/competing-hypothesis-generation
SOP: Generate mechanistically distinct competing hypotheses for the same phenomenon
$ npx -y skills add yogsoth-ai/de-anthropocentric-research-engine --skill competing-hypothesis-generation --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/competing-hypothesis-generation
Context preview
The summary Claude sees to decide when to auto-load this skill.
SOP: Generate mechanistically distinct competing hypotheses for the same phenomenon
SKILL.md
competing-hypothesis-generation.SKILL.mdname: competing-hypothesis-generation
description: 'SOP: Generate mechanistically distinct competing hypotheses for the same phenomenon'
version: 1.0.0
category: hypothesis-formation
type: sop
campaign: hypothesis-formulation
input: Phenomenon description + primary hypothesis (from upstream output)
output: Competing hypothesis list (mechanistically distinct, not variants of the primary hypothesis)
dependencies:
skills:
- subagent-spawning
Competing Hypothesis Generation
Generate genuinely distinct competing hypotheses for the same phenomenon to guard against confirmation bias and keep explanations open.
HARD-GATE
<HARD-GATE> Preconditions (all must hold before starting): 1. At least 1 primary hypothesis is available (with statement + mechanism) 2. A phenomenon description is provided (the phenomenon the primary hypothesis attempts to explain)
Not satisfied → stop and return error: primary hypothesis and phenomenon description required. </HARD-GATE>
Pipeline
1. Precondition check: verify completeness of the primary hypothesis and phenomenon description 2. Alternative mechanism search: look for different causal mechanisms that can explain the same phenomenon 3. Alternative theory application: derive predictions about the same phenomenon from different theoretical frameworks 4. Reverse reasoning: consider explanations with the opposite causal direction 5. Deduplication: ensure each competing hypothesis is mechanistically distinct from the primary hypothesis and from the other competing hypotheses 6. Output competing hypothesis list
Output Format
[
{
"hypothesis_id": "CH1",
"statement": "Competing hypothesis statement",
"mechanism": "Different causal mechanism from the primary hypothesis",
"theoretical_basis": "Theory or reasoning supporting this alternative",
"key_difference": "How this differs mechanistically from the primary hypothesis",
"shared_prediction": "Prediction shared with primary hypothesis (makes discrimination hard)",
"unique_prediction": "Prediction unique to this hypothesis (enables discrimination)"
}
]At least 2 competing hypotheses, each mechanistically distinct from the primary hypothesis. </output>
Read more
name: competing-hypothesis-generation description: 'SOP: Generate mechanistically distinct competing hypotheses for the same phenomenon' version: 1.0.0 category: hypothesis-formation type: sop campaign: hypothesis-formulation input: Phenomenon description + primary hypothesis (from upstream output) output: Competing hypothesis list (mechanistically distinct, not variants of the primary hypothesis) dependencies: skills: - subagent-spawning
Competing Hypothesis Generation
Generate genuinely distinct competing hypotheses for the same phenomenon to guard against confirmation bias and keep explanations open.
HARD-GATE
<HARD-GATE> Preconditions (all must hold before starting): 1. At least 1 primary hypothesis is available (with statement + mechanism) 2. A phenomenon description is provided (the phenomenon the primary hypothesis attempts to explain)
Not satisfied → stop and return error: primary hypothesis and phenomenon description required. </HARD-GATE>
Pipeline
1. Precondition check: verify completeness of the primary hypothesis and phenomenon description 2. Alternative mechanism search: look for different causal mechanisms that can explain the same phenomenon 3. Alternative theory application: derive predictions about the same phenomenon from different theoretical frameworks 4. Reverse reasoning: consider explanations with the opposite causal direction 5. Deduplication: ensure each competing hypothesis is mechanistically distinct from the primary hypothesis and from the other competing hypotheses 6. Output competing hypothesis list
Output Format
[
{
"hypothesis_id": "CH1",
"statement": "Competing hypothesis statement",
"mechanism": "Different causal mechanism from the primary hypothesis",
"theoretical_basis": "Theory or reasoning supporting this alternative",
"key_difference": "How this differs mechanistically from the primary hypothesis",
"shared_prediction": "Prediction shared with primary hypothesis (makes discrimination hard)",
"unique_prediction": "Prediction unique to this hypothesis (enables discrimination)"
}
]At least 2 competing hypotheses, each mechanistically distinct from the primary hypothesis. </output>
The complete research orchestration system for AI-native science. What It Does Design Philosophy Architecture (v3.2.2) Quick Start Configuration Roadmap License DARE is not a tool that helps you do research. It is the researcher.
Repo: yogsoth-ai/de-anthropocentric-research-engine
Other skills on de-anthropocentric-research-engine.
- /formated-results
Closing skill for the research-executor, loaded as the last step of formated-specs. Summarize the design just produced into one research-result JSON fenced block in your reply. Do not execute the research.
Open skill - /formated-specs
Spec-slot skill for the research-executor. Emit the 4-layer DARE orchestration of the assigned topic as one research-graph JSON fenced block in your reply. Replaces the generic spec-writing step.
Open skill - /injection-fidelity
Loss-1 judge (codex role). Given one sample's de-identified dialogue and its PolicyCard, decide axis-by-axis whether the user-simulator enacted the card's per-axis pressure. Judge enactment of the card, never whether the research is good.
Open skill - /ladder-quality-order
Loss-2 judge (codex role). Over one topic's 6 shuffled research-design samples, pairwise-rank by quality using the D1–D5 standard. Emit the pairwise log; the harness computes the order and the ladder verdicts. Judge quality difference, never against academic standards.
Open skill - /optimization-loop
The optimizer brain for the ladder-foundry pretraining loop. Runs the two-level nested batch loop, delegates gating to gate_eval, attributes a failing batch to one weight (attribute-first), and recovers from disk after compaction. Control flow is fully scripted; only the
Open skill - /acu-nugget-recall
Tactic: Extract atomic units from one paper and score how much of a caller-supplied summary covers. Use for ACU-style binary or Nugget-style ternary recall checks; cannot run without a target summary.
Open skill

