@human-avatar/skills-for-humanity 1.0.0

package/skills/constraint-workaround-mapping/SKILL.md

@@ -0,0 +1,88 @@
+---
+name: constraint-workaround-mapping
+description: "Finds paths around a fixed constraint without removing it — routing around a hard limit to reach the same goal. Triggers: 'work around this', 'given this constraint', 'path around the blocker', 'how do we do this anyway', 'constrained solution'."
+---
+
+# Constraint Workaround Mapping
+
+Some constraints are real and cannot be inverted or removed. The question then is not how
+to eliminate the constraint, but how to route around it to the same destination. A workaround
+is not a compromise — it is a valid path that respects a real limit while still delivering
+the outcome.
+
+---
+
+## Your Process
+
+**Step 1: State the Constraint and Confirm It's Hard**
+Write the constraint. Then confirm: is this actually fixed? A truly hard constraint has a
+concrete source — law, technical impossibility, signed contract. If the source is unclear,
+use constraint-hardness-testing first.
+
+**Step 2: Map the Exact Boundary**
+What does this constraint specifically prevent? What does it explicitly not prevent? Most
+constraints are narrower than they appear. Mapping the boundary precisely reveals the space
+around it.
+
+**Step 3: List All Paths Blocked**
+Enumerate every approach to the goal that the constraint forecloses. Be thorough — you are
+building a map of what's off the table.
+
+**Step 4: Find Adjacent Paths**
+For each blocked path: is there an adjacent path that reaches the same goal without crossing
+the constraint? Adjacent means achieving the same underlying outcome through a different
+mechanism — not a lesser outcome through the same mechanism.
+
+**Step 5: Generate 3-5 Workarounds with Cost**
+For each viable adjacent path, state the cost relative to the direct approach: additional
+time, complexity, dependency, quality reduction, or reversibility loss.
+
+**Step 6: Select Best Cost/Benefit**
+Choose the workaround where the cost is lowest relative to the outcome achieved. If all
+workarounds are too costly, the right answer may be to re-examine the goal.
+
+---
+
+## 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) Two best workarounds only** — highest-feasibility paths around the constraint
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**Constraint:**
+> [Statement + source confirming it's hard]
+
+**Constraint boundary:**
+- Blocks: [what it prevents]
+- Does not block: [what remains available]
+
+**Blocked paths:**
+> [Bulleted list]
+
+**Workarounds:**
+
+| # | Path | How it reaches the goal | Cost vs direct path |
+|---|------|------------------------|---------------------|
+| 1 | | | |
+| 2 | | | |
+| 3 | | | |
+
+**Recommended path:**
+> [Workaround name] — [rationale for cost/benefit selection]
+
+---
+
+## Notes
+
+The map is only useful if the constraint boundary in Step 2 is drawn accurately. People
+regularly assume constraints block more than they do — which is why checking what a
+constraint does NOT prevent is as important as what it does.

package/skills/creativity/SKILL.md

@@ -0,0 +1,173 @@
+---
+name: creativity
+description: "Entry point for the creativity toolkit. Routes to the right creative thinking technique based on your situation. Use when you say 'creativity', 'think creatively', 'I need fresh ideas', 'help me think differently', 'I'm stuck', or want creative help without knowing which specific tool applies. For comprehensive multi-method sessions, this runs them in sequence."
+---
+
+# Creativity
+
+Applies creative thinking to any challenge. Diagnoses what kind of creative work is needed and either runs the right individual tool or sequences multiple tools for comprehensive exploration.
+
+## Which tool fits
+
+| You need to... | Tool |
+|---|---|
+| Question whether the problem itself is framed correctly | assumption-excavator |
+| Escape a dominant idea you keep returning to | lateral-thinking |
+| See all options before choosing any | alternatives / concept-fan |
+| Evaluate a specific idea fairly, without snap judgment | plus-minus-interesting |
+| Think through something from multiple perspectives | six-hats |
+| Think from other people's actual positions | other-perspectives |
+| Explore without premature judgment | water-logic |
+| Break fixation with a random jolt | random-entry |
+| Use an absurd premise as a springboard | provocation |
+| Consider all factors before deciding | consider-factors |
+| Comprehensive multi-method session | run the full sequence below |
+
+## Routing Decision
+
+- **Problem framing might itself be wrong** → assumption-excavator (run before anything else)
+- **Stuck in one direction, keep returning to the same idea** → lateral-thinking
+- **Need to see the full option space before choosing** → alternatives or concept-fan
+- **Have a specific idea to evaluate** → plus-minus-interesting
+- **Need full multi-perspective analysis** → six-hats
+- **Decision affects other people** → other-perspectives
+- **Early exploration, premature judgment is the enemy** → water-logic
+- **Thoroughly stuck, need outside stimulus** → random-entry
+- **Need a deliberate jolt into the impossible** → provocation
+- **About to act, want to make sure nothing is missed** → consider-factors
+- **Big challenge, want everything applied** → run the full brainstorm sequence
+
+---
+
+## 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.
+
+---
+
+## Assumption Excavator
+
+*Surfaces and challenges hidden assumptions.*
+
+List every assumption embedded in the current problem framing — about what's possible, what's wanted, what's fixed, who's involved. Challenge each: what if this assumption were false? Which assumptions are load-bearing (the problem disappears without them) vs. incidental? Find the assumption that, if wrong, would most change the approach.
+
+**Output:** Full assumption inventory, classified by how hard they are to question, and the one reframe that most changes the problem.
+
+---
+
+## Lateral Thinking
+
+*Escapes dominant patterns to generate genuinely new directions.*
+
+Name the dominant idea — the direction that keeps surfacing. Suspend it deliberately: set it aside for the rest of this exercise. From that cleared space, generate 5+ directions that don't involve the dominant idea at all. Use movement thinking: don't evaluate, just move. After generating: which of these new directions, or which combination, deserves serious attention?
+
+**Output:** Dominant idea named and set aside. 5+ genuinely different directions. The 1-2 that deserve development.
+
+---
+
+## Alternatives (APC)
+
+*Deliberately generates options before evaluating any.*
+
+Apply Alternatives, Possibilities, Choices: set a quota — find at least 5 alternatives to the current approach before evaluating any of them. Prevent evaluation from entering the generation phase. After generating: now compare. The first idea is almost never the best, but it crowds out better alternatives when evaluation starts too early.
+
+**Output:** 5+ alternatives generated without judgment, then a brief comparative assessment.
+
+---
+
+## Concept Fan
+
+*Expands the solution space at different levels of abstraction.*
+
+Define the immediate solution being considered. Step back one level: what concept does it serve? Now generate multiple ways to serve that concept. Step back again: what broader purpose does the concept serve? Generate multiple concepts that could serve the purpose. This creates a fan of options from specific tactics to strategic alternatives.
+
+**Output:** Three levels — immediate solutions, serving concepts, and underlying purposes — each with multiple options.
+
+---
+
+## Plus/Minus/Interesting (PMI)
+
+*Evaluates an idea fairly before accepting or rejecting it.*
+
+Apply Plus/Minus/Interesting to the idea: (1) Plus — what is genuinely good about it, including non-obvious positives? (2) Minus — what is genuinely problematic, including non-obvious negatives? (3) Interesting — what is noteworthy regardless of good or bad, and what questions does it open? PMI is the antidote to snap judgment.
+
+**Output:** PMI table. Final assessment: does the plus outweigh the minus, accounting for what's interesting?
+
+---
+
+## Six Hats
+
+*Structured parallel thinking from six distinct angles.*
+
+Apply each hat in sequence: (1) White — facts and data only, (2) Red — emotional and intuitive response, (3) Black — risks, problems, and critical analysis, (4) Yellow — optimism and genuine benefits, (5) Green — creative alternatives and new possibilities, (6) Blue — process, what thinking is needed. Each hat is pure — no mixing.
+
+**Output:** Six-section analysis, one per hat. Final view: what does the full picture show when all hats are held together?
+
+---
+
+## Other Perspectives (OPS)
+
+*Genuinely thinks from other people's positions.*
+
+Identify the key people affected by or involved in this situation. For each person: what is their actual goal? What do they see as the problem? What are they worried about? What would a good outcome look like from their position? OPS is structured empathy — not sympathy, but actually reasoning from within someone else's constraints and goals.
+
+**Output:** Per-person analysis. Synthesis: what does thinking from all these positions reveal that your own position missed?
+
+---
+
+## Water Logic
+
+*Explores without premature judgment.*
+
+Enter flow mode: follow where ideas lead without asking "is this right?" Water logic doesn't judge, it maps. Start with the situation and ask: what does this lead to? Where does it flow naturally? What does it connect to? Build the territory before deciding what matters. Rock logic asks "is this true?"; water logic asks "where does this go?"
+
+**Output:** A map of where the situation flows — connections, directions, and possibilities — before any evaluation.
+
+---
+
+## Random Entry
+
+*Uses an unrelated stimulus to break cognitive ruts.*
+
+Select a random word or object (or have one provided). Apply it to the problem: what does this word make you think of? How does that relate to the challenge? Force connections, even absurd ones — absurd connections are the point. The randomness bypasses the grooves of familiar thinking.
+
+**Output:** Random word used, forced connections generated, and the 1-2 connections worth pursuing.
+
+---
+
+## Provocation (Po)
+
+*Uses an impossible or absurd statement as a springboard.*
+
+State a deliberate provocation — something obviously wrong or impossible: "Po: [impossible premise]." Don't evaluate the provocation. Instead: what does the world look like if this were true? What would we do? Now: which of those ideas could work in the real world? The provocation is scaffolding, not a destination.
+
+**Output:** The provocation stated, the ideas it generates from, and the real-world ideas those lead to.
+
+---
+
+## Consider All Factors (CAF)
+
+*Maps every relevant factor before acting.*
+
+List every factor that could affect the outcome: stakeholders, risks, resources, timing, dependencies, second-order effects. CAF is a pre-flight checklist — it doesn't evaluate, it inventories. After listing: which factors were you about to ignore? Which are more important than they appeared?
+
+**Output:** Full factor inventory. Factors most likely to be overlooked. Factors that most change the approach.
+
+---
+
+## Full Brainstorm Sequence
+
+*Orchestrated multi-method session for complex challenges.*
+
+For big challenges, sequence the tools: (1) Assumption-excavator to clear the framing, (2) Lateral thinking to escape the dominant idea, (3) Concept fan or alternatives to expand the option space, (4) Six hats or PMI to evaluate the best directions, (5) Consider-factors to catch what was missed. Between tools, make the connection explicit — each one builds on the previous.
+
+Close with synthesis: what do the tools, taken together, reveal that no single tool showed on its own? What is the single most important direction? What is the concrete next step?

package/skills/creativity-alternatives/SKILL.md

@@ -0,0 +1,84 @@
+---
+name: creativity-alternatives
+description: "Apply Edward de Bono's APC (Alternatives, Possibilities, Choices) tool to deliberately generate options before evaluating any of them. Use when the user is about to make a decision, wants more options before choosing, feels like they only see two paths, is planning something and wants to make sure they've considered all the approaches, or tends to go with the first good idea."
+---
+
+You are facilitating an APC (Alternatives, Possibilities, Choices) session using Edward de Bono's CoRT thinking tools. APC is a discipline for deliberate option generation — it creates a firewall between generating and evaluating, so judgment doesn't kill ideas before they've been considered.
+
+## Why APC matters
+
+The natural thinking pattern is: encounter a situation → think of a solution → evaluate it → if good, use it. The problem is that evaluation starts too early. The first adequate solution tends to terminate the search. We don't look for better options because we've already found a good one.
+
+APC forces a different sequence: generate all options first, evaluate nothing, then choose. The discipline is in the separation. Evaluation is suspended entirely until the generation phase is complete.
+
+## The three registers
+
+**Alternatives** — Different ways of doing something that is already being done. Not improvements to the current approach, but genuinely different approaches that achieve the same end.
+
+**Possibilities** — Things that might work even if they're uncertain, unconventional, or untested. Not committed options, just things worth putting on the table.
+
+**Choices** — The full range of things that *could* be decided at this moment, including doing nothing, doing the opposite, partial approaches, and combinations.
+
+These registers overlap — don't worry about which category something falls into. The categories are prompts to generate, not bins to sort into.
+
+## Your process
+
+**Step 1: Establish the decision or situation**
+What is the user trying to decide or do? State it clearly.
+
+**Step 2: Generate without evaluating**
+Work through all three registers systematically. For each option generated:
+- State it clearly
+- Do not evaluate it
+- Do not rank it
+- Do not express preference
+
+If an option seems obviously bad, include it anyway. The goal is coverage, not quality filtering. Weak options sometimes contain the seed of a strong one.
+
+Aim for a minimum of 10 options total across all three registers before moving to evaluation.
+
+**Step 3: Expand the list**
+After the first pass, push further. Ask: "What haven't I considered yet?" Look for:
+- The option that requires changing a fundamental assumption
+- The option that inverts the approach entirely
+- The option that does nothing (inaction is always a choice)
+- The option that combines two things on the list
+
+**Step 4: Now evaluate**
+Only after the full list is complete, evaluate. For each option: briefly note what makes it viable or not. Keep evaluations short — this is not the time for deep analysis, just a first filter.
+
+**Step 5: Highlight the options worth developing**
+Identify 2–4 options that deserve further thinking. These may not be the most obvious — look for the options that were surprising, that opened new thinking, or that address the situation in a fundamentally different way.
+
+## 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) Generation only** — produce the alternatives without the comparison or evaluation phase
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output format
+
+**Situation:** [What is being decided or planned]
+
+**Options — Alternatives, Possibilities, Choices:**
+[Numbered list of all generated options, no evaluation, minimum 10]
+
+**Expanded options:**
+[Any additional options found by pushing further]
+
+**First-pass evaluation:**
+[Brief notes on viability for each — keep it fast]
+
+**Worth developing:**
+[2–4 options with brief reasoning on why they deserve more attention]
+
+## The discipline
+
+The hardest part of APC is not generating options — it's suspending evaluation while generating. The moment an option is generated and judged inadequate, the mind stops there. Maintain the suspension. An option that "obviously won't work" may reveal something important when examined alongside others. Complete the list first. Always.

package/skills/creativity-assumption-excavator/SKILL.md

@@ -0,0 +1,95 @@
+---
+name: creativity-assumption-excavator
+description: "Surface and challenge the hidden assumptions in any problem, plan, or framing. Use when the user feels stuck despite trying multiple approaches, a problem seems intractable, a plan keeps failing for unclear reasons, something 'obvious' keeps producing unexpected results, or before using any other creative thinking tool when the problem itself might be wrongly framed. This is the prerequisite skill — run it when the ground itself might be wrong."
+---
+
+You are facilitating an assumption excavation. This is a meta-tool — it operates on the framing of a problem before any other thinking is applied. It is most valuable when other approaches haven't worked, because the reason they failed is often that the problem was wrongly defined.
+
+## Why assumptions matter
+
+Every problem framing rests on assumptions — things taken for granted that organize how we think about the situation. These assumptions are usually invisible precisely because they're foundational. We don't notice them any more than we notice the floor we're standing on.
+
+When a problem resists solution, the assumption underneath it is often the real issue. The effort goes into solving a problem that is defined in a way that makes it unsolvable — because a core assumption is wrong, incomplete, or outdated.
+
+Assumption excavation makes the invisible visible. Once an assumption is named, it can be questioned, inverted, relaxed, or replaced. This often opens directions that were structurally blocked before.
+
+## Three layers of assumptions
+
+Assumptions operate at different depths. Shallow assumptions are easy to spot. Deep assumptions are harder — they feel like facts.
+
+**Surface assumptions** — explicit constraints in the problem framing. These are usually visible: "we need to do this by Friday," "the budget is fixed," "it has to work for these users." They can be questioned, but they're already named.
+
+**Structural assumptions** — the framing itself. These are invisible: assumptions about what the problem *is*, who is responsible for solving it, what a solution would look like, what resources are available or unavailable, what the relevant domain is. Structural assumptions organize the whole inquiry and are rarely examined.
+
+**Identity assumptions** — assumptions about the solver. Who is doing this thinking, and why? What role are they in? What are they trying to protect? What would success mean for them personally? These assumptions shape which solutions feel acceptable and which feel threatening.
+
+## Your process
+
+**Step 1: Restate the problem as framed**
+Write out the user's problem as they've stated it, in their language. This is the surface to excavate.
+
+**Step 2: Surface assumptions at each layer**
+
+Work through all three layers. For each assumption you find:
+- State it explicitly as a claim: "This framing assumes that..."
+- Note which layer it's at
+- Note how load-bearing it is — what would change if this assumption were wrong?
+
+Generate at least 3 assumptions at each layer. The structural and identity layers typically require more probing.
+
+**Step 3: Challenge the most load-bearing assumptions**
+For the 3–5 assumptions that most constrain the solution space, ask:
+- Is this assumption actually true, or just taken for granted?
+- What if the opposite were true?
+- What if this assumption only applies some of the time?
+- Where did this assumption come from — is the source still valid?
+
+**Step 4: Generate lateral moves from dropped assumptions**
+For each challenged assumption, what becomes possible when it is relaxed or inverted? This connects to the lateral thinking primitive — each dropped assumption is a potential departure point.
+
+Name 1–2 new directions that open up when each key assumption is questioned.
+
+## 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) Load-bearing assumptions only** — the ones that most change the problem if they turn out to be wrong
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output format
+
+**Problem as framed:** [restated in user's language]
+
+**Surface assumptions:**
+- This framing assumes: [assumption] *(load-bearing: low/medium/high)*
+- ...
+
+**Structural assumptions:**
+- This framing assumes: [assumption] *(load-bearing: high)*
+- ...
+
+**Identity assumptions:**
+- This framing assumes: [assumption about the solver]
+- ...
+
+**Challenging the key assumptions:**
+
+*Assumption: [most load-bearing assumption]*
+- Is it actually true? [assessment]
+- What if it weren't? [implications]
+- What opens up: [new directions]
+
+*(repeat for 2–4 more)*
+
+**Reframings worth exploring:**
+[2–3 ways to restate the problem that become available once key assumptions are dropped]
+
+## The insight this tool exists to deliver
+
+Most intractable problems are intractable because of the frame, not the content. When smart people keep failing at a problem, the usual explanation is not insufficient intelligence — it's that everyone is working within an assumption that makes the problem unsolvable. The assumption excavator's job is to find that assumption and name it. Once named, it can be changed.

package/skills/creativity-brainstorm/SKILL.md

@@ -0,0 +1,102 @@
+---
+name: creativity-brainstorm
+description: "Run an orchestrated multi-method creative thinking sprint on a challenge. Use when the user wants to make real progress on a hard problem, says 'I need to think through this properly', wants a thorough creative exploration rather than a single technique, has a big decision or challenge and wants the full toolkit applied, or just says 'help me think through this'. This is the entry point for serious creative work — it selects and sequences the right tools automatically."
+---
+
+You are running an orchestrated creative thinking session. Rather than applying a single tool, this session selects and sequences the most appropriate thinking methods for the user's specific situation, then synthesizes across their outputs.
+
+## How to read the situation
+
+Before selecting methods, diagnose what kind of thinking challenge this is:
+
+**Is the problem itself unclear or stuck?**
+→ Start with `assumption-excavator`. The problem framing may be what's blocking progress, not the problem itself.
+
+**Is the user locked into one approach?**
+→ Start with `lateral-thinking`. The dominant idea needs to be named and escaped before other tools are useful.
+
+**Is it early-stage exploration?**
+→ Start with `water-logic` or `random-entry`. Generate movement and map the territory before applying structured tools.
+
+**Does the user need to see the full solution space?**
+→ Use `concept-fan` or `apc`. Expand options systematically before evaluating any of them.
+
+**Does the user need to evaluate something?**
+→ Use `cort-pmi` (for a specific idea) or `six-hats` (for a full multi-perspective analysis).
+
+**Are people and their reactions central?**
+→ Include `cort-ops` to map the perspectives of those affected.
+
+**Does the situation need a provocation to break it open?**
+→ Use `po` for a deliberate jolt into non-obvious territory.
+
+## 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) Two methods only** — most relevant pair of tools applied at full depth, skip synthesis across more
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Session structure
+
+### Opening: Diagnose the challenge
+Briefly state your read of the situation: what kind of thinking challenge is this, and why? This surfaces your reasoning and gives the user a chance to correct it before work begins.
+
+### Middle: Apply 2–4 methods in sequence
+Select the methods that best fit the diagnosis. Apply each one fully — do not abbreviate to get through more methods. A thorough application of 2 methods produces more value than a superficial pass through 5.
+
+**Between methods, make the connection explicit:** "The lateral thinking session revealed [X]. Now the concept fan will explore [Y] by treating [X] as the starting point." Methods should build on each other, not run in parallel.
+
+### Close: Synthesize
+After the methods are complete, synthesize across the outputs. This is not a summary — it is an integration. What do the different methods, taken together, reveal that no single method showed on its own?
+
+The synthesis should answer:
+- What is the most important insight this session produced?
+- What direction deserves the most attention, and why?
+- What should happen next?
+
+## Output format
+
+**Reading the situation:**
+[Your diagnosis — what kind of challenge is this, what methods you're selecting and why]
+
+---
+
+## [Method 1 name]
+[Full application of the method]
+
+---
+
+## [Method 2 name]
+[Full application, building on method 1 where relevant]
+
+---
+
+## [Method 3 name if used]
+[Full application]
+
+---
+
+## Synthesis
+**What this session revealed:**
+[2–3 paragraphs integrating across all methods — what the full picture shows]
+
+**Most important direction:**
+[The single most valuable direction to pursue, with reasoning]
+
+**Recommended next step:**
+[A specific, concrete action]
+
+## Notes on quality
+
+The session's value depends on the depth of each method application, not the number of methods used. It is better to run `assumption-excavator` and `lateral-thinking` thoroughly than to touch six methods superficially.
+
+The synthesis is the hardest and most important part. Most sessions produce insights in the individual method sections. The synthesis should produce an insight that only becomes visible when those outputs are held together.
+
+If the user's challenge shifts during the session — if the assumption excavator reveals that the real problem is different from the stated one — follow the actual problem, not the original framing.

package/skills/creativity-concept-fan/SKILL.md

@@ -0,0 +1,93 @@
+---
+name: creativity-concept-fan
+description: "Apply Edward de Bono's Concept Fan to expand the solution space before committing to an approach. Use when the user has a goal or problem and wants to see the full range of ways to achieve it, feels locked into one solution, is evaluating options and wants to make sure they haven't missed any, or wants to think at different levels of abstraction before deciding."
+---
+
+You are facilitating a Concept Fan session using Edward de Bono's technique. The Concept Fan is a tool for expanding solution space — it prevents premature commitment to one approach by making the full landscape of alternatives visible first.
+
+## Why the concept fan matters
+
+Most thinking about solutions is too narrow. We take a goal, think of one or two approaches, evaluate them, and pick the best. This feels thorough but it's actually a small sample of the possible solution space.
+
+The Concept Fan works by moving up and down a ladder of abstraction. At the top is the broadest possible framing of what you're trying to achieve — the pure purpose. At the bottom are specific implementations. Between them are concepts — general approaches that can each spawn multiple implementations.
+
+By mapping this landscape before committing, you avoid the trap of evaluating implementations when you should still be choosing concepts.
+
+## The structure
+
+Think of a fan with a handle and radiating spokes:
+
+- **The handle** is the goal — what you're ultimately trying to achieve, stated at its broadest useful level
+- **First ring of spokes** are broad concepts — different general approaches to achieving the goal
+- **Second ring of spokes** are sub-concepts — more specific approaches within each broad concept
+- **Outer ring** are specific implementations — concrete things you could actually do
+
+The fan expands outward from abstract to specific. At each level, the question is: "What are all the different ways to achieve this?"
+
+## Your process
+
+**Step 1: Establish the goal**
+State the user's goal at two levels:
+- Immediate goal: what they said they want
+- Purpose level: why they want it — the underlying need it serves
+
+The purpose level is important because it sometimes reveals entirely different solution families that address the real need without solving the stated problem.
+
+**Step 2: Generate broad concepts (first ring)**
+At the concept level, ask: "What are all the fundamentally different approaches to achieving this goal?" These should be distinct families of solutions, not variations on the same approach.
+
+Aim for 4–7 broad concepts. They should feel genuinely different from each other — different mechanisms, different assumptions, different resources they draw on.
+
+**Step 3: Expand each concept (second ring)**
+For 2–3 of the most promising broad concepts, generate 3–4 sub-concepts — more specific versions that show the range within that approach family.
+
+**Step 4: Generate specific implementations (outer ring)**
+For the most interesting sub-concepts, suggest 2–3 concrete implementations — actual things that could be done.
+
+**Step 5: Highlight the overlooked**
+After mapping the fan, identify: which concepts or sub-concepts did the user probably not consider before this exercise? These are the fan's main value — the alternatives that only become visible when you systematically expand the space.
+
+## 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) Concept level only** — middle tier of the fan (concepts that serve the purpose), skip both immediate tactics and strategic alternatives
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output format
+
+**Goal:** [Immediate goal]
+**Purpose:** [Underlying need — why this goal matters]
+
+**Concept Fan:**
+
+*Broad concepts:*
+1. [Concept A] — [one sentence on the approach]
+2. [Concept B] — ...
+3. [Concept C] — ...
+(etc.)
+
+*Expanding Concept [X]:*
+- Sub-concept X1: [description]
+  - Implementation: [specific action]
+  - Implementation: [specific action]
+- Sub-concept X2: [description]
+  - Implementation: [specific action]
+
+*Expanding Concept [Y]:*
+(same structure)
+
+**What this reveals:**
+[Which alternatives were probably not on the user's radar, and why they're worth considering]
+
+## Notes
+
+The fan's value is in the breadth of the second-ring concepts, not in the depth of any one branch. Resist going too deep on one concept at the expense of mapping the others — incomplete maps lead back to the same premature commitment the tool is designed to prevent.
+
+If the user already has a preferred solution, include it in the fan — but map the rest of the space before returning to it.