@human-avatar/skills-for-humanity 1.0.0

package/skills/logic-fixer/SKILL.md

@@ -0,0 +1,94 @@
+---
+name: logic-fixer
+description: "Take broken reasoning — a flawed argument, contradictory spec, unsound plan, or invalid inference — diagnose exactly what's wrong, and produce a corrected version. Use when you have reasoning that doesn't hold and you want it fixed, not just critiqued. TRIGGERS: 'fix this reasoning', 'repair this argument', 'this logic is broken, fix it', 'make this argument sound', 'my reasoning is circular, help', any situation where broken reasoning needs to be made valid rather than just flagged. Pairs with logic-argument-validation (which diagnoses) and logic-council (which pressure-tests) — this skill fixes."
+---
+
+# Logic Fixer
+
+Diagnosis without repair is incomplete. This skill takes broken reasoning and produces a corrected version — one where the premises actually support the conclusion, the hidden assumptions are made explicit, the fallacies are removed, and the argument can be defended.
+
+The output is not a critique. It is a fixed version of what you were trying to say.
+
+---
+
+## Your Process
+
+**Step 1: Diagnose before repairing**
+Don't jump to a fix. First, be specific about what's broken:
+- What type of failure is this? (Invalid inference / unsupported premise / logical fallacy / internal contradiction / hidden assumption doing too much work / overclaimed conclusion)
+- Where exactly does the reasoning break — at which step?
+- What is the argument *trying* to establish? (Separate the intent from the execution — the intent might be sound even if the argument isn't.)
+
+**Step 2: Classify the repair needed**
+Different failure modes need different repairs:
+
+| Failure | Repair |
+|---|---|
+| Unsupported premise | Add evidence, or qualify the premise |
+| Overclaimed conclusion | Narrow the conclusion to what the premises actually support |
+| Missing step | Make the implicit inference explicit |
+| Circular reasoning | Identify the begged question; provide independent support for the conclusion |
+| False dichotomy | Reframe to acknowledge the full option space |
+| Invalid inference | Add the bridging premise that makes the inference valid |
+| Equivocation | Disambiguate the term; use different words for different senses |
+| Hidden assumption | Surface it as an explicit premise; assess whether it holds |
+
+**Step 3: Produce the fixed version**
+Rewrite the argument so that:
+- Every premise is stated explicitly
+- Every inference from premise to conclusion is valid
+- The conclusion claims no more than the premises support
+- Fallacies are removed, not just noted
+- Hidden assumptions are surfaced as explicit premises (and labelled as assumptions if they're not established)
+
+**Step 4: Note what changed and why**
+Don't just hand over the fixed version without explanation. For each change:
+- What was wrong
+- What the fix was
+- Whether the fix strengthens or narrows the original claim
+
+If the original conclusion cannot be made to hold under any reasonable repair — because the premises are too weak or the claim is simply unsupported — say so directly rather than producing a version that technically avoids fallacies but doesn't actually establish what the author wanted to establish.
+
+---
+
+## Human Check-in
+
+Before proceeding, ask the user:
+
+**How do you want to run this?**
+
+- **A) Full analysis** — complete all steps, reasoning shown throughout
+- **B) Key findings only** — bottom-line output, skip step-by-step detail
+- **C) Fixed version first** — show the corrected reasoning before explaining what was wrong
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**Original reasoning:**
+[The broken argument, spec, or reasoning as provided]
+
+**Diagnosis**
+| Issue | Location | Type |
+|---|---|---|
+| [what's broken] | [where in the argument] | [failure type] |
+
+**Fixed Version**
+[The corrected argument — written cleanly, as if it were the original. Not a tracked-changes edit, but a finished version.]
+
+**What Changed**
+| Original | Fixed | Why |
+|---|---|---|
+| [original claim/step] | [fixed version] | [reason] |
+
+**Strength Assessment**
+[Is the fixed argument now sound? Does it establish what the original was trying to establish, or did the repairs require narrowing the conclusion? Be honest about this.]
+
+---
+
+## Notes
+
+Sometimes a broken argument can't be fixed because the conclusion isn't supportable — the premises, even repaired, don't get you there. In those cases, the honest output is: "This conclusion cannot be established with the evidence available. Here is what the available evidence *does* support." That is more useful than a technically valid argument for a weaker claim dressed up to look like the original.
+
+The fixer's job is sound reasoning, not salvaging a predetermined conclusion.

package/skills/narrative/SKILL.md

@@ -0,0 +1,78 @@
+---
+name: narrative
+description: "Entry point for the narrative toolkit. Routes to the right narrative skill based on your situation. Use when you say 'narrative', 'story', 'this feels flat', 'how do I structure this', 'the framing is wrong', 'who am I talking to', 'make this compelling', 'find the tension', or want narrative/storytelling help without knowing which specific tool fits."
+---
+
+# Narrative
+
+Applies narrative and storytelling thinking to communication, strategy, and meaning-making. Diagnoses what kind of narrative work is needed and applies the right tool.
+
+## Which tool fits
+
+| You need to... | Tool |
+|---|---|
+| Map the audience's actual beliefs, goals, and fears | audience-modeling |
+| Identify the current frame and generate better alternatives | frame-analysis |
+| Apply story architecture to a proposal or presentation | structure-mapping |
+| Find or create the tension that makes communication worth attending to | tension-mapping |
+
+## Routing Decision
+
+- **Don't know why the audience isn't responding** → audience-modeling
+- **The framing of a situation is wrong or limiting** → frame-analysis
+- **Have content but it's not landing — structure problem** → structure-mapping
+- **Communication is flat, forgettable, or not engaging** → tension-mapping
+- **Unclear** → structure-mapping; most communication problems are structural
+
+## Confirm Direction
+
+After diagnosing which tool fits, present the recommendation before executing:
+
+> My read: **[diagnosed tool]** — one sentence on why it fits.
+
+- **A) Yes, run that tool**
+- **B) Show me all options** — list every skill in this category with one-line descriptions
+- **C) Quick version** — lighter-weight alternative for this situation, if one exists
+- **D) Re-diagnose** — describe the situation differently for a second read
+
+Wait for their selection before proceeding.
+
+---
+
+## Audience Modeling
+
+*Maps the audience's current beliefs, real goals, fears, and threshold conditions.*
+
+What do they already believe about this topic? What do they actually care about — not their job title, but their real goals? What are they afraid of — about the message, the change, the consequences? What would they need to see or hear to act? Build this model before structuring the communication; the best-structured message in the wrong frame for the wrong audience still fails.
+
+**Output:** Audience belief map, real goals, fears, and the minimum conditions for a positive response.
+
+---
+
+## Frame Analysis
+
+*Identifies the current frame and generates alternative frames.*
+
+Every situation is perceived through a frame — a set of implicit assumptions about what kind of thing this is, who the relevant parties are, and what's at stake. Name the current frame explicitly. Now generate 3-5 alternative frames: what if this were a different kind of situation? Each frame makes different elements visible and others invisible. Find the frame that reveals the truth you need people to see.
+
+**Output:** Current frame explicitly stated, 3-5 alternative frames, and the frame that best serves the communication goal with reasoning.
+
+---
+
+## Structure Mapping
+
+*Applies story architecture to any communication.*
+
+Information delivered as data rarely moves people. Information delivered as story does. Apply narrative architecture: (1) Status quo — the world before, (2) Disruption — what changed or needs to change, (3) Stakes — what's at risk if nothing happens, (4) Journey — the path forward, (5) Resolution — the new world this creates. Map the content onto this arc. Cut everything that doesn't move the story forward.
+
+**Output:** Content mapped onto narrative arc, elements to cut, and the structure that moves from status quo to resolution.
+
+---
+
+## Tension Mapping
+
+*Finds or creates the tension that makes communication worth paying attention to.*
+
+Without tension, there is no story. Without story, there is no attention. Tension is the gap between where things are and where they should be — or between what we know and what we need to know. Find the tension already present in this situation: what's at stake? What could go wrong? What is the unresolved question the audience needs answered? If tension is absent, it must be created — not manufactured, but surfaced from what's actually true.
+
+**Output:** The genuine tension in this situation, how to make it visible and felt, and how the communication resolves it.

package/skills/narrative-audience-modeling/SKILL.md

@@ -0,0 +1,65 @@
+---
+name: narrative-audience-modeling
+description: "Maps the audience's current beliefs, real goals, fears, and threshold conditions before communicating with them. Use when asked to 'model the audience', 'audience analysis', 'who am I talking to', 'what do they care about', or 'why aren't they getting it'."
+---
+
+# Narrative Audience Modeling
+
+Communication fails at the receiver, not the sender. The most common communication failure is not poor evidence or unclear logic — it is delivering a message the audience was not ready to receive, about a problem they do not recognize, to a goal they do not hold. Modeling the audience before communicating means identifying not what you want to say, but what they are able to hear.
+
+---
+
+## Your Process
+
+**Step 1: Name Specific People**
+Resist generic categories. Not "senior leadership" but "the CFO and CTO who approved last quarter's roadmap". The more specific the audience, the more useful the model.
+
+**Step 2: Current Belief**
+What do they already think about this topic? Include their current confidence level. This is the starting point — you are moving them from here, not from zero.
+
+**Step 3: Real Goal**
+What do they actually care about — the underlying motivation, not their stated preference? "Wants a decision" often means "wants to not be blamed for a bad outcome". Stated goals are proxies; find the underlying one.
+
+**Step 4: Fear**
+What do they need not to lose? Status, control, consistency with a prior decision, a relationship, a budget. Fear shapes reception more than aspiration does.
+
+**Step 5: What Moves Them — and What Doesn't**
+What evidence, framing, or messenger would change their mind? What definitely will not work, regardless of quality? Understanding the latter saves time.
+
+**Step 6: Threshold Condition**
+What must they hear or believe first, before they can receive anything else? If the threshold is not met, all subsequent communication fails regardless of content.
+
+---
+
+## Human Check-in
+
+Before proceeding, ask the user:
+
+**How do you want to run this?**
+
+- **A) Full analysis** — complete all steps, reasoning shown throughout
+- **B) Key findings only** — bottom-line output, skip step-by-step detail
+- **C) Threshold conditions only** — what would make this audience act or change their view
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**Audience Table**
+
+| Segment | Current Belief | Real Goal | Fear | What Moves Them | Threshold Condition |
+|---------|---------------|----------|------|----------------|---------------------|
+| | | | | | |
+
+**Message Implications**
+- Lead with: [threshold condition]
+- Frame around: [real goal]
+- Avoid: [what won't work]
+- Primary ask: [what they need to do or decide]
+
+---
+
+## Notes
+
+If the threshold condition is not met first, nothing else lands. Sequence matters as much as content. Address the threshold before making your argument.

package/skills/narrative-frame-analysis/SKILL.md

@@ -0,0 +1,66 @@
+---
+name: narrative-frame-analysis
+description: "Identifies the current frame around a situation and generates alternative frames that reveal different truths. Use when asked to 'reframe this', 'the framing is wrong', 'change the narrative', 'different angle', or 'why won't they see it'."
+---
+
+# Narrative Frame Analysis
+
+Frames are invisible until named. The same facts support radically different conclusions depending on who is the protagonist, what counts as the problem, and what counts as success. Most communication failures are framing failures — not evidence failures. Reframing does not change the facts; it changes which facts are salient and which conclusions they support.
+
+---
+
+## Your Process
+
+**Step 1: Name the Current Frame**
+Make the implicit explicit. Who is the protagonist in the current frame? What is the problem being solved? What counts as a successful outcome? What is the frame's implicit villain or antagonist?
+
+**Step 2: Identify What the Current Frame Hides**
+Every frame foregrounds some things and backgrounds others. What does the current frame make invisible, irrelevant, or unthinkable? Who loses standing in this frame? What solutions become impossible to see?
+
+**Step 3: Generate 3–4 Alternative Frames**
+For each alternative, change at least one of: protagonist, problem definition, success criteria, or time horizon. Assign each alternative a short name.
+
+**Step 4: Assess Each Alternative**
+What does each alternative frame reveal that the current frame hides? Who gains standing? What solutions become visible? What previously central concerns become peripheral?
+
+**Step 5: Select the Most Useful Frame**
+The best frame is not the most flattering — it is the one that most accurately surfaces what matters and opens the most productive path forward. State the rationale.
+
+---
+
+## Human Check-in
+
+Before proceeding, ask the user:
+
+**How do you want to run this?**
+
+- **A) Full analysis** — complete all steps, reasoning shown throughout
+- **B) Key findings only** — bottom-line output, skip step-by-step detail
+- **C) Reframe options only** — alternative frames, skip analysis of the current frame
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**Current Frame**
+- Protagonist: [who]
+- Problem: [what]
+- Success: [what counts]
+- What it hides: [what becomes invisible]
+
+**Alternative Frames**
+
+| Frame Name | Protagonist | Problem Definition | Success Criteria | What It Reveals |
+|-----------|-------------|-------------------|-----------------|----------------|
+| | | | | |
+
+**Recommended Frame:** [name] — [rationale in 2 sentences]
+
+**Message Implications:** [how communication changes under the recommended frame]
+
+---
+
+## Notes
+
+Reframing surfaces different truths, not false ones. If an alternative frame requires ignoring real evidence, it is spin — a useful frame must be defensible against the facts.

package/skills/narrative-structure-mapping/SKILL.md

@@ -0,0 +1,70 @@
+---
+name: narrative-structure-mapping
+description: "Applies story architecture to any communication — proposal, presentation, strategy doc — so it moves people rather than informing them. Use when asked to 'structure this as a story', 'make this compelling', 'narrative arc', 'how do I present this', or 'story structure'."
+---
+
+# Narrative Structure Mapping
+
+Facts don't change behavior; narrative does. The same information delivered as a story is more persuasive, more memorable, and more likely to produce action than the same information delivered as a report. Three-act structure works because it mirrors how humans process change: there is a world, the world is disrupted, a new world becomes possible. Any communication that needs to move people — not just inform them — benefits from this architecture.
+
+---
+
+## Your Process
+
+**Step 1: Identify Audience and Current Belief**
+Who is the specific audience? What do they already believe about this situation? You are not starting from zero — you are moving them from where they are.
+
+**Step 2: Find the Tension**
+What is the gap between current state and desired state? If there is no tension, there is no story. The tension must be real to the audience, not just to the sender.
+
+**Step 3: Map Three-Act Structure**
+- **Act 1 — Setup:** The world as it is. Establish the context the audience already inhabits. Then: the disruption — something has changed, is at risk, or is being missed.
+- **Act 2 — Confrontation:** The struggle. What makes resolution non-obvious? What are the stakes if the problem isn't addressed? This is where complexity lives.
+- **Act 3 — Resolution:** The new world. What becomes possible if the audience acts or accepts the argument? Make it concrete.
+
+**Step 4: Locate the Transformation**
+What must the audience feel or understand at the turning point that makes the resolution feel earned rather than asserted? This is the moment of insight — the structural heart of the communication.
+
+**Step 5: Place Evidence Inside the Story**
+Data supports narrative; it does not replace it. Assign each data point or proof element to its place in the arc — evidence that arrives before the audience is ready to receive it doesn't land.
+
+---
+
+## Human Check-in
+
+Before proceeding, ask the user:
+
+**How do you want to run this?**
+
+- **A) Full analysis** — complete all steps, reasoning shown throughout
+- **B) Key findings only** — bottom-line output, skip step-by-step detail
+- **C) Missing elements only** — what story components are absent from this communication
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**Audience:** [who + current belief]
+
+**Tension:** [current state → desired state → gap]
+
+**Narrative Outline**
+
+| Section | Content | Function |
+|---------|---------|---------|
+| Hook | | Opens with tension, not context |
+| Setup | | World as audience knows it |
+| Disruption | | What has changed or is at risk |
+| Confrontation | | Stakes and complexity |
+| Turning Point | | The insight that makes resolution possible |
+| Resolution | | The new world; what becomes possible |
+| Call to Action | | Specific ask |
+
+**Where Data Fits:** [data point → narrative position]
+
+---
+
+## Notes
+
+The most common failure is leading with resolution — announcing the answer before the audience has felt the tension. Make them need the answer before you give it.

package/skills/narrative-tension-mapping/SKILL.md

@@ -0,0 +1,62 @@
+---
+name: narrative-tension-mapping
+description: "Finds or creates the tension that makes communication worth paying attention to. Use when asked 'this feels flat', 'no one's engaging', 'make this compelling', 'find the tension', 'what's the story here', or 'add stakes'."
+---
+
+# Narrative Tension Mapping
+
+Without a gap between current state and desired state, communication is noise. Tension is not drama or manufactured urgency — it is the honest articulation of what is wrong, at risk, or missing. Audiences disengage not because a topic is unimportant but because the communication fails to make the gap visible and real. The tension must be felt before the solution can land.
+
+---
+
+## Your Process
+
+**Step 1: State the Communication**
+What is the communication — its subject, its argument, its ask? State it plainly before analyzing what's missing.
+
+**Step 2: Locate the Tension**
+Ask: what is wrong, at risk, or missing in the world this communication addresses? That is the tension. It should be a gap between where things are and where they need to be. If you can't find it, note that — it's diagnostic.
+
+**Step 3: Test for Genuine Tension**
+If no tension is apparent: ask why this communication matters at all. If the honest answer is "it doesn't," that is the real problem to solve — the communication should not exist yet or should be restructured around something that does matter.
+
+**Step 4: Test for Audience Relevance**
+Is this tension real to the audience, or only to the sender? A tension that only the sender feels is not yet a tension — it requires first making the audience care about the domain before the gap can register.
+
+**Step 5: Surface It Plainly**
+State the tension explicitly, early, without burying it in qualifications. The single most common failure: putting the tension in the middle or end after extensive context-setting. Audiences stop paying attention before they reach it.
+
+---
+
+## Human Check-in
+
+Before proceeding, ask the user:
+
+**How do you want to run this?**
+
+- **A) Full analysis** — complete all steps, reasoning shown throughout
+- **B) Key findings only** — bottom-line output, skip step-by-step detail
+- **C) Central tension only** — the one conflict that makes this worth attending to
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**Tension Statement**
+- Current state: [what is true now]
+- Desired state: [what needs to be true]
+- Gap: [what separates them]
+- Stakes: [what happens if the gap persists]
+
+**Audience Relevance:** [real to audience? Y/N + explanation]
+
+**Opening Line:** [how to open with the tension, not context]
+
+**Diagnosis (if no tension found):** [what the absence of tension means for the communication]
+
+---
+
+## Notes
+
+Tension is not negativity. Stating what is at risk is not pessimistic — it is the precondition for the audience to care about your resolution. A solution without a stated problem is just noise.

package/skills/play/SKILL.md

@@ -0,0 +1,80 @@
+---
+name: play
+description: "Entry point for the play toolkit. Routes to the right playful thinking skill based on your situation. Use when you say 'play', 'think playfully', 'flip this', 'what if there were no constraints', 'steelman the opposition', 'random stimulus', 'worst possible idea', or want unconventional thinking applied without knowing which specific tool fits."
+---
+
+# Play
+
+Applies playful, unconventional thinking to break fixed patterns and generate unexpected possibilities. Play isn't frivolous — it's a serious tool for accessing ideas that conventional thinking misses.
+
+## Which tool fits
+
+| You need to... | Tool |
+|---|---|
+| Remove or invert the main constraint to see what becomes possible | constraint-inversion |
+| Fully inhabit the opposing perspective to find what you're missing | perspective-reversal |
+| Introduce a random, unrelated element to break mental fixation | stimulus-generation |
+| Design the worst possible version, then reverse it | worst-case-reversal |
+
+## Routing Decision
+
+- **Constraint feels like the ceiling on all thinking** → constraint-inversion
+- **Missing what the other side sees — competitor, critic, user** → perspective-reversal
+- **Stuck in the same circles, need a jolt from outside** → stimulus-generation
+- **Polite brainstorming keeps producing safe ideas** → worst-case-reversal
+- **Unclear** → perspective-reversal; inhabiting another view unblocks most stuck situations
+
+---
+
+## Confirm Direction
+
+After diagnosing which tool fits, present the recommendation before executing:
+
+> My read: **[diagnosed tool]** — one sentence on why it fits.
+
+- **A) Yes, run that tool**
+- **B) Show me all options** — list every skill in this category with one-line descriptions
+- **C) Quick version** — lighter-weight alternative for this situation, if one exists
+- **D) Re-diagnose** — describe the situation differently for a second read
+
+Wait for their selection before proceeding.
+
+---
+
+## Constraint Inversion
+
+*Removes or inverts the main constraint to see what becomes possible.*
+
+State the primary constraint explicitly. Now remove it: what would you do if this limit didn't exist? Generate freely in the unconstrained space — don't evaluate, just explore. Now: for each unconstrained idea, ask what version of it could work within the real constraint? Often the unconstrained idea reveals a direction that a constrained version of it can actually reach.
+
+**Output:** Unconstrained ideas generated without the limit, and constrained versions of the most promising ones that respect the actual boundary.
+
+---
+
+## Perspective Reversal
+
+*Fully inhabits the opposing perspective to find what is invisible from your own position.*
+
+Choose the opposing perspective: competitor, critic, user, regulator, skeptic, adversary. Step into it completely — not to dismiss it, but to genuinely reason from within it. What do they see that you don't? What are their legitimate points? What would they say is wrong with your approach? What would they do instead? The opposing perspective almost always contains information your own position is structurally unable to see.
+
+**Output:** The opposing position stated from the inside, what it reveals that was invisible from the original position, and which legitimate points deserve a genuine response.
+
+---
+
+## Stimulus Generation
+
+*Introduces a random, unrelated element to break mental fixation.*
+
+Select a random word, object, or image — something genuinely unrelated to the problem (a random dictionary word, an object in the room, a Wikipedia random article). Now force connections: what does this word/object make you think of? How could that connect to the challenge? Generate without filtering — absurd connections are expected and valuable. The randomness is the point; it bypasses the grooves of familiar thinking.
+
+**Output:** Random stimulus used, forced connections generated without filtering, and the 1-2 connections worth developing seriously.
+
+---
+
+## Worst-Case Reversal
+
+*Deliberately designs the worst possible version, then reverses each failure mode into a design principle.*
+
+Ask: how would you deliberately make this as bad as possible? What would guarantee failure, frustration, or harm? Generate the worst possible version without restraint — this removes the pressure of being right and unlocks creative honesty that polite brainstorming suppresses. Now reverse each failure mode: if X makes it terrible, then NOT-X is a design principle. The worst version is often the clearest map to the best version.
+
+**Output:** The worst possible version described vividly, each failure mode listed, and the design principles generated by reversing each one.

package/skills/play-constraint-inversion/SKILL.md

@@ -0,0 +1,97 @@
+---
+name: play-constraint-inversion
+description: "Removes or inverts the main constraint to see what becomes possible — then uses those unconstrained solutions to find real ones. TRIGGERS: 'what if there were no constraints', 'rule inversion', 'what if we could do anything', 'break the rules', 'invert the assumption'."
+---
+
+# Play: Constraint Inversion
+
+Most constraints are treated as fixed when they are actually assumed. The ones that
+are genuinely fixed are fewer than people believe — and the ones that are assumed
+become invisible over time because they've been treated as given for so long.
+Inverting a constraint — imagining its complete opposite — reveals what underlying
+goal it has been blocking and often generates solutions that work within the real
+constraint once the goal becomes visible.
+
+---
+
+## Your Process
+
+**Step 1: Name the Main Constraint**
+What is the primary constraint on the current problem or design? Be specific — not
+"we don't have enough resources" but "we have 6 weeks and two engineers available
+after existing commitments." Not "the budget is limited" but "the approved budget
+is $40k with no variance mechanism." Specificity matters because vague constraints
+produce vague inversions.
+
+**Step 2: Invert Completely**
+State the opposite world. Don't soften or partially invert — flip it completely.
+"6 weeks and two engineers" becomes "18 months and a team of twelve." "Budget of
+$40k" becomes "unlimited funding with board approval." The inversion should feel
+unrealistic. That is the design — if it feels achievable, it isn't inverted enough.
+
+**Step 3: Generate Freely in the Inverted World**
+What would you do if the constraint were fully removed? Generate without filtering.
+No "but we can't" or "in reality though" — those are prohibited at this stage. Aim
+for 3-5 substantially different unconstrained approaches.
+
+**Step 4: Find the Underlying Goal of Each**
+For each unconstrained solution: strip away the specifics and name the underlying
+goal it's pursuing. What is it actually trying to accomplish? This step converts
+"hire a team of specialists" into "access deep expertise quickly." The goal is more
+transferable than the method.
+
+**Step 5: Reintroduce Real Constraints**
+For each identified goal: is there a way to pursue this goal within the real
+constraints? Sometimes yes — the unconstrained version was solving the right problem
+in an impossible way, and a constrained version exists. Sometimes no — the goal is
+genuinely blocked by the constraint. Both are real findings.
+
+**Step 6: Map Real vs Assumed Constraints**
+The gap between constrained and unconstrained versions shows where each constraint
+is doing real work versus assumed work. A constraint does real work when it genuinely
+prevents a goal. It does assumed work when the goal is achievable within it — just
+not obviously. Assumed constraints are the most valuable finding.
+
+---
+
+## Human Check-in
+
+Before proceeding, ask the user:
+
+**How do you want to run this?**
+
+- **A) Full analysis** — complete all steps, reasoning shown throughout
+- **B) Key findings only** — bottom-line output, skip step-by-step detail
+- **C) One inversion only** — the strongest constraint removal and what it makes possible
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**Constraint:** [the specific, concrete real constraint]
+
+**Inverted World:** [the fully opposite assumption — stated without softening]
+
+**Unconstrained Solutions**
+
+| Solution | Underlying Goal |
+|---|---|
+| [what you'd do with no constraint] | [what it's actually trying to achieve] |
+
+**Constrained Versions:** For each goal — does a within-constraint version exist?
+If yes, describe it.
+
+**Real vs Assumed Constraints**
+- Constraints doing real work (goal genuinely blocked): [list + explanation]
+- Constraints doing assumed work (goal achievable within): [list — highest-value findings]
+
+---
+
+## Notes
+
+The most productive output is usually not the unconstrained solutions themselves but
+the underlying goals they expose — goals that were invisible while the constraint
+was accepted as fixed. Those goals are the real design brief. Once visible, they
+often turn out to be achievable within the actual constraints through routes that
+the constrained framing had ruled out prematurely.