@human-avatar/skills-for-humanity 1.0.0

package/skills/strategy-intelligence/SKILL.md

@@ -0,0 +1,65 @@
+---
+name: strategy-intelligence
+description: "Audits what you actually know vs. what you're assuming about yourself and your opponent before acting. Triggers: 'what do I actually know', 'intelligence audit', 'know your enemy', 'what am I assuming vs knowing', 'prep for negotiation', 'what information do I have', 'what don't I know about them', 'am I missing something important'."
+---
+
+# Strategy: Intelligence
+
+Sun Tzu's most quoted principle — "Know yourself and know your enemy; in a hundred battles you will never be in peril" — is often treated as a slogan. Its operational meaning is precise: knowledge asymmetry determines outcomes before any action is taken. A general who knows the terrain, the opponent's strength, the opponent's commander, and his own limitations will defeat an equivalent force every time. A general who acts on assumption held as fact will suffer the predictable consequence.
+
+The self-audit is as important as the opponent audit, and harder. Self-flattery is the most common intelligence failure. We know our strengths clearly; we hold our weaknesses vaguely. We know our opponent's stated position; we assume their actual constraints, motives, and fallback options. The intelligence discipline is the discipline of holding the line between what is known and what is assumed — because the gap is where strategic surprises live.
+
+---
+
+## Your Process
+
+**Step 1: Self-audit**
+List actual strengths, weaknesses, hard constraints, and available resources. Do not soften the weaknesses. Ask: what would embarrass you to admit in this situation? Those admissions are the accurate self-assessment. What dependencies do you have? What time pressures? What is your actual walk-away position?
+
+**Step 2: Opponent audit**
+What do you know about their position, capabilities, constraints, and intentions? Separate every item into two columns: **Known fact** (directly observed, documented, confirmed) vs. **Assumption** (inferred, expected, believed but unverified). Most opponent assessments contain far more assumptions than facts — naming this is the point.
+
+**Step 3: Intelligence gaps**
+What would change your decision if you knew it? List the three most important unknowns — the gaps where your current assumption, if wrong, would alter your strategy significantly. Rank by impact.
+
+**Step 4: Information-gathering paths**
+For each top gap: how might it be closed before acting? What is available through legitimate observation, inquiry, public sources, or network access? What would it cost (time, money, relationship capital) to close each gap?
+
+**Step 5: Assumption risk rating**
+For each current assumption in the opponent audit: rate the risk if that assumption is wrong. High — strategy fails if wrong. Medium — strategy degrades but survives. Low — minor adjustment required. Highlight the high-risk assumptions.
+
+---
+
+## Output Format
+
+### Intelligence Audit
+
+**Self-Assessment**
+- *Strengths:* [Genuine strengths in this context]
+- *Weaknesses:* [Candid — include what would be embarrassing to admit]
+- *Hard constraints:* [Time, resources, relationships, walk-away limits]
+
+**Opponent Assessment**
+
+| Item | Status | Risk if wrong |
+|---|---|---|
+| [Known fact 1] | Known | — |
+| [Assumption 1] | Assumption | High/Medium/Low |
+| ... | | |
+
+**Intelligence Gaps (ranked by impact)**
+1. [Most important unknown — what would change if you knew it]
+2. [Second most important unknown]
+3. [Third most important unknown]
+
+**Recommended Information Gathering**
+[For each top gap: how to close it, what it costs, whether it's worth closing before acting]
+
+**Assumption Risk Summary**
+[High-risk assumptions that could cause strategic failure — these are the decisions to hold until more intelligence is available]
+
+---
+
+## Notes
+
+Pairs with `/strategy-terrain` — intelligence informs the terrain map, and an inaccurate terrain map comes from treating assumptions as facts. Pairs with `/strategy-deception` — once you know what your opponent currently believes about you, you can manage that belief deliberately. Use `/strategy-timing` to determine whether gathering more intelligence before acting is worth the delay.

package/skills/strategy-positioning/SKILL.md

@@ -0,0 +1,62 @@
+---
+name: strategy-positioning
+description: "Builds the conditions for competitive unassailability before the contest begins. Triggers: 'create a position', 'competitive positioning', 'make myself the obvious choice', 'how do I make myself hard to compete with', 'strategic positioning', 'establish advantage before competing', 'what makes me hard to displace', 'build a moat'."
+---
+
+# Strategy: Positioning
+
+Sun Tzu: "The good fighters of old first put themselves beyond the possibility of defeat, and then waited for an opportunity of defeating the enemy." The first move is not to attack — it is to make yourself unassailable. Position precedes contest.
+
+Michael Porter's parallel insight in competitive theory: sustainable advantage comes not from trying to be best at everything, but from choosing not to compete everywhere. A position that is genuinely defensible requires trade-offs — commitments that make you excellent in one direction at the cost of flexibility in others. The value of the trade-off is precisely that it cannot be easily replicated by a competitor without abandoning their own position. A competitor who tries to copy you has to give up what they've optimized for. That is what makes a position real.
+
+The failure mode is positioning by assertion: saying you occupy a position without doing the investment that makes it true. Genuine positioning requires assets, capabilities, relationships, or reputations that are costly to build and therefore difficult to replicate. The question is not "where do I want to be?" but "what would I need to truly hold this ground?"
+
+---
+
+## Your Process
+
+**Step 1: Ideal unassailable position**
+What would it look like to hold a position that a rational, well-resourced opponent would choose to go around rather than contest directly? Describe the ideal: what would you be known for, what would you own, what would your relationships and reputation make you? Be specific — "market leader" is not a position. "The only reliable provider for this niche, with a five-year track record and the three key relationships in the sector" is a position.
+
+**Step 2: Required assets and capabilities**
+What would you need to hold that position? List specifically: skills, relationships, reputation, information, technology, capital, team, time. What do you currently have? What is missing?
+
+**Step 3: Current position**
+Honest assessment of where you stand today. What do you actually own in this competitive landscape? Not what you aspire to, not what you're building toward — what position do you hold right now that an opponent would need to consider?
+
+**Step 4: Gap-widening moves**
+What investments or actions create the largest gap between your current position and any attacker's ability to replicate it? Rank by leverage: which moves create the deepest moat per unit of investment? Which moves compound — making future moves easier?
+
+**Step 5: Position test**
+Would a rational, well-resourced opponent, looking at your fully-built position, choose a different arena rather than attack you here? If the honest answer is "no — they'd still come at us," then the position isn't unassailable yet. Name what's missing.
+
+---
+
+## Output Format
+
+### Positioning Analysis
+
+**Ideal Unassailable Position**
+[Specific description — what you own, what you're known for, what relationships you hold, what makes a rational opponent go around rather than through]
+
+**Required Assets and Capabilities**
+- *Have:* [What you currently hold that contributes to this position]
+- *Need:* [What is missing — specific gaps between current state and ideal]
+
+**Current Position**
+[Honest assessment of what you actually own today]
+
+**Gap-Widening Moves**
+[Ranked investments and actions — highest leverage per unit of investment first]
+
+**Position Test Result**
+[Would a rational, well-resourced opponent choose a different arena? What's missing if no]
+
+**Implementation Path**
+[Sequenced steps — what to build first, in what order, over what timeframe]
+
+---
+
+## Notes
+
+Terrain analysis identifies which positions are available — run `/strategy-terrain` first when you're not yet sure which positions exist worth holding. Better positioning reduces force required to defend: pair with `/strategy-force-economy` to understand how position investment pays back in reduced ongoing cost. For the specific timing of when to build vs. when to contest now, pair with `/strategy-timing`.

package/skills/strategy-terrain/SKILL.md

@@ -0,0 +1,64 @@
+---
+name: strategy-terrain
+description: "Maps the competitive landscape to identify where you have advantage, where contests are evenly matched, and where engagement is costly. Triggers: 'map the landscape', 'terrain analysis', 'where should I compete', 'what's the ground like', 'competitive landscape', 'where do I have advantage', 'which markets should I enter', 'is this fight worth having'."
+---
+
+# Strategy: Terrain
+
+Sun Tzu identifies six types of terrain and nine strategic situations in *The Art of War*, each demanding different conduct. The underlying principle is that position shapes outcome before the contest begins: "He who occupies the ground first and awaits the enemy is at ease; he who comes later and hastens to fight is weary." The key strategic question is not "how do I win this battle?" but "which battles should be fought at all?" Terrain analysis is the discipline of answering that question before committing resources.
+
+Sun Tzu's nine situations range from dispersive ground (where retreat is correct) to deadly ground (where fighting hard is the only option). What unifies them is this: each type of ground demands a different response, and treating all ground as equal is a reliable path to defeat. A position that is unfavorable for you may be excellent for your opponent. A position that looks contested may be yours to win with the right move first.
+
+---
+
+## Your Process
+
+**Step 1: Landscape inventory**
+What are the available positions in this competitive context? Include: markets or segments, relationships, information asymmetries, timing windows, resource positions, and reputation or brand territory. List them without judgment first — the goal is completeness before evaluation.
+
+**Step 2: Favorable ground**
+Where do your strengths meet their weaknesses? Where do you have natural advantage — by virtue of existing position, capabilities, relationships, speed, or knowledge? Sun Tzu: "In battle, use the orthodox method; win through the unorthodox." Favorable ground is where your orthodoxy is their weakness.
+
+**Step 3: Contested ground**
+Where are you and competitors evenly matched? What would it take to tip contested ground in your favor — first-mover advantage, a decisive capability gap, a key alliance? Note the cost of tipping each contested position vs. the value of holding it.
+
+**Step 4: Dangerous ground**
+Where do you have no natural advantage and engagement drains you? Sun Tzu's "dispersive ground" — where your forces scatter and confidence wavers. Name each dangerous position explicitly. The strategic discipline is the willingness to name ground as dangerous and refuse to fight there.
+
+**Step 5: High-ground assessment**
+Who currently holds the most advantageous position in this landscape? What makes their position strong — network effects, information advantage, first-mover lock-in, relationships? What would it take for you to hold that position instead? Is acquiring it worth the cost?
+
+**Step 6: Terrain verdict**
+Based on the above: which positions are worth fighting for, which require waiting and preparation, and which should be avoided? A clear verdict — not a hedge.
+
+---
+
+## Output Format
+
+### Terrain Analysis
+
+**Landscape Inventory**
+[Full list of available positions in this competitive context]
+
+**Favorable Ground**
+[Positions where your strengths meet opponent weaknesses — your natural advantages]
+
+**Contested Ground**
+[Evenly matched positions — with assessment of what tipping each requires and whether it's worth it]
+
+**Dangerous Ground**
+[Positions to avoid — explicit, without softening. Why each is dangerous for you specifically]
+
+**High-Ground Holder**
+[Who holds the strongest current position, why, and what taking it would require]
+
+**Terrain Verdict**
+[Clear prioritization: fight here, prepare here, avoid here — with rationale]
+
+---
+
+## Notes
+
+Run terrain analysis before any other strategy skill — it establishes the competitive context that all other choices operate within. An accurate terrain map requires honest intelligence; pair with `/strategy-intelligence` when your knowledge of the landscape is uncertain or you suspect your assumptions about competitor positions are wrong.
+
+For moving to favorable ground once identified, use `/strategy-positioning`. For understanding what opponents hold in contested positions, use `/strategy-intelligence`. For deciding whether the overall objective is worth the terrain cost, use `/strategy-victory` first.

package/skills/strategy-timing/SKILL.md

@@ -0,0 +1,64 @@
+---
+name: strategy-timing
+description: "Analyzes whether to act now or wait, reads your opponent's rhythm, and identifies trigger conditions for the right moment. Triggers: 'when should I act', 'timing analysis', 'is now the right moment', 'should I wait', 'when to launch', 'when to make my move', 'is the window closing', 'am I too early', 'am I too late'."
+---
+
+# Strategy: Timing
+
+Miyamoto Musashi opens *The Book of Five Rings* with a meditation on timing: "Timing exists in everything." His insight is not simply that timing matters — it is that timing must be actively read rather than passively experienced. A swordsman who ignores his opponent's rhythm and attacks on his own preferred schedule will find the interval closed. A swordsman who reads when the opponent is overextended, committed, or off-balance will find the interval open.
+
+Sun Tzu's complementary metaphor: "Water shapes its course according to the nature of the ground over which it flows; the soldier works out his victory in relation to the foe he is facing." Water does not insist on a fixed form. It adapts to the terrain continuously. The question is never simply "should I act?" — it is: "does the current moment give me an advantage that waiting would not compound, or does waiting improve conditions beyond what action now delivers?"
+
+Both Musashi and Sun Tzu agree on one further principle: the opponent's timing is as important as your own. Attacking when your opponent is preparing is different from attacking when they are overextended. The interval is not a point on your schedule; it is a relationship between two rhythms.
+
+---
+
+## Your Process
+
+**Step 1: Conditions favoring action now**
+What is true right now that will not be true later? What windows are closing — competitor moves, decision-maker availability, market conditions, relationships, information advantages that decay? What cost do you pay for each week of delay?
+
+**Step 2: Conditions favoring waiting**
+What conditions are improving with time on your side? What intelligence is still missing that would increase your confidence? What resources are still being built? What opponent conditions are approaching that would favor you (an opponent is about to be overextended, a regulatory decision is pending, a key hire is coming)?
+
+**Step 3: Situation type**
+Classify the situation:
+- **Flowing** — conditions are changing rapidly; the window is finite and shortening. Waiting compounds the disadvantage. Act or lose the window.
+- **Stable** — conditions are largely fixed; time is not an enemy. Patience is strategic. The cost of acting too early outweighs the cost of delay.
+- **Turning** — conditions are about to shift in a direction you can read. The question is not whether to act but exactly when the shift creates the optimal moment.
+
+**Step 4: Opponent's rhythm**
+Musashi's "interval": where is your opponent in their cycle? Are they overextended, mid-commitment, distracted, preparing, or at ease? When are they most off-balance? The best moment to act is rarely when you are most ready — it is when they are most unable to respond effectively.
+
+**Step 5: Cost asymmetry**
+What is the cost of acting too early? What is the cost of acting too late? Which error is more recoverable? In most situations, one error is reversible and one is not — name which, and let that asymmetry weight the timing decision.
+
+---
+
+## Output Format
+
+### Timing Analysis
+
+**Conditions Favoring Action Now**
+[Windows closing, costs of delay, time-sensitive advantages]
+
+**Conditions Favoring Waiting**
+[Improving conditions, intelligence gaps, opponent developments approaching]
+
+**Situation Type**
+[Flowing / Stable / Turning — with brief rationale]
+
+**Opponent's Rhythm**
+[Where they are in their cycle, when they are most off-balance, what the interval looks like]
+
+**Cost Asymmetry**
+[Cost of acting too early vs. too late — which error is less recoverable]
+
+**Recommended Timing**
+[Act now / Wait for trigger / Wait for specific condition] — with trigger conditions stated explicitly: "Act when X occurs" or "Do not act before Y is true"
+
+---
+
+## Notes
+
+Timing decisions depend heavily on intelligence quality — pair with `/strategy-intelligence` when your picture of the opponent's current state is uncertain. Timing and position interact: sometimes the right timing is simply "when your position is ready" — pair with `/strategy-positioning` when that's the case. For flowing situations with closing windows, force economy becomes critical — pair with `/strategy-force-economy` to identify the minimum effective action before the window closes.

package/skills/strategy-victory/SKILL.md

@@ -0,0 +1,64 @@
+---
+name: strategy-victory
+description: "Defines what winning actually means before the contest begins — prevents the pyrrhic trap of winning in ways that lose the larger goal. Triggers: 'what does winning look like', 'define victory', 'victory conditions', 'what are we actually trying to achieve', 'define success', 'is winning worth it', 'pyrrhic trap', 'are we optimizing for the right thing'."
+---
+
+# Strategy: Victory
+
+Clausewitz's central insight in *On War*: "War is the continuation of politics by other means." The military contest is not the point; it is a means to a political end. The moment a commander loses sight of the political objective and optimizes purely for military victory, they have already failed strategically — because a military win that undermines the political aim is worse than a negotiated settlement.
+
+The same principle applies to any contest. A company that wins a price war by destroying its margins has won the battle and lost the business. A legal team that wins at trial and spends three years doing it, producing a verdict worth less than the settlement foregone, has won the judgment and lost the case. A negotiator who extracts every possible concession and destroys the relationship needed for implementation has won the negotiation and lost the outcome. The pyrrhic trap is the failure to define victory before the contest forces its own definition on you.
+
+Sun Tzu's corollary: "The supreme art of war is to subdue the enemy without fighting." This is not a counsel of passivity — it is the recognition that the cheapest possible victory is the right objective. A victory that requires the maximum cost is a strategic failure even when it succeeds. Minimum victory conditions exist for a reason: they prevent over-prosecution of a contest that has already been won.
+
+---
+
+## Your Process
+
+**Step 1: Stated objective**
+What are you trying to achieve? Name it as it is currently framed.
+
+**Step 2: Real objective**
+What would you actually have if you achieved the stated objective? What is the objective behind the stated one — the political end, in Clausewitz's terms? Why does the stated objective matter? Sometimes the stated objective is the real one; often it is a proxy for something deeper, and winning the proxy while losing the underlying goal is precisely the pyrrhic trap.
+
+**Step 3: Minimum victory**
+The least outcome you would accept as a win. What must be true for this effort to have been worth it? Minimum victory conditions often look unsatisfying in advance — they feel like compromises. They are not. They are the protection against prosecuting a contest past the point of value.
+
+**Step 4: Maximum victory**
+What would unequivocally mean you won? What outcome makes the cost obviously worthwhile, regardless of what it took? Maximum victory conditions serve a different function: they tell you when to stop pressing once you've reached them.
+
+**Step 5: Pyrrhic check**
+What does winning cost at maximum force? At minimum force? At the likely cost, is the maximum victory worth it? Is the minimum victory worth it? Name the specific things you could lose — relationships, capital, time, reputation, flexibility — by prosecuting this contest. What would constitute a pyrrhic outcome even on a win?
+
+**Step 6: Victory recognition**
+How will you know when you've won? What observable condition tells you to stop? This is the step most often skipped — and its absence produces contests that continue past their objective, consuming additional resources toward a goal already achieved or already unachievable.
+
+---
+
+## Output Format
+
+### Victory Definition
+
+**Stated Objective**
+[How the objective is currently framed]
+
+**Real Objective**
+[The underlying political end — why the stated objective matters, and what you'd actually have if you achieved it]
+
+**Minimum Victory**
+[The least outcome that makes this worth the effort — what must be true]
+
+**Maximum Victory**
+[The unequivocal win — what makes the cost obviously worthwhile]
+
+**Pyrrhic Check**
+[What winning costs — and what would constitute a pyrrhic outcome even on a technical win]
+
+**Victory Recognition Conditions**
+[Observable conditions that tell you to stop — you have won, or you have lost and further prosecution only adds cost]
+
+---
+
+## Notes
+
+Run this before any other strategy skill when the objective is unclear — all other skills operate in service of a defined objective, and without one, they produce well-structured answers to the wrong question. Pairs tightly with `/strategy-force-economy`: knowing minimum and maximum victory conditions shapes how much force to deploy, and when the minimum has been achieved. When the pyrrhic check suggests the cost of maximum victory is unacceptable, use `/strategy-alliance` and `/strategy-positioning` to understand whether the cost can be reduced before the contest begins.

package/skills/systems/SKILL.md

@@ -0,0 +1,78 @@
+---
+name: systems
+description: "Entry point for the systems thinking toolkit. Routes to the right systems skill based on your situation. Use when you say 'systems', 'feedback loops', 'how does this system work', 'where should we intervene', 'unexpected behavior', 'what archetype is this', 'find the leverage', or want systems thinking applied without knowing which specific tool fits."
+---
+
+# Systems
+
+Applies systems thinking to complex, dynamic situations. Diagnoses what kind of systems analysis is needed and applies the right tool.
+
+## Which tool fits
+
+| You need to... | Tool |
+|---|---|
+| Recognize what recurring system pattern this is | archetype-matching |
+| Understand unexpected or counterintuitive system behavior | emergence-detection |
+| Map the feedback loops driving behavior | feedback-mapping |
+| Find where small interventions produce large change | leverage-analysis |
+
+## Routing Decision
+
+- **Situation has a familiar-feeling dynamic — want to name the archetype** → archetype-matching
+- **System is producing results no one intended or expected** → emergence-detection
+- **Need to understand what's reinforcing the current behavior** → feedback-mapping
+- **Need to know where to intervene for maximum effect** → leverage-analysis
+- **Unclear** → feedback-mapping; mapping the loops reveals archetypes, emergence, and leverage points together
+
+## 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.
+
+---
+
+## Archetype Matching
+
+*Identifies what recurring system pattern this is.*
+
+Systems behave in recurring patterns. The common archetypes: Limits to Growth (growth stalls as it approaches an unseen constraint), Shifting the Burden (quick fixes address symptoms while the underlying problem grows), Fixes that Fail (interventions create delayed side effects that make things worse), Escalation (each side responds to the other's moves, spiraling), Tragedy of the Commons (individual rational behavior depletes a shared resource). Name the candidates. Test each against the current situation.
+
+**Output:** Archetype identified with structural evidence, what the archetype predicts will happen next, and the leverage point specific to this archetype.
+
+---
+
+## Emergence Detection
+
+*Understands unexpected behavior that no single part of the system intended.*
+
+Emergent behavior arises from interactions, not components. When the system produces a result that surprises everyone: map the interactions that generate it. Which feedback loop is amplifying the behavior? Which constraint is the system bumping against? Emergence is often counterintuitive — pushing harder in the obvious direction makes things worse. Find the non-obvious intervention.
+
+**Output:** The emergent behavior described structurally, the interactions generating it, why intuitive interventions fail, and the non-obvious leverage point.
+
+---
+
+## Feedback Mapping
+
+*Maps the feedback loops driving behavior in a system.*
+
+Identify reinforcing loops (R): A increases B, B increases A — creates exponential growth or collapse. Identify balancing loops (B): A increases, B responds to reduce A — creates stability or oscillation. For the current situation: which loops are active? Which are dominant? What is the time delay between cause and effect — where delays exist, oscillation is likely. The behavior of any system is the behavior of its feedback loops.
+
+**Output:** Feedback map — reinforcing and balancing loops, dominant loops, time delays, and the behavior each loop generates.
+
+---
+
+## Leverage Analysis
+
+*Finds where small interventions produce large, lasting change.*
+
+Apply Donella Meadows' leverage point hierarchy. Low-leverage interventions: adjusting numbers, parameters, flow rates. Medium-leverage: changing feedback loop strength, information availability, rules. High-leverage: changing system goals, system structure, the paradigm the system operates within. Map current interventions by leverage level. Find the higher-leverage points being avoided — they're usually avoided for a reason (political resistance, long time horizon, requires belief change). That reason is worth examining.
+
+**Output:** Intervention map by leverage level, identification of high-leverage points being avoided and why, and the most feasible high-leverage intervention.

package/skills/systems-archetype-matching/SKILL.md

@@ -0,0 +1,72 @@
+---
+name: systems-archetype-matching
+description: "Applies the 8 classic system archetypes (Senge) to diagnose recurring system behavior. Use when asked 'this keeps repeating', 'the fix made it worse', 'we've solved this before', 'identify the pattern', or 'system archetype'."
+---
+
+# Systems Archetype Matching
+
+Recurring system behaviors are not unique — they follow a small set of structural patterns that have known causes and known high-leverage responses. Senge's eight archetypes give names to these patterns. Matching the current situation to an archetype tells you what structure is producing the behavior and what intervention actually works, rather than re-discovering the same solution each cycle.
+
+---
+
+## Your Process
+
+**Step 1: Describe the Recurring Behavior**
+State what keeps happening. Include: what was tried, what temporarily worked, what came back. The more specific, the better the match.
+
+**Step 2: Compare Against All Eight Archetypes**
+Screen each archetype:
+- **Limits to Growth:** growth slows unexpectedly as a constraint is hit
+- **Shifting the Burden:** symptomatic fix used repeatedly, undermining fundamental solution
+- **Eroding Goals:** goals lowered to close the gap instead of improving performance
+- **Escalation:** two parties each respond to the other's actions by increasing their own
+- **Success to the Successful:** winner gets more resources, making it harder for others to compete
+- **Tragedy of the Commons:** shared resource overused because individual gain exceeds individual cost
+- **Fixes that Fail:** short-term fix has delayed negative side effects that recreate the problem
+- **Growth and Underinvestment:** growth slows because capacity investment lags demand
+
+**Step 3: Select the Best Match**
+Choose the archetype whose causal structure most closely matches the described situation. Note any secondary archetypes.
+
+**Step 4: Map the Situation Onto the Archetype**
+Translate the archetype's generic variables into the specific people, resources, decisions, and feedback loops of this situation.
+
+**Step 5: Apply the Standard Intervention**
+Each archetype has a known high-leverage response. State it for this situation specifically.
+
+---
+
+## 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) Archetype identification only** — name the recurring system pattern, skip full dynamics analysis
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**Archetype Match:** [archetype name] (secondary: [if any])
+
+**Why It Matches:** [2–3 sentences mapping behavior to archetype structure]
+
+**Situation Mapped to Archetype Structure**
+
+| Archetype Variable | This Situation |
+|-------------------|---------------|
+| | |
+
+**Standard Intervention:** [what actually works for this archetype, made specific to this situation]
+
+**What to Stop Doing:** [the low-leverage or counterproductive response the archetype predicts]
+
+---
+
+## Notes
+
+If two archetypes both fit, that is meaningful — overlapping archetypes indicate a more entrenched structure. Apply the higher-leverage archetype's intervention first.

package/skills/systems-emergence-detection/SKILL.md

@@ -0,0 +1,65 @@
+---
+name: systems-emergence-detection
+description: "Identifies system-level properties that exist nowhere in any individual component. Use when asked about 'emergent behavior', 'components are fine but the system isn't', 'why does the whole behave like this', or 'what creates this property'."
+---
+
+# Systems Emergence Detection
+
+Emergent properties are the most important features of complex systems and the least designed for. They arise from interactions between components, not from the components themselves — which is why fixing individual parts often fails to fix system-level problems. Identifying emergence requires asking not what each component does, but what arises when they interact.
+
+---
+
+## Your Process
+
+**Step 1: State the System-Level Property**
+Name the property to explain or design for. Be precise: "the platform feels trustworthy", "the team produces poor decisions", "the market self-corrects". Vague properties produce vague analysis.
+
+**Step 2: List Components**
+Enumerate the system's components — people, subsystems, rules, technologies, incentives. These are the parts whose interactions you will examine.
+
+**Step 3: Test Each Component**
+For each component: does the property exist in it alone? If trust cannot exist in a single user, the property is emergent. This step confirms emergence and rules out simple aggregation.
+
+**Step 4: Trace the Producing Interactions**
+Identify the specific interactions between components that generate the property. Not all interactions contribute equally — find the ones that are necessary and sufficient.
+
+**Step 5: Assess Desirability**
+Is this emergent property desirable? If yes: which interactions need protection from being disrupted? If no: which specific interactions need changing — not which components need replacing.
+
+**Step 6: Identify Intervention Points**
+If the emergence is undesirable, locate where in the interaction chain the property can be interrupted or redirected with minimum disruption to desirable emergent properties.
+
+---
+
+## 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) Emergence sources only** — where unexpected behavior is coming from, skip implications
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**System-Level Property:** [precise statement]
+
+**Emergence Table**
+
+| Property | Present in Components Alone? | Producing Interactions | Desirable? |
+|----------|------------------------------|----------------------|-----------|
+| | | | |
+
+**Key Producing Interactions:** [the 2–3 interactions most responsible for the property]
+
+**Intervention Points (if undesirable):** [where to change interactions, not components]
+
+---
+
+## Notes
+
+Removing a component to fix an emergent property rarely works — the interaction pattern will reproduce the property with whatever components remain. Target the interaction, not the part.

package/skills/systems-feedback-mapping/SKILL.md

@@ -0,0 +1,67 @@
+---
+name: systems-feedback-mapping
+description: "Identifies all reinforcing (+) and balancing (−) feedback loops in a system. Use when asked to 'map the feedback loops', 'why does this keep happening', 'unintended consequences', or 'system keeps oscillating'."
+---
+
+# Systems Feedback Mapping
+
+Most system failures come from unrecognized feedback loops — especially delayed balancing loops that cause overshoot and collapse. Reinforcing loops amplify change in one direction; balancing loops push back toward a target. Until both types are visible and named, diagnosis and intervention are guesswork.
+
+---
+
+## Your Process
+
+**Step 1: Define System Boundary**
+State what is inside the system and what is outside it. Name the time horizon and the key behavior to explain (growth, oscillation, collapse, stagnation).
+
+**Step 2: List Key Variables**
+Identify 5–10 variables that change over time and drive the behavior in question. These are stocks (levels that accumulate) or flows (rates of change). Be specific — "customer trust" not "sentiment".
+
+**Step 3: Map Causal Links**
+For each variable pair where a relationship exists: does A increasing cause B to increase (same direction, +) or decrease (opposite direction, −)? Mark the polarity of each link.
+
+**Step 4: Trace Loops**
+Follow causal chains until they close back on themselves. Count the number of negative (−) links in the loop. Even number of negatives = reinforcing loop (R). Odd number = balancing loop (B). Name each loop.
+
+**Step 5: Mark Delays**
+Identify where cause is separated from effect in time. Delays are the primary source of oscillation and overshoot — a balancing loop with a long delay will overcorrect.
+
+**Step 6: Identify the Dominant Loop**
+Which loop is currently driving system behavior? The dominant loop changes as conditions change — map the transition conditions.
+
+---
+
+## 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) Reinforcing loops only** — what's accelerating in this system, skip balancing loops
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**System Boundary:** [scope + time horizon + behavior to explain]
+
+**Feedback Loop Table**
+
+| Loop Name | Type (R/B) | Variables in Loop | Delay? | Current Strength |
+|-----------|-----------|-------------------|--------|-----------------|
+| | | | | |
+
+**Dominant Loop:** [name] — [what behavior it produces]
+
+**Delay Risks:** [which delays are creating overshoot or oscillation]
+
+**What This Predicts:** [expected system behavior if current structure holds]
+
+---
+
+## Notes
+
+Loops are not permanent — the dominant loop shifts as variables hit limits or thresholds. Map the transition condition that would shift dominance from one loop to another.