Science

How This Skill Approaches It

The skill embeds the scientific method as a literal execution loop: DefineGoal first (success criteria before any action), then GenerateHypotheses with a hard floor of three candidates (single-hypothesis work is confirmation bias by construction), DesignExperiment to make tests falsifiable, MeasureResults to collect only goal-relevant data, AnalyzeResults against the original success criteria, then Iterate back to the hypothesis phase. QuickDiagnosis applies this cycle in 15-minute bursts for fast debugging. StructuredInvestigation runs the full multi-factor version for complex problems. The skill integrates Council for hypothesis generation, Evals for structured measurement, and RedTeam for stress-testing conclusions before you commit to them.

In Action

What you say to your DA, and what the Science skill actually does.

• You say "figure out why the surface time filters are showing stale items"
  → Runs QuickDiagnosis: generates at least three hypotheses (timestamp format mismatch, cache invalidation gap, query boundary condition), designs a minimal test for each, runs them, compares results to the success criterion, and surfaces the structural cause — not just the first thing that looked suspicious.
• You say "experiment with different prompt structures to get better output quality"
  → Runs FullCycle: defines a measurable quality criterion, generates 3+ prompt variants as competing hypotheses, designs controlled experiments with the Evals skill as the measurement layer, analyzes which variant actually moved the metric, and iterates until the winner is confirmed or a new hypothesis enters the pool.
• You say "how do we test whether adding a rate limit will actually reduce abuse"
  → Runs DesignExperiment: frames the question as a falsifiable claim, identifies what data would confirm or refute it, defines the minimum viable test, and flags second-order effects (legitimate traffic retry load) that the hypothesis needs to account for before the experiment runs.

Inside the Skill

The thinking, frameworks, and architecture that distinguish this skill from a generic version of the same task.

Workflows & Routing · 3

Each workflow is one job the skill runs. The trigger phrases route your request to the right one — this is the skill's routing table.

1. 01
   DefineGoal Intents/DefineGoal.md

   define the goal, what are we trying to achieve

2. 02
   QuickDiagnosis Intents/QuickDiagnosis.md

   Quick debugging (15-min rule); not for an obvious five-minute fix or creative/generative work, which need no ceremony

3. 03
   StructuredInvestigation Intents/StructuredInvestigation.md

   investigate, complex or research-grade investigation

How to Invoke

Say any of these to your DA and LifeOS activates the Science skill automatically:

• "think about"
• "figure out"
• "diagnose"
• "investigate"
• "why is this happening"
• "science"
• "quick diagnosis"
• "structured investigation"
• "define the goal"
• "what are we trying to achieve"
• "research-grade investigation"

Or invoke explicitly:

Skill("Science")

References · 4

Auxiliary files the skill loads at runtime — frameworks, guides, configs.

• Examples
• Methodology
• Protocol
• Templates

Related Skills