specsmd 0.0.0-dev.80 → 0.0.0-dev.81

package/flows/ideation/agents/orchestrator/skills/spark/references/techniques/questorming.md

@@ -0,0 +1,51 @@
+# Questorming Technique
+
+**Origin**: Hal Gregersen's "Question Burst" methodology; also related to Osborn's principle of exploring the problem space before solving.
+
+**Interaction type**: Co-build — AI generates questions, user identifies the most important ones, AI builds ideas from those.
+
+## How It Works
+
+1. **State the topic** without any solutions in mind
+2. **Generate questions only** — no answers allowed during this phase
+3. **Aim for 15-20 questions** in rapid succession
+4. **Categorize** — which questions challenge assumptions? Which reframe the problem?
+5. **Select the most provocative questions** — these become the seed for new ideas
+6. **Generate ideas** from the selected questions
+
+## Question Types
+
+### Assumption-Challenging
+- Why do we assume [X] is necessary?
+- What if [commonly accepted truth] were false?
+- Who said this has to be done by [conventional actor]?
+
+### Scope-Shifting
+- What if we zoom out 10x — what's the bigger problem?
+- What if we zoom in 10x — what's the specific pain point?
+- What would this look like from the customer's customer's perspective?
+
+### Stakeholder Questions
+- Who benefits from the current broken state?
+- Who would lose if we solved this perfectly?
+- Who has already solved this in a different context?
+
+### Temporal Questions
+- Why hasn't this been solved yet?
+- What will make this irrelevant in 5 years?
+- What had to change for this to become solvable now?
+
+### Provocative Questions
+- What's the most expensive possible solution? The cheapest?
+- What would a competitor do with this opportunity?
+- What would a child suggest?
+
+## AI Application Notes
+
+When using questorming internally:
+1. Generate a burst of 8-10 questions about the topic
+2. Present 3-5 of the most provocative ones to the user
+3. Ask: "Which of these feels most important?" (the one elicit moment)
+4. If user doesn't engage, pick the most provocative question yourself (ai_fallback)
+5. Generate ideas seeded from the selected question(s)
+6. Best used when the problem space feels unclear or when the user says "I'm not sure what I want"

package/flows/ideation/agents/orchestrator/skills/spark/references/techniques/random-word.md

@@ -0,0 +1,34 @@
+# Random Word Technique
+
+**Origin**: Edward de Bono's lateral thinking toolkit. Forces connections between unrelated concepts.
+
+**Interaction type**: Generate — AI selects random stimulus and forces connections.
+
+## How It Works
+
+1. **Select a random concept** from an unrelated domain (not a literal random word — pick a vivid, concrete thing)
+2. **List its attributes** — what makes it interesting, how it works, what it's known for
+3. **Force connections** — map each attribute to the ideation topic
+4. **Develop the strongest connections** into full ideas
+
+## Examples of Forcing Connections
+
+**Topic**: Improving employee onboarding
+**Random concept**: Coral reef
+
+| Coral Reef Attribute | Forced Connection |
+|---------------------|-------------------|
+| Self-organizing ecosystem | Onboarding that self-organizes based on new hire's role and interests |
+| Symbiotic relationships | Pair each new hire with a "symbiont" — someone from a different team |
+| Builds slowly, lasts centuries | First-week foundations that compound over the entire tenure |
+| Bleaches under stress | Early warning system when onboarding overwhelms |
+| Attracts diverse species | Make onboarding a magnet event that existing employees want to attend |
+
+## AI Application Notes
+
+When using random-word internally:
+1. Pick concepts from **distant domains** — nature, games, history, architecture, music
+2. The more unrelated the concept, the more novel the connections
+3. Generate at least 5 attribute-connections, then pick the 2-3 most surprising
+4. Present only the resulting ideas — never mention "random word" or the stimulus process
+5. This technique is excellent for breaking fixation when ideas are clustering

package/flows/ideation/agents/orchestrator/skills/spark/references/techniques/scamper.md

@@ -0,0 +1,52 @@
+# SCAMPER Technique
+
+**Origin**: Bob Eberle, building on Alex Osborn's idea prompter checklists from *Applied Imagination* (1953).
+
+**Interaction type**: Generate — AI applies transformations, user reacts.
+
+## The Seven Operators
+
+### S — Substitute
+What can be substituted? Different materials, people, processes, components, approaches?
+- Replace one element with something unexpected
+- Swap the medium, channel, or context
+
+### C — Combine
+What can be combined? Blend two ideas, merge functions, mix purposes?
+- Combine features from different domains
+- Merge two user needs into one solution
+
+### A — Adapt
+What can be adapted from elsewhere? What analogies apply? What else is like this?
+- Borrow solutions from other industries
+- Adapt natural processes to the problem
+
+### M — Modify (also: Magnify / Minimize)
+What can be changed? Size, shape, color, meaning, frequency, intensity?
+- Make it 10x bigger or smaller
+- Change the speed, frequency, or intensity
+- Alter the form factor entirely
+
+### P — Put to Other Use
+Can this serve a different purpose? New contexts? New users? New markets?
+- Repurpose for a completely different audience
+- Use the byproduct as the main product
+
+### E — Eliminate
+What can be removed? Simplify? What's non-essential?
+- Remove the most complex component — what happens?
+- Strip to the absolute minimum viable version
+
+### R — Reverse (also: Rearrange)
+What if the order were reversed? What if roles swapped? What if inside-out?
+- Reverse the workflow
+- Let the user become the provider
+- Flip the value proposition
+
+## AI Application Notes
+
+When using SCAMPER internally:
+1. Pick 2-3 operators per batch (not all 7 — that produces too-similar ideas)
+2. Apply each operator to a **different domain** from the domain wheel
+3. Make the result vivid and specific, not abstract
+4. Never tell the user you're "using SCAMPER" — just present the transformed ideas

package/flows/ideation/agents/orchestrator/skills/spark/references/techniques/what-if.md

@@ -0,0 +1,49 @@
+# What-If Scenarios Technique
+
+**Origin**: Assumption-challenging methodology found across creative problem solving traditions.
+
+**Interaction type**: Generate — AI constructs scenarios, user reacts to the most interesting ones.
+
+## How It Works
+
+1. **Identify core assumptions** about the topic (explicit and implicit)
+2. **Challenge each assumption** with a "what if" that negates or transforms it
+3. **Explore the scenario** — what would the world look like if this were true?
+4. **Extract ideas** from the alternate reality
+
+## Types of What-If
+
+### Constraint Removal
+- What if money were no object?
+- What if there were no technical limitations?
+- What if you had unlimited time?
+- What if there were no regulations?
+
+### Constraint Inversion
+- What if the user had to pay NOT to use it?
+- What if it only worked for 5 minutes per day?
+- What if it required 100 people to operate?
+
+### Context Shift
+- What if this existed in 1920? In 2120?
+- What if this were designed for children? For astronauts? For animals?
+- What if this operated underwater? In zero gravity? In complete darkness?
+
+### Scale Shift
+- What if 1 billion people used this simultaneously?
+- What if it were the size of a building? A molecule?
+- What if it lasted 100 years? 100 milliseconds?
+
+### Role Reversal
+- What if the customer built it and the company used it?
+- What if the problem were actually the solution?
+- What if success and failure metrics were swapped?
+
+## AI Application Notes
+
+When using what-if internally:
+1. Identify 2-3 non-obvious assumptions about the topic
+2. Pick the most interesting what-if type for each assumption
+3. Briefly explore the scenario (2-3 sentences), then extract a concrete idea
+4. Present only the ideas — mention the "what if" framing only if it makes the idea clearer
+5. Best used when ideas are getting too conventional or practical

package/flows/ideation/agents/orchestrator/skills/spark/templates/spark-bank.md.hbs

@@ -0,0 +1,72 @@
+---
+session: {{session_id}}
+topic: "{{topic}}"
+phase: spark
+created: {{created}}
+total_ideas: {{total_ideas}}
+total_batches: {{total_batches}}
+favorites_count: {{favorites_count}}
+domains_covered: {{domains_covered}}
+---
+
+# Spark Bank: {{topic}}
+
+> {{total_ideas}} ideas generated across {{total_batches}} batches, covering {{domains_covered}}/12 domains.
+
+---
+
+## Favorites
+
+{{#each favorites}}
+### {{id}} — {{title}}
+
+{{description}}
+
+*Domain: {{domain}}*
+
+{{/each}}
+
+{{#unless favorites}}
+*No favorites selected yet.*
+{{/unless}}
+
+---
+
+## All Ideas by Theme
+
+{{#each themes}}
+### {{name}}
+
+{{#each ideas}}
+**{{id}}** — **{{title}}**
+{{description}}
+{{#if is_favorite}}*(favorite)*{{/if}}
+*Domain: {{domain}}*
+
+{{/each}}
+
+{{/each}}
+
+---
+
+## Domain Coverage
+
+| Domain | Ideas | Coverage |
+|--------|-------|----------|
+{{#each domain_stats}}
+| {{name}} | {{count}} | {{bar}} |
+{{/each}}
+
+---
+
+## Session Stats
+
+- **Batches generated**: {{total_batches}}
+- **Total ideas**: {{total_ideas}}
+- **Favorites**: {{favorites_count}}
+- **Techniques used**: {{techniques_used}}
+- **Provocations injected**: {{provocations_count}}
+
+---
+
+*Generated by specsmd Ideation Flow — Spark skill*

package/flows/ideation/commands/flame.md

@@ -0,0 +1,43 @@
+---
+description: Flame - multi-perspective idea evaluation and scoring
+---
+
+# Activate Flame
+
+**Command**: `/specsmd-flame`
+
+---
+
+## Activation
+
+You are now the **Ideation Orchestrator** in **Flame mode** for specsmd.
+
+**IMMEDIATELY** read and adopt the persona from:
+→ `.specsmd/ideation/agents/orchestrator/agent.md`
+
+Then execute the Flame skill:
+→ `.specsmd/ideation/agents/orchestrator/skills/flame/SKILL.md`
+
+---
+
+## Critical First Steps
+
+1. **Read Config**: `.specsmd/ideation/memory-bank.yaml`
+2. **Read Interaction Protocol**: `.specsmd/ideation/shared/protocols/interaction-adaptation.md`
+3. **If Spark Bank exists**: Load it and begin evaluation
+4. **If ideas provided directly**: Accept them and begin evaluation
+5. **If nothing**: Ask "Which ideas would you like to evaluate?"
+
+---
+
+## Routing Targets
+
+- **Back to Orchestrator**: `/specsmd-ideation`
+- **To Spark**: `/specsmd-spark`
+- **To Forge**: `/specsmd-forge`
+
+---
+
+## Begin
+
+Activate now. Read the Flame skill and start evaluating ideas.

package/flows/ideation/commands/forge.md

@@ -0,0 +1,43 @@
+---
+description: Forge - shape top ideas into actionable concept briefs
+---
+
+# Activate Forge
+
+**Command**: `/specsmd-forge`
+
+---
+
+## Activation
+
+You are now the **Ideation Orchestrator** in **Forge mode** for specsmd.
+
+**IMMEDIATELY** read and adopt the persona from:
+→ `.specsmd/ideation/agents/orchestrator/agent.md`
+
+Then execute the Forge skill:
+→ `.specsmd/ideation/agents/orchestrator/skills/forge/SKILL.md`
+
+---
+
+## Critical First Steps
+
+1. **Read Config**: `.specsmd/ideation/memory-bank.yaml`
+2. **Read Interaction Protocol**: `.specsmd/ideation/shared/protocols/interaction-adaptation.md`
+3. **If Flame Report exists**: Load shortlisted ideas and begin shaping
+4. **If ideas provided directly**: Accept them and begin shaping
+5. **If nothing**: Ask "Which ideas would you like to develop into concepts?"
+
+---
+
+## Routing Targets
+
+- **Back to Orchestrator**: `/specsmd-ideation`
+- **To Spark**: `/specsmd-spark`
+- **To Flame**: `/specsmd-flame`
+
+---
+
+## Begin
+
+Activate now. Read the Forge skill and start shaping concepts.

package/flows/ideation/commands/ideation.md

@@ -0,0 +1,51 @@
+---
+description: Ideation Flow - creative idea generation, evaluation, and shaping
+---
+
+# Activate Ideation Flow
+
+**Command**: `/specsmd-ideation`
+
+---
+
+## Activation
+
+You are now the **Ideation Orchestrator** for specsmd.
+
+**IMMEDIATELY** read and adopt the persona from:
+→ `.specsmd/ideation/agents/orchestrator/agent.md`
+
+---
+
+## Critical First Steps
+
+1. **Read Config**: `.specsmd/ideation/memory-bank.yaml`
+2. **Check Sessions**: Look for active sessions in `.specs-ideation/sessions/`
+3. **Route**:
+   - Topic provided → jump to Spark skill
+   - Ideas provided → jump to Flame skill
+   - Concepts provided → jump to Forge skill
+   - Nothing → ask "What would you like to explore ideas about?"
+
+---
+
+## Your Skills
+
+- **Spark**: `.specsmd/ideation/agents/orchestrator/skills/spark/SKILL.md` → Generate ideas
+- **Flame**: `.specsmd/ideation/agents/orchestrator/skills/flame/SKILL.md` → Evaluate ideas
+- **Forge**: `.specsmd/ideation/agents/orchestrator/skills/forge/SKILL.md` → Shape concepts
+
+---
+
+## Shared Protocols
+
+- **Anti-Bias**: `.specsmd/ideation/shared/protocols/anti-bias.md`
+- **Deep Thinking**: `.specsmd/ideation/shared/protocols/deep-thinking.md`
+- **Diverge-Converge**: `.specsmd/ideation/shared/protocols/diverge-converge.md`
+- **Interaction Adaptation**: `.specsmd/ideation/shared/protocols/interaction-adaptation.md`
+
+---
+
+## Begin
+
+Activate now. Read your agent definition and start ideating.

package/flows/ideation/commands/spark.md

@@ -0,0 +1,43 @@
+---
+description: Spark - rapid idea generation with cross-domain diversity
+---
+
+# Activate Spark
+
+**Command**: `/specsmd-spark`
+
+---
+
+## Activation
+
+You are now the **Ideation Orchestrator** in **Spark mode** for specsmd.
+
+**IMMEDIATELY** read and adopt the persona from:
+→ `.specsmd/ideation/agents/orchestrator/agent.md`
+
+Then execute the Spark skill:
+→ `.specsmd/ideation/agents/orchestrator/skills/spark/SKILL.md`
+
+---
+
+## Critical First Steps
+
+1. **Read Config**: `.specsmd/ideation/memory-bank.yaml`
+2. **Read Anti-Bias Protocol**: `.specsmd/ideation/shared/protocols/anti-bias.md`
+3. **Read Deep Thinking Protocol**: `.specsmd/ideation/shared/protocols/deep-thinking.md`
+4. **If topic provided**: Jump straight to generating the first batch
+5. **If no topic**: Ask "What would you like to explore ideas about?" — then generate immediately
+
+---
+
+## Routing Targets
+
+- **Back to Orchestrator**: `/specsmd-ideation`
+- **To Flame**: `/specsmd-flame`
+- **To Forge**: `/specsmd-forge`
+
+---
+
+## Begin
+
+Activate now. Read the Spark skill and start generating ideas.

package/flows/ideation/memory-bank.yaml

@@ -0,0 +1,177 @@
+# Ideation Flow Configuration
+# Spark → Flame → Forge — Creative ideation for AI-native thinkers
+
+# Flow Version
+version: "1.0.0"
+
+# Artifact folder (created at project initialization)
+artifact_root: ".specs-ideation"
+
+# Structure created at project initialization
+structure:
+  - path: sessions/
+    description: "Ideation sessions with spark banks, flame reports, and concept briefs"
+  - path: standards/
+    description: "Project standards (optional, for context-aware ideation)"
+
+# ─────────────────────────────────────────────────────────────────────────────────
+# SESSION MANAGEMENT
+# ─────────────────────────────────────────────────────────────────────────────────
+
+sessions:
+  output_dir: ".specs-ideation/sessions"
+  naming:
+    format: "{topic-slug}-{YYYYMMDD}"
+    example: "ai-onboarding-20260208"
+    note: "Kebab-case topic slug + date"
+
+# ─────────────────────────────────────────────────────────────────────────────────
+# SCHEMA DEFINITION (Source of Truth for Agents)
+# ─────────────────────────────────────────────────────────────────────────────────
+
+schema:
+  # Session Artifacts
+  sessions: ".specs-ideation/sessions/"
+  session_folder: ".specs-ideation/sessions/{session-id}/"
+  session_state: ".specs-ideation/sessions/{session-id}/session.yaml"
+  spark_bank: ".specs-ideation/sessions/{session-id}/spark-bank.md"
+  flame_report: ".specs-ideation/sessions/{session-id}/flame-report.md"
+  concept_briefs: ".specs-ideation/sessions/{session-id}/concept-briefs/"
+  concept_brief: ".specs-ideation/sessions/{session-id}/concept-briefs/{concept-name}.md"
+
+  # Standards (optional)
+  standards: ".specs-ideation/standards/"
+
+# ─────────────────────────────────────────────────────────────────────────────────
+# SESSION STATE (session.yaml)
+# ─────────────────────────────────────────────────────────────────────────────────
+
+session_state:
+  fields:
+    session:
+      - id: "Session identifier (topic-slug-date)"
+      - topic: "The ideation topic"
+      - created: "ISO 8601 timestamp"
+      - updated: "ISO 8601 timestamp"
+      - phase: "spark | flame | forge | complete"
+    spark:
+      - batches_generated: "Number of idea batches generated"
+      - total_ideas: "Total ideas generated"
+      - favorites: "List of favorited idea IDs"
+      - domains_used: "List of domain sectors used"
+      - domains_remaining: "List of domain sectors not yet used"
+      - techniques_used: "List of techniques applied"
+    flame:
+      - ideas_evaluated: "Number of ideas evaluated"
+      - shortlist: "List of shortlisted idea IDs"
+      - scoring_method: "Scoring method used (six-hats, impact-feasibility, etc.)"
+    forge:
+      - concepts_shaped: "Number of concepts shaped"
+      - briefs_generated: "List of concept brief filenames"
+
+# ─────────────────────────────────────────────────────────────────────────────────
+# DATA CONVENTIONS
+# ─────────────────────────────────────────────────────────────────────────────────
+
+conventions:
+  timestamps:
+    format: "ISO 8601 with time and timezone"
+    pattern: "YYYY-MM-DDTHH:MM:SSZ"
+    example: "2026-02-08T10:30:00Z"
+
+naming:
+  sessions:
+    format: "{topic-slug}-{YYYYMMDD}"
+    example: "ai-onboarding-20260208"
+    note: "Kebab-case topic slug + date"
+
+  ideas:
+    format: "S{batch}-{number}"
+    example: "S1-3"
+    note: "Spark batch number + idea number within batch"
+
+  concepts:
+    format: "{concept-name}"
+    example: "gamified-onboarding"
+    note: "Kebab-case concept name"
+
+# ─────────────────────────────────────────────────────────────────────────────────
+# SPARK CONFIGURATION
+# ─────────────────────────────────────────────────────────────────────────────────
+
+spark:
+  batch_size: 5                    # Ideas per batch
+  target_count: 50                 # Min ideas before suggesting convergence
+  max_batches: 20                  # Safety limit
+
+# ─────────────────────────────────────────────────────────────────────────────────
+# DEEP THINKING
+# ─────────────────────────────────────────────────────────────────────────────────
+
+deep_thinking:
+  prefer_mcp: true                 # Use sequential-thinking MCP if available
+  fallback: built-in               # Use built-in protocol if MCP unavailable
+  steps_per_batch: 6               # Reasoning steps per idea batch
+  visibility: collapsed            # visible | collapsed | hidden
+
+# ─────────────────────────────────────────────────────────────────────────────────
+# ANTI-BIAS ENGINE
+# ─────────────────────────────────────────────────────────────────────────────────
+
+anti_bias:
+  domain_diversity_min: 3          # Min different domains per batch of 5
+  provocation_frequency: 15        # Every N ideas, inject a provocation
+  perspective_shift_frequency: 20  # Every N ideas, shift perspective
+  domains:
+    - Technology/Engineering
+    - Human Psychology/Behavior
+    - Business/Economics
+    - Nature/Biology
+    - Art/Design/Aesthetics
+    - Games/Play
+    - Social/Community
+    - Physical Space/Architecture
+    - Time/Temporal
+    - Extreme/Edge Cases
+    - Inversion/Opposite
+    - Random Cross-Pollination
+
+# ─────────────────────────────────────────────────────────────────────────────────
+# FLAME CONFIGURATION
+# ─────────────────────────────────────────────────────────────────────────────────
+
+flame:
+  default_method: six-hats-rapid
+  shortlist_size: 5                # Top ideas to carry forward
+
+# ─────────────────────────────────────────────────────────────────────────────────
+# FORGE CONFIGURATION
+# ─────────────────────────────────────────────────────────────────────────────────
+
+forge:
+  default_method: disney-strategy
+  include_pitch: true
+  include_risks: true
+
+# ─────────────────────────────────────────────────────────────────────────────────
+# INTERACTION ADAPTATION
+# ─────────────────────────────────────────────────────────────────────────────────
+#
+# The technique determines interaction mode — not a user toggle.
+# Phase ratios (generate / elicit / co-build):
+#   Spark:  80% / 5%  / 15%
+#   Flame:  60% / 15% / 25%
+#   Forge:  40% / 20% / 40%
+#
+# Rules:
+#   - Never more than 2 questions in a row before generating something
+#   - "you decide" → more generation
+#   - "ask me" → more elicitation
+#   - Every elicitative technique has an ai_fallback so flow never stalls
+
+# ─────────────────────────────────────────────────────────────────────────────────
+# AGENT OWNERSHIP
+# ─────────────────────────────────────────────────────────────────────────────────
+
+ownership:
+  orchestrator: [sessions, standards]