specsmd 0.0.0-dev.85 → 0.0.0-dev.87

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

@@ -7,38 +7,52 @@
 ## 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
@@ -46,6 +60,7 @@ What if the order were reversed? What if roles swapped? What if inside-out?
 ## 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

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

@@ -14,27 +14,32 @@
 ## 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?
@@ -42,6 +47,7 @@
 ## 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

package/flows/ideation/shared/protocols/anti-bias.md

@@ -24,16 +24,18 @@ The domain wheel has 12 sectors. Every idea must be tagged with its primary doma
 ## Enforcement Rules
 
 ### Per-Batch (5 ideas)
+
 1. **Minimum 3 different domains** per batch — HARD REQUIREMENT
 2. **Never 2 consecutive ideas from the same domain**
 3. **Track domain usage** across the entire session
 4. **Prioritize underused domains** — if a domain has 0 ideas, it should appear in the next 2 batches
 
 ### Per-Session
-5. **After every 15 ideas**: inject 1 provocative idea (see Provocation Types below)
-6. **After every 20 ideas**: shift perspective entirely (different user persona, different era, different culture)
-7. **If user favorites cluster in 1-2 domains**: deliberately diversify the next batch into 4+ domains
-8. **By session end**: aim for 8+ domains covered
+
+1. **After every 15 ideas**: inject 1 provocative idea (see Provocation Types below)
+2. **After every 20 ideas**: shift perspective entirely (different user persona, different era, different culture)
+3. **If user favorites cluster in 1-2 domains**: deliberately diversify the next batch into 4+ domains
+4. **By session end**: aim for 8+ domains covered
 
 ### Domain Tracking Format
 
@@ -58,6 +60,7 @@ Provocations are deliberately absurd or extreme ideas that break fixation patter
 | **Stakeholder swap** | Different user entirely | "Design this for a 5-year-old. Now for a 90-year-old." |
 
 ### Provocation Rules
+
 - Label provocations internally but present them naturally among other ideas
 - If a provocation resonates with the user, develop it into a real idea
 - Provocations should be surprising but contain a kernel of insight

package/flows/ideation/shared/protocols/deep-thinking.md

@@ -29,35 +29,41 @@ Execute the same reasoning chain as an internal process. Think through each step
 ## The 6-Step Reasoning Chain
 
 ### Think 1 — Domain Check
+
 - Review domain usage tracking from session state
 - Which domains are underexplored?
 - Select 3+ target domains for this batch
 - If user expressed preferences, balance between preferred and underexplored
 
 ### Think 2 — Raw Concepts
+
 - Generate 1-2 raw ideas per selected domain
 - Use a technique internally: SCAMPER, analogy, inversion, random-word, what-if, first-principles, or questorming
 - Select technique based on: what hasn't been used recently, what fits the user's energy, what the topic needs
 - Aim for 6-8 raw concepts to select 5 from
 
 ### Think 3 — Novelty Filter
+
 - For each raw concept, ask: "Is this genuinely new or a repackaged version of an obvious idea?"
 - Check against ideas already generated in this session
 - Replace any that feel generic, incremental, or too similar to existing ideas
 - The bar: would this make someone say "huh, I never thought of that"?
 
 ### Think 4 — Cross-pollinate
+
 - If user has stated favorites, can any new ideas combine with them?
 - Look for unexpected connections between the raw concepts themselves
 - Create at least one idea that bridges two different domains
 
 ### Think 5 — Provocation
+
 - Check: is a provocation due? (every 15 ideas)
 - If yes: select a provocation type and generate one deliberately absurd idea
 - If no: ensure at least one idea in the batch challenges a core assumption
 - The provocation should be surprising but contain a genuine insight
 
 ### Think 6 — Polish
+
 - For each of the 5 selected ideas:
   - Make it vivid: use concrete details, not abstractions
   - Make it specific: "a quest system where..." not "gamification"
@@ -65,6 +71,7 @@ Execute the same reasoning chain as an internal process. Think through each step
 - Final anti-bias check: do the 5 ideas span 3+ domains? No 2 consecutive from same domain?
 
 ### Think 7 — Meta-check (Optional)
+
 - Only if something feels off about the batch
 - Is this batch genuinely diverse or are the ideas structurally similar?
 - Does this batch feel different from the previous batch?

package/flows/ideation/shared/protocols/diverge-converge.md

@@ -50,12 +50,14 @@ Mixing them kills creativity. Judging during generation produces safe, increment
 ## The "Deferred Judgment" Contract
 
 During divergent phases, the AI MUST:
+
 - Record every idea, even seemingly bad ones
 - Never add qualifiers like "while this might not be practical..."
 - Never rank or compare ideas within a divergent phase
 - Treat every idea as equally valid until convergence
 
 During convergent phases, the AI MUST:
+
 - Apply consistent evaluation criteria
 - Not generate new ideas (unless explicitly extending)
 - Acknowledge trade-offs rather than seeking a single "best"

package/flows/ideation/shared/protocols/interaction-adaptation.md

@@ -23,6 +23,7 @@ Generation-heavy at start (Spark), increasingly collaborative as ideas become co
 ## Hard Rules
 
 ### The 2-Question Limit
+
 **NEVER more than 2 questions in a row before generating something creative.**
 
 If the AI has asked 2 questions, it MUST generate output next — even if it doesn't have complete information. Use the `ai_fallback` for the technique and generate based on available context.
@@ -39,6 +40,7 @@ If the AI has asked 2 questions, it MUST generate output next — even if it doe
 | (detailed responses, high engagement) | More co-build to leverage engagement |
 
 ### Ratio Tracking
+
 Track the question-to-generation ratio. If it exceeds 1:3 (more than 1 question per 3 generated outputs), shift toward more generation.
 
 ## Technique-Interaction Mapping
@@ -62,19 +64,24 @@ Each technique declares its natural interaction type:
 The AI reads engagement signals and adapts:
 
 ### High Energy Signals
+
 - Long responses, exclamation marks, building on ideas
 - **Response**: Match energy, increase pace, go bolder
 
 ### Medium Energy Signals
+
 - Moderate responses, picking favorites, giving direction
 - **Response**: Steady pace, follow their direction
 
 ### Low Energy Signals
+
 - Short responses ("ok", "sure", "next"), slow replies
 - **Response**: Generate more (don't ask), try a different angle, offer to pause or switch skills
 
 ### Re-energizing Tactics
+
 When energy drops:
+
 1. Switch technique (if SCAMPER isn't landing, try inversion or random-word)
 2. Switch domain (if tech ideas aren't exciting, try nature or games)
 3. Inject a provocation (absurd idea can re-spark interest)