - Add new constraints: "What if you had to solve this with 1800s technology?"
+ ### 6. Define transparent criteria
- 5. **Interdisciplinary Fusion**
- - Suggest combining methodologies from different fields
- - Propose collaborations that bridge disciplines
+ Before rating, define each criterion, direction, scale anchors, evidence
+ needed, conflicts, and explicit weights. Common dimensions include:
- 6. **Technology Speculation**
- - Imagine emerging technologies applied to the problem
- - "What becomes possible with CRISPR/AI/quantum computing/etc.?"
+ - potential information gain and discriminating predictions;
+ - relevance to the scoped question;
+ - originality relative to the checked literature, not merely to the room;
+ - feasibility, resources, and reversibility;
+ - methodological rigor and vulnerability to bias;
+ - ethics, safety, equity, dual-use, and regulatory burden;
+ - value if the result is null or contradicts the favored mechanism.
- **Interaction style:**
- - Rapid-fire idea generation with the scientist
- - Build on their suggestions with "Yes, and..."
- - Encourage wild ideas explicitly: "What's the most radical approach imaginable?"
- - Consult references/brainstorming_methods.md for additional structured techniques
+ Use ranges or confidence labels where assessors are uncertain. Do not hide
+ vetoes inside an averaged score. See `references/idea_evaluation.md`.
- ### Phase 3: Connection Making
+ ### 7. Run adversarial review
- Help identify patterns, themes, and unexpected connections among the generated ideas.
+ Assign a reviewer who did not originate each shortlisted idea. Ask:
- **Approach:**
- - Look for common threads across different ideas
- - Identify which ideas complement or enhance each other
- - Find surprising connections between seemingly unrelated concepts
- - Map relationships between ideas visually (if helpful)
+ - What observation would make this idea wrong or uninformative?
+ - Which alternative explanation fits the same predicted result?
+ - What hidden dependency, measurement failure, confounder, or selection effect
+ could dominate?
+ - Are authority, anchoring, group loyalty, publication incentives, or an
+ attractive technology driving preference?
+ - Could this cause harm, worsen inequity, expose sensitive information, or
+ enable misuse?
- **Prompts:**
- - "I notice several ideas involve [theme]—what if we combined them?"
- - "These three approaches share [commonality]—is there something deeper there?"
- - "What's the most unexpected connection you're seeing?"
+ Record the response, mitigation, residual uncertainty, and whether the idea was
+ revised—not just pass/fail.
- ### Phase 4: Critical Evaluation
+ ### 8. Check literature and evidence
- Shift to constructively evaluating the most promising ideas while maintaining creative momentum.
+ Search authoritative databases, primary studies, methods guidance, negative
+ results, and adjacent fields. Verify every citation at its source. For each
+ idea, record query/date, sources screened, evidence for and against, and search
+ limits. Use statuses such as `not-checked`, `search-incomplete`,
+ `support-located`, `challenge-located`, or `mixed`.
- **Balance:**
- - Be critical but not dismissive
- - Identify both strengths and challenges
- - Consider feasibility while preserving innovative elements
- - Suggest modifications to make wild ideas more tractable
+ Absence from a bounded search does not establish novelty, and supportive
+ literature does not validate a new mechanism. Reopen one short independent
+ generation round after the evidence check.
- **Questions to explore:**
- - "What would it take to actually test this?"
- - "What's the first small experiment to run?"
- - "What existing data or tools could be leveraged?"
- - "Who else would need to be involved?"
- - "What's the biggest obstacle, and how might it be overcome?"
+ ### 9. Apply feasibility, rigor, and ethics gates
- ### Phase 5: Synthesis and Next Steps
+ Before advancing an idea, identify the appropriate domain review:
- Help crystallize insights and create concrete paths forward.
+ - For biomedical work, consider rigor of prior research, robust design,
+ relevant biological variables, and resource authentication. When NIH policy
+ applies, sex as a biological variable should be considered from the research
+ question through design, analysis, and reporting; justify a single-sex scope
+ with relevant evidence.
+ - Route human-subjects, animal, biosafety, data-governance, export-control,
+ clinical, environmental, and other regulated work to the relevant office.
+ - Screen life-science and enabling-technology ideas for dual-use or misuse
+ potential early. Current U.S. oversight is evolving; consult the institution
+ and current agency policy rather than relying on a static checklist.
+ - Do not upload sensitive, unpublished, proprietary, controlled, or personal
+ information to an external AI service.
- **Deliverables:**
- - Summarize the most promising directions identified
- - Highlight novel connections or perspectives discovered
- - Suggest immediate next steps (literature search, pilot experiments, collaborations)
- - Capture key questions that emerged for future exploration
- - Identify resources or expertise that would be valuable
+ An ethics or feasibility concern may require redesign, controlled handling, or
+ stopping. A high creativity score never overrides a gate.
- **Close with encouragement:**
- - Acknowledge the creative work done
- - Reinforce the value of the ideas generated
- - Offer to continue the brainstorming in future sessions
+ ### 10. Decide and log
- ## Adaptive Techniques
+ The accountable human decision owner records:
- ### When the Scientist Is Stuck
+ - candidates considered and criteria/weights used;
+ - raw ratings, uncertainty ranges, dissent, abstentions, and sensitivity
+ results;
+ - literature and review dates;
+ - gate outcomes and required approvals;
+ - decision, rationale, rejected alternatives, unresolved risks, owner, and
+ revisit trigger.
- - Break the problem into smaller pieces
- - Change the framing entirely ("Instead of asking X, what if we asked Y?")
- - Tell a story or analogy that might spark new thinking
- - Suggest taking a "vacation" from the problem to explore tangential ideas
+ Label the next action correctly: further search, consultation, simulation,
+ pilot design, protocol development, preregistration, or no action. If a
+ confirmatory study is planned, preregister hypotheses and analysis decisions
+ before outcomes are known; report later deviations and exploratory work
+ transparently. Preregistration improves transparency but is not peer review,
+ ethical approval, or proof of validity.
- ### When Ideas Are Too Safe
+ ## Bias and failure controls
- - Explicitly encourage risk-taking: "What's an idea so bold it makes you nervous?"
- - Play devil's advocate to the conservative approach
- - Ask about failed or abandoned approaches and why they might actually work
- - Propose intentionally provocative "what ifs"
+ - **Production blocking:** private parallel generation before oral discussion.
+ - **Anchoring and design fixation:** no leader answer or AI examples until the
+ independent round; reopen generation after evidence review.
+ - **Authority and status effects:** leader-last sharing, anonymous input,
+ independent ratings, and visible dissent.
+ - **Groupthink:** assign a genuine alternative-generation role, invite outside
+ review, and document rejected options. Treat “groupthink” as a family of
+ risks, not a single universally established diagnosis.
+ - **Evaluation apprehension:** separate contribution from attribution where
+ possible; critique ideas, not contributors.
+ - **Premature convergence:** fixed divergence window followed by an explicit
+ transition and predeclared criteria.
+ - **False precision:** use anchored scales, uncertainty ranges, sensitivity
+ analysis, and narrative review.
+ - **Research-gap inflation:** record search boundaries and use “no direct
+ evidence located,” not “never studied.”
+ - **AI hallucination or homogenization:** human-first ideation, provenance,
+ independent verification, multiple non-AI perspectives, and comparison for
+ suspiciously repeated frames. See `references/responsible_ai.md`.
- ### When Energy Lags
+ ## Optional local CLIs
- - Inject enthusiasm about interesting ideas
- - Share genuine curiosity about a particular direction
- - Ask about something that excites them personally
- - Take a brief tangent into a related but different topic
+ The scripts are deterministic, standard-library utilities. They do not call a
+ network service, LLM, or scientific database and do not make scientific
+ conclusions.
- ## Resources
+ ```bash
+ python scripts/session_scaffold.py --help
+ python scripts/validate_register.py --help
+ python scripts/evaluate_matrix.py --help
+ ```
- ### references/brainstorming_methods.md
+ Create a session register:
- Contains detailed descriptions of structured brainstorming methodologies that can be consulted when standard techniques need supplementation:
- - SCAMPER framework (Substitute, Combine, Adapt, Modify, Put to another use, Eliminate, Reverse)
- - Six Thinking Hats for multi-perspective analysis
- - Morphological analysis for systematic exploration
- - TRIZ principles for inventive problem-solving
- - Biomimicry approaches for nature-inspired solutions
+ ```bash
+ python scripts/session_scaffold.py \
+ --session-id "microbiome-01" \
+ --title "Microbiome mechanism ideation" \
+ --question "Which mechanisms could explain the scoped observation?" \
+ --participant P01 --participant P02 \
+ --output session.json
+ ```
- Consult this file when the scientist requests a specific methodology or when the brainstorming session would benefit from a more structured approach.
+ Validate structure and provenance:
- ## Notes
+ ```bash
+ python scripts/validate_register.py session.json --output validation.json
+ ```
- - This is a **conversation**, not a lecture. The scientist should be doing at least 50% of the talking.
- - Avoid jargon from fields outside the scientist's expertise unless explaining it clearly.
- - Be comfortable with silence—give space for thinking.
- - Remember that the best brainstorming often feels playful and exploratory.
- - The goal is not to solve everything, but to open new possibilities.
+ Calculate a fully disclosed weighted matrix from CSV, including score intervals
+ and one-at-a-time weight sensitivity:
+ ```bash
+ python scripts/evaluate_matrix.py scores.csv \
+ --config criteria.json \
+ --weight-delta 0.10 \
+ --output matrix.json
+ ```
+
+ Outputs refuse symlinks and existing files unless `--force` is explicit; inputs
+ and collection sizes are bounded. The validator checks structure, not truth.
+ The matrix preserves qualitative review and uncertainty and leaves
+ `decision` null. Input formats and interpretation are documented in
+ `references/idea_evaluation.md`.
+
+ ## Reference index
+
+ - `references/brainstorming_methods.md` — evidence-calibrated method selection,
+ nominal groups, Delphi, structured elicitation, and creative prompts.
+ - `references/facilitation_workflows.md` — ready-to-run individual, group, and
+ asynchronous session protocols plus provenance templates.
+ - `references/idea_evaluation.md` — criteria, scoring formula, uncertainty,
+ sensitivity analysis, gates, and decision logs.
+ - `references/responsible_ai.md` — accountable AI assistance, confidentiality,
+ hallucination, homogenization, disclosure, dual-use, and integrity.
+ - `references/sources.md` — dated primary studies and official guidance
+ consulted for this version.