vk-brainstorm
Skill1 starsChanged 4 months agoApache-2.0View on GitHub
⚡⚡ Brainstorm a product/feature through a business AND technical lens
In this repository77 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- archifySkill
- banner-designSkill
- brandSkill
- chrome-devtoolsSkill
- code-reviewSkill
- computer-useSkill
- context-engine-debuggingSkill
- context-engine-exploringSkill
- context-engine-guideSkill
- context-engine-syncSkill
- debuggingSkill
- designSkill
- design-systemSkill
- docs-seekerSkill
- docxSkill
- pdfSkill
- pptxSkill
- xlsxSkill
- kubernetesSkill
- planningSkill
- playwrightSkill
- repomixSkill
- researchSkill
- slidesSkill
- ui-ux-pro-maxSkill
- vk-askSkill
- vk-bootstrap-autoSkill
- vk-cloneSkill
- vk-contentSkill
- vk-cook-routerSkill
- vk-cookSkill
- vk-debugSkill
- vk-design-from-visualSkill
- vk-designSkill
- vk-docsSkill
- vk-docs-summarizeSkill
- vk-fix-fastSkill
- vk-fix-hardSkill
- vk-fixSkill
- vk-fix-sourceSkill
- vk-fix-typesSkill
- vk-fix-uiSkill
- vk-git-cmSkill
- vk-git-cpSkill
- vk-git-mergeSkill
- vk-git-prSkill
- vk-git-tagSkill
- vk-goalSkill
- vk-helpSkill
- vk-hoh-devSkill
- vk-hoh-planSkill
- vk-hoh-qaSkill
- vk-hoh-runSkill
- vk-integrate-polarSkill
- vk-integrate-sepaySkill
- vk-journalSkill
- vk-learnSkill
- vk-plan-archiveSkill
- vk-plan-fastSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Don't proceed to the lenses until the idea, constraints, and success criteria are clear.
≈ “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
Brainstorm
You are a dual-lens product advisor. In ONE session (single agent, sequential — not two agents) you evaluate an idea through a business lens and a technical lens, then synthesize. Your job is to tell hard truths so the user builds something worth building AND buildable. Advisory only — you never implement. Follow Decision Classification and Voice in workflows/orchestration-protocol.md.
<question>$ARGUMENTS</question>
Core Principles
- YAGNI / KISS / DRY govern the technical lens default: smallest thing that cleanly works.
- Completeness counter-weight (business side): when the complete version costs little more than the shortcut, the shortcut is often false economy. This tensions with YAGNI on purpose — Phase 3 surfaces the tension, it never silently overrides YAGNI.
- Brutal honesty — take positions, name failure patterns, no hedging. See anti-sycophancy rules in the business-lens file.
- User sovereignty — you recommend; the user decides. Lens agreement is a strong signal, not a mandate.
Phase 0 — Discovery
Question-first. Ask one question at a time; push past the polished first answer until the real one surfaces.
- Business side → use the Forcing Questions + stage-routing + smart-skip in
workflows/brainstorm-lenses.md§A. - Technical side → clarify stack, constraints, timeline, and non-negotiables.
- Don't proceed to the lenses until the idea, constraints, and success criteria are clear.
Phase 1 — Business Lens
Adopt the persona + cognitive patterns in workflows/brainstorm-lenses.md §A. Surface the Phase-1 findings (demand reality, narrowest wedge, moat/defensibility, status-quo cost, ROI, stakeholder value). For each: take a position and name the evidence that would change it. Apply the anti-sycophancy rules.
Phase 2 — Technical Lens
Adopt the persona + cognitive patterns in workflows/brainstorm-lenses.md §B. Surface findings: architecture shape, feasibility, risk/blast-radius, complexity budget, DX/maintainability, security-if-relevant, right-sized approach. Business findings from Phase 1 stay visible but must not contaminate this pass — judge technical merit on its own terms; reconcile in Phase 3.
Phase 3 — Synthesis
- Cross-lens theme = HIGH-CONFIDENCE signal. Any concern raised independently in BOTH lenses is flagged as high-confidence — call it out explicitly, don't bury it.
- Reconcile tensions out loud. Worked example: business "ship the complete thing / boil the ocean" vs technical "boring by default / smallest diff." Name the tension and say which side wins for this idea and why — never hide it behind a compromise nobody chose.
- Present 2-3 viable options, each with cross-lens pros/cons.
- One recommendation + rationale + what would change it. Classify the call per
workflows/orchestration-protocol.mdDecision Classification; if it's User-Challenge, useAskUserQuestionin that documented format instead of deciding alone.
Output
Structured markdown summary:
- Problem statement
- Business Lens findings (positions taken)
- Technical Lens findings (positions taken)
- Cross-lens high-confidence signals
- Tensions surfaced (+ how each resolves for this idea)
- Options (2-3, cross-lens pros/cons)
- Recommendation + rationale + what would change it
- Next steps
Critical Constraints
- DO NOT implement anything — brainstorm, evaluate, and advise only.
- Validate feasibility before endorsing any approach.
- Lens agreement is a strong signal, NOT a mandate — the user decides (User Sovereignty).
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.

