Stats
Actions
Tags
From skills-for-humanity
Maps solution spaces as fitness landscapes to analyze local optima, adaptive valleys, and path dependence. Helps recognize when you're stuck on a local peak and how to cross valleys.
How this skill is triggered — by the user, by Claude, or both
Slash command
/skills-for-humanity:s4h-evolution-fitness-landscapeThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Sewall Wright introduced the fitness landscape metaphor in 1932: imagine every possible combination of traits mapped onto a surface, with elevation representing fitness. Populations move across this surface by natural selection — uphill, always, toward higher fitness. The metaphor contains a profound trap: gradient-following reliably finds local peaks but may never reach the global optimum if t...
Sewall Wright introduced the fitness landscape metaphor in 1932: imagine every possible combination of traits mapped onto a surface, with elevation representing fitness. Populations move across this surface by natural selection — uphill, always, toward higher fitness. The metaphor contains a profound trap: gradient-following reliably finds local peaks but may never reach the global optimum if that optimum is separated from the current position by a valley — a region of lower fitness that must be crossed to reach higher ground.
Stuart Kauffman formalised the implications. In a rugged landscape (many local peaks of varying heights), adaptive evolution produces a rich variety of stable-but-suboptimal solutions. Path dependence is total: where you end up depends entirely on where you started, because the trajectory of selection is irreversible and local. In an ultra-smooth landscape (one peak), selection reliably finds the global optimum. In a chaotic landscape (fitness changes with every step), selection fails entirely — there is no stable higher ground to climb toward.
This tool maps the fitness landscape of a problem, strategy space, or technology domain. It identifies where the current entity sits, which kind of landscape this is, what the local peaks look like, what valleys must be crossed to reach higher ground, and whether valley-crossing is currently viable. The practical question is almost always: are we trapped on a local peak, and if so, what does it cost to get off it?
Step 1: Define the Landscape Specify the axes and the fitness measure. Every landscape has:
Framing check: Confirm the landscape axes and fitness measure before continuing. State what you've identified — the entity, the key dimensions of variation, and what counts as fitness — in one sentence, then use AskUserQuestion:
Step 2: Assess Landscape Ruggedness How many distinct high-fitness solutions exist in this space? Is this:
Name evidence for the ruggedness assessment.
Step 3: Locate the Current Position Where does the entity currently sit on the landscape? Describe this precisely: which traits, configurations, or strategy choices define their current position? Assess whether they are:
Identify the evidence for the current position — what patterns suggest they are or are not at a local peak?
Before mapping neighbours: Use AskUserQuestion:
Step 4: Map Adjacent Peaks and Valleys What are the nearest alternative high-fitness positions — the other local peaks that are reachable from here? For each:
Step 5: Assess Valley-Crossing Viability Whether crossing a fitness valley is viable depends on:
Assess viability honestly: valley-crossing that requires sustained tolerance for sub-fitness is often strategically obvious but organisationally impossible.
Step 6: Strategic Implication Synthesise: where is the entity trapped, if anywhere? What would it take to get to higher ground? Is the current trajectory one of local optimisation (reliably improving toward a local peak) or genuine progress (crossing toward a global peak)? What needs to be true — in the environment, in the entity's capabilities, or in the competitive pressure — for a valley crossing to be attempted?
Before proceeding, use the AskUserQuestion tool. State your interpretation in 1–2 sentences — where the entity sits on the landscape, what the key peak or valley question is — then ask:
Proceed based on their selection. If the user reframes, incorporate the correction before running any analysis.
Landscape Definition [Entity, key axes, fitness measure, and landscape ruggedness type]
Current Position [Where the entity sits — which traits, strategy, or configuration define their current position and whether they are near a local peak, on a slope, in a valley, or at a global peak]
Evidence for Peak Status [Signs that incremental improvement is hitting a ceiling — or evidence that improvement is still productive]
Adjacent Peaks
| Peak | Description | Relative Fitness | Valley Depth | Valley Width | Path Options |
|---|---|---|---|---|---|
| [name] | [strategy/configuration] | [higher / lower / similar] | [shallow / moderate / deep] | [narrow / wide] | [stepping stones or none] |
Valley-Crossing Viability Assessment
| Factor | Assessment |
|---|---|
| Slack available | [high / moderate / low] |
| Valley duration | [brief / moderate / prolonged] |
| Landscape stability | [stable / shifting / eroding under current position] |
| Forcing mechanism | [present / absent — if present, describe] |
Strategic Implication [Synthesised recommendation: stay and optimise the current peak, attempt a valley crossing (under what conditions), or wait for environmental shift to change the landscape]
The fitness landscape metaphor is descriptive, not prescriptive. It names the structural reason why incremental improvement fails to reach the global optimum — not because the strategy is wrong, but because the topology of the solution space makes gradient-following insufficient. This is why discontinuous innovation often looks foolish from within the existing peak and obvious in retrospect: the valley had to be crossed.
Stephen Jay Gould's concept of the contingency of evolutionary history maps directly: which peak a lineage ends up on depends entirely on historical path, not on the quality of the peak itself. Many sub-optimal peaks are stably occupied simply because they were reached first. This is the structural explanation for lock-in, legacy architecture, and incumbent advantage.
Pairs with /s4h-evolution-variation-selection to understand which selection pressures are defining the current fitness landscape. Pairs with /s4h-constraint-hardness-testing to evaluate whether constraints that keep the entity on the current peak are truly hard or merely assumed. Pairs with /s4h-systems-leverage-analysis to find where small changes in landscape topology (changing the fitness measure, changing the environment) would make valley-crossing tractable.
After delivering this output, use AskUserQuestion to offer the next move:
/s4h-evolution-variation-selection — Understand what selection pressures are shaping this landscape/s4h-constraint-hardness-testing — Test whether constraints keeping you on the current peak are truly binding/s4h-strategy-timing — Determine when the right moment is to attempt a valley crossingnpx claudepluginhub human-avatar/skills-for-humanityRoutes to the right evolutionary reasoning tool based on your situation. Use when analyzing how populations, strategies, or systems change through variation, selection, niches, fitness landscapes, or coevolution.
Explores solution spaces using ant colony optimization — deploying scout hypotheses, reinforcing promising approaches, and detecting when to abandon a strategy. Use when multiple approaches exist with no clear winner or when debugging with no obvious root cause.
Analyzes software component evolution stages (Genesis to Commodity) and Wardley climatic patterns for planning, design, and best practices guidance.