brainstorming-and-ideating
Skill1 starsChanged 6 days agoUnlicenseView on GitHub
Explores requirements, mines user insights, and designs architectural or creative concepts before implementation. Synthesizes structured ideation (SIT, TRIZ, bisociation), tension spotting, project-native architectural trade-offs, and multi-axis evaluation. Use when initiating creative work, designing features, brainstorming research ideas, developing product specs, or exploring technical alternatives. Don't use for deterministic linear workflows, one-off scripts, final copywriting polish, or general coding edits.
In this repository76 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ad-copy-writerSkill
- ae-inspect-describeSkill
- algorithmic-artSkill
- animation-directorSkill
- assembly-guideSkill
- brainstorming-research-ideasSkill
- brainstormingSkill
- brief-to-tasksSkill
- canvas-designSkill
- cli-designSkill
- cli-output-hierarchySkill
- commit-messageSkill
- craft-uiSkill
- creative-directorSkill
- design-briefSkill
- design-flowSkill
- design-mock-auditSkill
- design-reviewSkill
- design-system-patternsSkill
- design-tokensSkill
- deslopifySkill
- diagnoseSkill
- diagramming-app-routesSkill
- doc-restructureSkill
- eval-criticSkill
- formatting-open-markdownsSkill
- frontend-designSkill
- frontend-slidesSkill
- gdocs-tab-writerSkill
- gemini-apiSkill
- gif-creationSkill
- github_repo_researchSkill
- grill-meSkill
- grill-with-docsSkill
- hallmarkSkill
- handoffSkill
- html-presentationSkill
- humanizerSkill
- i-have-adhdSkill
- improve-codebase-architectureSkill
- information-architectureSkill
- install-skill-from-githubSkill
- markdown-output-hierarchySkill
- marketing-psychologySkill
- merge-latestSkill
- modern-web-performanceSkill
- motion-designSkill
- pdf-readerSkill
- pm-brainstormingSkill
- pm-discovery-brainstormSkill
- product-marketingSkill
- prototypeSkill
- pull-requestSkill
- ralph_loopSkill
- react-best-practicesSkill
- review-loopSkill
- sandbox-explainerSkill
- skill-creatorSkill
- skill-optSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 41
Never overwhelm the user or developer with multiple questions in a single response.
- Distinctive: line 60
Treat ideas 1 through 3 as conventional warmup.
- Distinctive: line 72
Every proposed architectural or research alternative must include concrete, falsifiable verification criteria (e.g., runnable validation …
- Very specific: line 78
Write finalized, validated designs to a markdown artifact in the session's plans directory using the format YYYY-MM-DD-<topic>-design.md.
- Very specific: line 88
For Phase 2 (Insight Discovery & Tensions): Read references/insight-and-tensions.md (covers Mark Pollard's Four Points, Jobs-to-be-Done …
- Very specific: line 92
For Phase 3 (Ideation & Triplet Generation): Read references/ideation-methods.md (covers triplet method selection across Structural, …
- Very specific: line 100
For Phase 4 (Evaluation & Stress-Testing Rubrics): Read references/evaluation-rubric.md (covers Brief Compliance pass/fail gates, …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Brainstorming & Ideating Concepts Into Designs
This skill orchestrates requirements exploration, consumer tension mining, structural ideation, and multi-axis evaluation before implementation.
1. Phase Router
Determine the active phase from conversation context:
- Phase 1: INTAKE: New brief, feature request, "come up with", or initiating conceptual design.
- Phase 2: INSIGHT: "Find an insight", tension discovery, or possessing raw requirements without underlying rationale.
- Phase 3: IDEATION: "Generate ideas", exploring alternatives, or possessing an insight needing concrete concepts.
- Phase 4: EVALUATE & REFINE: "Critique", "improve the concept", "stress-test", or scoring proposals against rubrics.
- Phase 5: ARTICULATE: "Finalize design doc", structuring specifications, or preparing persistence artifacts.
- Full Cycle (Standard Workflow): Execute sequentially: Phase 1 → Phase 2
→ Phase 3 → Phase 4 → Phase 5.
- Dynamic Bypass Rule: For straightforward engineering implementation tasks (e.g., adding a caching layer or retry flag), dynamically bypass Phase 2 insight discovery and advance directly from Phase 1 to Phase 3 (proposing 2 to 3 architectural trade-offs).
2. Non-Negotiable Core Constraints
2.1 Single-Question Refinement
Never overwhelm the user or developer with multiple questions in a single response. Ask clarifying questions strictly one at a time during refinement.
2.2 Incremental Validation Blocks
Deliver architectural or creative proposals in bite-sized blocks (200 to 300 words). Pause and request explicit user validation after each block. Do not advance to subsequent design sections until the preceding block is approved.
2.3 Simplicity as Violence & YAGNI
Actively recommend pruning speculative features, configurability, or over-engineering. Enforce the clarity check: if a concept cannot be explained completely in one sentence, it is not an idea—it is a plan.
2.4 Warmup Pruning (Serial Order Effect)
Statistically, early ideas generated during an ideation cycle represent conventional warmup (obvious approaches accessible to anyone in the domain). Treat ideas 1 through 3 as conventional warmup. Deprioritize these early concepts and focus refinement on deeper directions (ideas 5 through 12+).
2.5 Competitor Swap Verification
Replace the primary product, brand, or architecture component in a proposal with
a direct competitor or generic alternative. If the concept still functions
identically without modification, it lacks differentiating specificity
(Originality <= 5.0). Re-anchor the design in unique core capabilities.
2.6 Verifiable Falsifiability
Every proposed architectural or research alternative must include concrete, falsifiable verification criteria (e.g., runnable validation checks via native test runners, explicit test assertions, or quantitative empirical thresholds).
2.7 Plan Persistence
Write finalized, validated designs to a markdown artifact in the session's plans
directory using the format YYYY-MM-DD-<topic>-design.md.
3. Phase Execution Modules
For comprehensive methodologies, mining prompts, and scoring rubrics, consult the L2 reference modules on demand:
- For Phase 2 (Insight Discovery & Tensions): Read
references/insight-and-tensions.md(covers Mark Pollard's Four Points, Jobs-to-be-Done analysis, Cultural/Category/Human tension spotting, How-Might-We laddering, and canonical insight formulas). - For Phase 3 (Ideation & Triplet Generation): Read
references/ideation-methods.md(covers triplet method selection across Structural, Collision, and Perturbation categories, warmup pruning, and system architecture idioms). When ideas must be genuinely novel rather than competent variations, also readreferences/novel-ideation.md(covers anti-convergence techniques: average purge, bisociative domain collision, constraint inversion, temporal retrieval, adversarial stress testing, and specificity checks to defeat LLM mode collapse). - For Phase 4 (Evaluation & Stress-Testing Rubrics): Read
references/evaluation-rubric.md(covers Brief Compliance pass/fail gates, 6-Criteria multi-axis scoring, Competitor Swap verification, and Kill Your Darlings stress-testing).
4. Upstream Attribution & Documentation
For complete upstream attribution, cognitive provenance, and links to all source
repositories, read README.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

