@dzhechkov/keysarium 1.0.0

package/templates/.claude/rules/domain-specific.md

@@ -0,0 +1,32 @@
+# Domain-Specific Rules
+
+## Banking / FinTech
+- ALWAYS recommend on-premise LLM deployment (GigaChat, YandexGPT, open-source)
+- ALWAYS reference: ФЗ-152, ЦБ requirements, ФСТЭК
+- HITL (Human-in-the-Loop) is MANDATORY for any decision-making
+- Data NEVER leaves the security perimeter
+- Palette: Blue/Navy/Silver
+- Tone: strict, reliable, conservative
+
+## Retail / E-commerce
+- Latency budget: < 200ms for real-time recommendations
+- A/B testing as primary validation method
+- Balance personalization vs. privacy (GDPR/ФЗ-152)
+- Address seasonality and cold-start problems
+- Palette: Amber/Orange
+
+## Enterprise / B2B
+- Address Change Management (people resist AI)
+- Plan for Legacy system integration
+- Define SLA and fault tolerance
+- Express ROI in FTE/hours saved, not abstract percentages
+- Palette: Teal/Indigo
+
+## Healthcare
+- HITL mandatory for ALL clinical decisions
+- Reference: ФЗ-323, medical device regulations
+- Explainability requirements for AI decisions
+- Patient data isolation (ФЗ-152 + medical specifics)
+
+## Detection
+Detect domain from case description keywords and apply rules automatically.

package/templates/.claude/rules/file-conventions.md

@@ -0,0 +1,38 @@
+# File Conventions
+
+## Research Artifacts
+All research artifacts MUST be created inside `researches/<case-slug>/` directory.
+NEVER create research files in the project root.
+
+## Naming
+- Case slugs: snake_case, Latin characters only (e.g., `bank_kc_automation`)
+- Phase artifacts: numbered prefix (00_, 01_, 02_, etc.)
+- Diagrams: descriptive kebab-case (e.g., `architecture-c4.mermaid`)
+- Prototypes: in `prototype/` subdirectory
+
+## File Creation Timing
+Artifacts are created AT THE END of their phase, NOT deferred to Phase 6.
+Each phase checkpoint verifies the file exists.
+
+## Directory Structure per Research
+```
+researches/<slug>/
+├── 00_product_discovery.md
+├── 01_case_brief.md
+├── 02_research_findings.md
+├── 02.5_trend_brief.md
+├── 03_solution_strategy.md
+├── 04_architecture.md
+├── 05_presentation_content.md
+├── 06_speaker_script.md
+├── 07_qa_preparation.md
+├── 08_executive_summary.md
+├── prototype/
+│   └── cjm-prototype.jsx
+├── diagrams/
+│   ├── architecture-c4.mermaid
+│   ├── sequence-main-flow.mermaid
+│   ├── process-as-is.mermaid
+│   └── process-to-be.mermaid
+└── README.md
+```

package/templates/.claude/rules/modular-reuse.md

@@ -0,0 +1,35 @@
+# Modular Reuse Rules
+
+## Skills are Domain-Agnostic
+Skills in .claude/skills/ are designed to work across ANY domain:
+- explore: works for any task clarification
+- goap-research-ed25519: works for any research topic
+- problem-solver-enhanced: works for any complex problem
+- frontend-design: works for any UI task
+- presentation-storyteller: works for any presentation
+- reverse-engineering-unicorn: works for any company analysis
+
+## Commands are Pipeline-Specific
+Commands in .claude/commands/ implement the Casarium pipeline.
+They can be adapted for other pipelines by:
+1. Copying the command file
+2. Modifying phase-specific content
+3. Keeping the skill loading pattern intact
+
+## Agent Templates are Reusable
+Agent templates in .claude/agents/ define reusable agent configurations.
+They can be composed for different workflows.
+
+## Library Functions
+Shared logic lives in lib/ directory:
+- lib/phase-utils.md: Common phase utilities
+- lib/agent-patterns.md: Agent spawning patterns
+- lib/checkpoint-template.md: Checkpoint formatting
+
+## Extending the System
+To add a new phase:
+1. Create .claude/commands/new-phase.md
+2. Create or reuse a skill in .claude/skills/
+3. Add agent template in .claude/agents/ if parallelizable
+4. Update CLAUDE.md pipeline table
+5. Update docs/

package/templates/.claude/rules/research-quality.md

@@ -0,0 +1,20 @@
+# Research Quality Rules
+
+## PARANOID Mode (Default for all research)
+- Every factual claim MUST have a verifiable source
+- Zero tolerance for hallucinated citations
+- Confidence threshold: 0.99 minimum
+- If source cannot be verified → mark as [UNVERIFIED] and flag
+
+## Citation Requirements
+- Format: `[Claim] — Source: [URL or publication], [Date]`
+- No bare claims without attribution in research documents
+- Self-generated analysis must be explicitly marked as `[ANALYSIS]`
+
+## Verification Checklist
+Before completing any research phase:
+- [ ] All claims have sources
+- [ ] No unverified statistics or percentages
+- [ ] Competitor names verified to exist
+- [ ] Technology recommendations are for real, available products
+- [ ] Regulatory references cite actual laws/standards

package/templates/.claude/settings.json

@@ -0,0 +1,37 @@
+{
+  "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Write|Edit",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "bash -c 'if echo \"$CLAUDE_TOOL_INPUT\" | grep -q '\"researches/\"' && ! echo \"$CLAUDE_TOOL_INPUT\" | grep -qE '\"researches/[a-z0-9_]+/\"'; then echo \"⚠️ BLOCKED: Research files must be inside researches/<case-slug>/ directory\" && exit 1; fi; exit 0'"
+          }
+        ]
+      }
+    ],
+    "PostToolUse": [
+      {
+        "matcher": "Write",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "bash -c 'if echo \"$CLAUDE_TOOL_INPUT\" | grep -qE \"0[0-8]_.*\\.md\"; then echo \"📋 Artifact created. Remember to update the tracker in README.md\"; fi; exit 0'"
+          }
+        ]
+      }
+    ],
+    "Notification": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "echo '🔔 Task completed'"
+          }
+        ]
+      }
+    ]
+  }
+}

package/templates/.claude/skills/explore/SKILL.md

@@ -0,0 +1,215 @@
+---
+name: explore
+description: >
+  Adaptive task exploration and clarification skill for transforming vague 
+  requests into actionable specifications. Use when a user presents any task, 
+  problem, or goal that requires clarification before execution. Triggers on 
+  ambiguous requests, complex multi-part tasks, "I want to...", "help me with...", 
+  strategic decisions, product ideas, creative briefs, and any situation where 
+  understanding the real need is essential before proposing solutions. Does NOT 
+  provide solutions until task is fully explored.
+---
+
+# Explore: Adaptive Task Clarification
+
+Transform vague requests into crystal-clear, actionable task specifications through systematic Socratic questioning.
+
+## Core Philosophy
+
+**Never solve before you understand.** Most failed solutions solve the wrong problem. This skill ensures the real problem is understood before any solution is proposed.
+
+Key principles:
+- Questions unlock understanding; answers often hide assumptions
+- The stated goal is rarely the real goal
+- Constraints reveal opportunities
+- Success criteria prevent scope creep
+
+## Task Classification
+
+Before asking questions, classify the task type to select appropriate exploration dimensions:
+
+| Task Type | Indicators | Primary Dimensions |
+|-----------|------------|-------------------|
+| **Product/Feature** | "build", "create app", "develop" | Outcome, Users, Constraints, Success |
+| **Problem Solving** | "fix", "solve", "issue with" | Root Cause, Constraints, Attempted Solutions |
+| **Decision Making** | "should I", "choose between", "evaluate" | Criteria, Tradeoffs, Timeline, Reversibility |
+| **Creative** | "write", "design", "make content" | Audience, Tone, Format, Examples |
+| **Research** | "find out", "analyze", "understand" | Scope, Depth, Sources, Deliverable |
+| **Process/Workflow** | "how to", "improve process" | Current State, Desired State, Blockers |
+
+## Exploration Dimensions
+
+Select 3-5 dimensions based on task type. Each dimension has multiple question variants—choose the most natural for context.
+
+### 1. The Real Objective
+Uncover what success truly looks like, beyond the stated request.
+
+**Questions:**
+- "If this worked perfectly, what would be different in your [work/life/business]?"
+- "What outcome would make you say 'this was absolutely worth it'?"
+- "Is this goal a means to something else, or the end itself?"
+- "If you could wave a magic wand and have any result, what would you choose?"
+
+**Red flags to probe:** Generic goals ("make it better"), proxy metrics, solutions presented as requirements.
+
+### 2. Constraints & Boundaries
+Identify hard limits that shape the solution space.
+
+**Questions:**
+- "What's absolutely off the table—budget, time, technology, or approach-wise?"
+- "What existing systems, processes, or decisions must this work with?"
+- "Who needs to approve this, and what are their non-negotiables?"
+- "What would disqualify a solution, even if it technically works?"
+
+**Red flags to probe:** No constraints mentioned (usually means hidden ones), unrealistic expectations.
+
+### 3. Available Resources
+Understand leverage points and existing assets.
+
+**Questions:**
+- "What do you already have that we could build on—data, tools, people, prior work?"
+- "Who else is involved, and what can they contribute?"
+- "What similar problems have you solved before, and what worked?"
+- "What's your actual capacity to implement this?"
+
+**Red flags to probe:** Overestimated capabilities, unacknowledged dependencies.
+
+### 4. Timeline & Urgency
+Distinguish real deadlines from arbitrary ones.
+
+**Questions:**
+- "What happens if this takes 2x longer than expected?"
+- "Is there a hard deadline, and what's driving it?"
+- "Would you prefer a quick 80% solution or a slower 100% solution?"
+- "What's the cost of delay vs. the cost of getting it wrong?"
+
+**Red flags to probe:** Artificial urgency, no clear driver for deadline.
+
+### 5. Success Criteria
+Define what "done" actually means.
+
+**Questions:**
+- "How will you know this is successful? What will you measure?"
+- "Who decides if this is good enough, and what will they look for?"
+- "What's the minimum viable outcome that would still be valuable?"
+- "In 6 months, what would make you regret the approach we took?"
+
+**Red flags to probe:** Vague criteria ("stakeholders will be happy"), moving targets.
+
+### 6. Attempted Solutions (for problems)
+Learn from what hasn't worked.
+
+**Questions:**
+- "What have you already tried, and why didn't it work?"
+- "What solutions have you considered but rejected?"
+- "What would the obvious solution be, and why isn't that good enough?"
+
+### 7. Audience & Stakeholders (for products/content)
+Understand who this serves.
+
+**Questions:**
+- "Who specifically will use this, and what's their context when they do?"
+- "What does your audience already know or believe about this?"
+- "Who might be negatively affected, and does that matter?"
+
+## Execution Protocol
+
+### Phase 1: Initial Assessment (1 turn)
+
+1. Parse the user's request
+2. Identify what's already clear from context
+3. Classify task type
+4. Select 3-5 most critical dimensions
+5. Note any immediate red flags or assumptions
+
+### Phase 2: Adaptive Questioning (3-7 turns)
+
+**Rules:**
+- Ask ONE question at a time
+- Make questions specific and decision-shaping, not generic
+- Challenge vague answers: "Can you be more specific about...?"
+- Acknowledge answers before next question
+- Skip dimensions already clarified
+- Stop when you have enough to create a clear brief
+
+**Question Sequencing:**
+1. Start with Real Objective (reveals the most)
+2. Follow with Constraints (narrows solution space)
+3. Then Success Criteria (defines done)
+4. Fill gaps with other dimensions as needed
+
+**Adaptive behavior:**
+- If user gives detailed answer → compress follow-ups
+- If user seems frustrated → summarize and ask if they want to continue
+- If contradiction detected → gently probe: "Earlier you mentioned X, but now Y—help me understand?"
+
+### Phase 3: Task Brief Synthesis (1 turn)
+
+After sufficient exploration, synthesize into a **Task Brief**:
+
+```
+## Task Brief
+
+**Objective:** [Clear statement of what we're actually solving]
+
+**Context:** [Relevant background and constraints]
+
+**Success Criteria:**
+- [Measurable criterion 1]
+- [Measurable criterion 2]
+
+**Constraints:**
+- [Hard constraint 1]
+- [Hard constraint 2]
+
+**Resources Available:** [What we can leverage]
+
+**Timeline:** [Deadline and urgency level]
+
+**Key Assumptions:** [Things we're assuming that could change the approach]
+
+**Out of Scope:** [Explicitly excluded items]
+```
+
+Ask user: "Does this capture what you need? Anything to add or correct?"
+
+### Phase 4: Handoff
+
+Once validated, either:
+- Proceed to solution (if user wants immediate help)
+- Export brief for later use
+- Suggest appropriate next steps/skills
+
+## Anti-Patterns to Avoid
+
+❌ **Interrogation mode:** Don't fire questions robotically
+❌ **Assuming context:** Don't skip clarification because you "think" you understand
+❌ **Premature solutions:** Don't hint at solutions before exploration is complete
+❌ **Over-questioning:** Stop when you have enough clarity
+❌ **Generic questions:** Each question should be tailored to this specific task
+❌ **Ignoring signals:** If user provides info proactively, don't re-ask
+
+## Example Flow
+
+**User:** "I want to create a dashboard for my team"
+
+**Claude (Phase 1 assessment):**
+- Task type: Product/Feature
+- Unclear: Who uses it, what data, what decisions it enables, timeline
+- Dimensions needed: Real Objective, Audience, Constraints, Success Criteria
+
+**Claude:** "Before we dive in—what decisions will your team make differently once they have this dashboard? What's the main insight they're missing today?"
+
+*[User answers about tracking project delays]*
+
+**Claude:** "Got it—so the core need is visibility into project health to catch delays early. How do you know a project is delayed today? What's the current process for catching these issues?"
+
+*[Continues adaptively based on answers...]*
+
+## Integration Notes
+
+After exploration, this skill can hand off to:
+- problem-solver-enhanced (for complex problems)
+- goap-research (for research tasks)
+- frontend-design (for UI/product tasks)
+- Any implementation skill with the structured Task Brief

package/templates/.claude/skills/explore/references/questioning-techniques.md

@@ -0,0 +1,151 @@
+# Advanced Questioning Techniques
+
+Reference for sophisticated question patterns when standard approaches don't yield clarity.
+
+## Socratic Techniques
+
+### Clarifying Questions
+When answers are vague or use undefined terms:
+- "What do you mean by [term]?"
+- "Can you give me a specific example of [concept]?"
+- "How would you explain this to someone unfamiliar with your context?"
+
+### Assumption Probing
+When hidden assumptions might be distorting the problem:
+- "What would have to be true for this approach to work?"
+- "What are you taking for granted here that might not be true?"
+- "If you were wrong about [assumption], how would that change things?"
+
+### Consequence Exploration
+When second-order effects matter:
+- "If this succeeds, what problems might it create?"
+- "Who might be affected that we haven't considered?"
+- "What's the worst realistic outcome if this goes wrong?"
+
+### Perspective Shifting
+When stuck in one frame:
+- "How would [competitor/user/skeptic] view this?"
+- "If you had to argue against this approach, what would you say?"
+- "What would you advise someone else in this situation?"
+
+## Techniques for Specific Blockers
+
+### When user presents solution as requirement
+"I need a mobile app for X"
+
+**Approach:** Trace back to underlying need
+- "What problem would the mobile app solve?"
+- "How do users handle this today without the app?"
+- "If a mobile app wasn't an option, how else might you solve this?"
+
+### When user can't articulate success
+"I'll know it when I see it"
+
+**Approach:** Use concrete scenarios
+- "Imagine it's 6 months from now and this was a huge success—describe what's happening"
+- "If you had to bet money on one metric improving, what would it be?"
+- "What would your boss/customer/user say that would prove this worked?"
+
+### When constraints seem impossible
+"We need enterprise features but have startup budget"
+
+**Approach:** Separate hard from soft constraints
+- "If you had to prioritize: which constraint is truly immovable?"
+- "What's the minimum viable version that would still be valuable?"
+- "What could you trade off to make this feasible?"
+
+### When user is emotionally invested
+User seems attached to a specific solution
+
+**Approach:** Validate, then explore
+- "It sounds like you've thought about this a lot. What led you to this approach?"
+- "What would make you reconsider this direction?"
+- "What's the strongest argument against this that you've heard?"
+
+### When multiple stakeholders with conflicting needs
+"My boss wants X but users want Y"
+
+**Approach:** Map the conflict explicitly
+- "Let's map out who wants what. What does your boss's ideal outcome look like?"
+- "Where exactly do these needs conflict?"
+- "Is there a version that gives each party their most important thing?"
+
+## Question Formulation Patterns
+
+### The Magic Wand
+Removes artificial constraints to reveal true desires:
+"If you could wave a magic wand and have any outcome, what would you choose?"
+
+### The Premortem
+Surfaces hidden risks:
+"Imagine this failed spectacularly—what went wrong?"
+
+### The Constraint Inversion
+Challenges assumptions about limitations:
+"What if [constraint] wasn't a factor—would you approach this differently?"
+
+### The Minimum Viable Success
+Defines the essential core:
+"What's the smallest version of this that would still be valuable?"
+
+### The Regret Test
+Clarifies priorities over time:
+"In a year, what would you regret not having done?"
+
+### The Opportunity Cost
+Reveals trade-offs:
+"What else could you do with the time/money/effort this would require?"
+
+### The Outsider View
+Escapes insider bias:
+"How would you explain this problem to someone completely outside your industry?"
+
+## Red Flags and Responses
+
+| Red Flag | What It Might Mean | How to Probe |
+|----------|-------------------|--------------|
+| "Everyone knows..." | Unexamined assumption | "Help me understand—what's the evidence for this?" |
+| "We've always done it this way" | Inertia, not strategy | "What originally drove this approach? Is that still true?" |
+| "It's obvious that..." | Blind spot | "Walk me through why this is obvious—I want to make sure I understand" |
+| "We just need to..." | Oversimplification | "What could go wrong with this approach?" |
+| "ASAP" | Artificial urgency | "What specifically happens if this takes longer?" |
+| No constraints mentioned | Hidden constraints | "What would disqualify a solution even if it technically works?" |
+| Very specific solution stated | Solution fixation | "What problem does this solve? Are there other ways to solve it?" |
+
+## Calibrating Question Depth
+
+### Light Touch (1-2 questions per dimension)
+Use when:
+- User is experienced and already has clarity
+- Task is straightforward
+- Time is genuinely constrained
+- User shows frustration
+
+### Deep Exploration (3-5 questions per dimension)
+Use when:
+- High stakes decision
+- Multiple stakeholders
+- Technical complexity
+- User seems uncertain
+- Contradictions in answers
+
+### Signs to Stop Questioning
+- User is repeating themselves
+- Answers are becoming terse
+- You have enough for a clear brief
+- User explicitly says "that's enough"
+- Remaining questions are nice-to-know, not need-to-know
+
+## Cultural Considerations
+
+Some users may:
+- View detailed questions as distrust
+- Expect to define solutions themselves
+- Be uncomfortable with "why" questions
+- Prefer to give context incrementally
+
+**Adaptive responses:**
+- Frame questions as "helping me help you better"
+- Acknowledge their expertise: "You know this space—help me understand..."
+- Use "what" instead of "why" when appropriate
+- Offer to explain why you're asking