yogsoth-ai/de-anthropocentric-research-engine.

abductive-hypothesis-generation

Strategy: 面对异常的最佳解释推理

ablation-brainstorm

Remove components one by one, observe system changes to reveal hidden dependencies and generate ideas from structural gaps.

ablation-component-mapping

Map system architecture to ablatable units for ablation studies

ablation-design

Design ablation studies to isolate component contributions in ML systems

ablation-execution

Remove components one by one from a system, record the response/impact of each removal.

abp-vulnerability-classification

Classify assumptions on 2 axes — load-bearing (how much conclusion depends on it) × vulnerable (how likely to be false). Focuses attention on High-Load × High-Vulnerable quadrant.

abstraction-extraction

Extract abstract principles from concrete domain cases. Strips domain-specific details to reveal transferable mechanisms.

abstraction-ladder

Perform bisociation at multiple abstraction levels

abstraction-laddering

Move between concrete and abstract framings — 3 levels up (Why?) and 3 levels down (How?) to find the most productive research level.

abstraction-to-design

Abstract biological principle to design principle. Bridge from biology to engineering.

action-priority-matrix

Compute Risk Priority Number (RPN = S x O x D), classify failure modes into H/M/L action priority per AIAG-VDA tables.

activity-listing

Enumerate all implementation activities from an experiment design

actor-profiling

Understand who the user is — background, resources, constraints, and deep motivations. Produces an ActorProfile that informs all downstream decisions. Use this tactic at the start of any crystallization process to build a model of the user's capabilities, limitations, and intent.

adaptive-pair-selection

Iteratively select maximally informative pairs, execute comparisons, update ratings, and check convergence until ranking stabilizes.

adversarial-debate-protocol

Structured debate protocol that constructs an advocate, deploys critic attacks, and renders a judge verdict through iterative rounds.

adversarial-escalation

Strategy: Progressive pressure escalation — starts with surface-level challenges and escalates to fundamental assumption attacks based on defender confidence decay.

adversarial-persona

Strategy: Role-play attacks from hostile personas — competing lab researcher, hostile reviewer, funding skeptic, domain outsider — each with distinct attack motivations and blind spots.

adversarial-roleplay

Tactic: Construct detailed hostile persona, attack artifact from that persona's perspective, record successful attack paths for aggregation.

adversarial-stress-testing

Campaign: Logical extreme and boundary testing via reductio ad absurdum and edge-case analysis. Core question: Does this artifact collapse under logical limits and boundary conditions? Methods: Lakatos 1976, Dutilh Novaes 2016, BVA, Flyvbjerg Critical Case, Popper.

advocate-construction

Construct the strongest possible case for a rejected candidate or counter-position.

aggregation-method

Aggregate multiple ranking ballots into a consensus ranking using a specified social choice method.

ahp-weighting

SOP: 使用 AHP 层次分析法确定评分维度权重，输出权重向量

ahrq-picme-assessment

SOP: 使用 AHRQ PiCMe 框架对研究 gap 进行 6 维度系统评估

ahrq-reason-classification

Classify gap root causes using AHRQ 4-reason framework (insufficient info, biased info, inconsistent info, not yet integrated).

alternative-analysis

Strategy: What-If Analysis, Alternative Futures, and Four Ways of Seeing — generate competing explanations and scenarios to challenge the dominant narrative.

alternative-futures

Generate 2-4 divergent scenarios from the same evidence base, each representing a plausible alternative to the artifact's conclusions.

alternative-model-generation

Generate alternative model formulations by relaxing, replacing, or generalizing specific assumptions.

alternative-scoring

Score each candidate alternative against all criteria to produce a score matrix.

alternatives-generation

Generate alternatives for every known approach — ensure no approach goes unchallenged.

analogical-transfer

Systematic structure-mapping from source to target domain (Gentner). Identify relational correspondences and transfer higher-order constraints.

analogy-chain

Chain analogies to deeper levels (3-5 layers). Each layer reveals new aspects and insights not visible at the surface.

analogy-extraction

Extract transferable structural principles from source domains. Orchestrates source identification → abstraction → structural mapping → transfer validation.

analogy-quality-assessment

Assess analogy depth (surface/structural/systemic). Determines whether an analogy warrants transfer investment.

and-or-decompose

KAOS-style recursive goal decomposition. AND decomposition for sub-goals that must ALL be satisfied. OR decomposition for alternative paths where any one suffices. Produces a GoalTree (DAG structure).

anomaly-characterization

SOP: 描述和分类无法被现有理论解释的异常现象

anomaly-driven-abduction

Tactic: 归纳/溯因路径——描述异常现象，生成候选解释，按可信度排序

answering-sequence-design

SOP: 设计子问题的最优回答顺序

anti-benchmark

Challenge industry best practices' hidden assumptions. Deconstruct benchmarks to reveal unexamined constraints.

appreciative-discovery

Search for positive deviants and extract transferable principles using Appreciative Inquiry.

appreciative-reframing

Find positive deviants and reframe the problem from deficit-based to asset-based using Appreciative Inquiry.

appropriateness-bounding

Establish acceptability standards through RAND/UCLA Appropriateness Method or Consensus Conference protocols.

argument-crystallization

Distill the strongest arguments from each perspective through Argument Delphi or Dialectical Delphi methods.

argument-extraction

Extract and steel-man the core arguments supporting a given opinion cluster.

artifact-detection

Detect annotation artifacts and shortcuts in benchmarks

ask-constraints

Understand hard boundaries on the user's research — target venues, methodology preferences, areas to avoid, advisor/team requirements. Not limited to ML/AI — works for any research domain.

ask-decomposition-validation

Present the GoalTree to the user for confirmation. Ask about reasonableness, missing elements, and priority ordering among sub-goals.

ask-intentionality

Deep WHY probing inspired by i* Intentionality modeling. Understand the user's motivation, success definition, risk tolerance, innovation preference, independence preference, time urgency, and learning willingness. The most important SOP in actor-profiling — understanding WHY drives everything downstream.

ask-obstacle-acceptance

Present obstacles with their severity assessments and proposed mitigations to the user. Ask whether they can accept these obstacles. If unacceptable after 2 rounds, return to present-candidates.

assess-obstacle-severity

Rate each identified obstacle's difficulty — overcomability, time cost, workaround existence. May optionally use search tools to validate assessments.

assignee-normalization

Standardize assignee names and identify corporate group affiliations across patent offices

assumption-audit

Surface all assumptions, classify by vulnerability (load-bearing × likely-false), validate causal logic. Focus on dangerous assumptions — high load-bearing + non-explicit.

assumption-cascade

Tactic: Surface assumptions, sort by dependency, attack root assumptions first, then trace cascade failures through the dependency graph.

assumption-cascade-tracer

Build assumption dependency graphs and trace cascade failures when root assumptions are invalidated.

assumption-challenge

Construct the strongest counter-argument against a specific assumption and propose alternatives.

assumption-challenging

Challenge each assumption's validity — shared cross-repo SOP

assumption-constraint

Which assumptions are most fragile? — Vulnerability ranking + impact assessment of experiment assumptions

assumption-criticality

Measure how much conclusions change when each assumption is negated. Ranks assumptions by their impact on the final result.

assumption-destruction

Assumption Destruction Campaign — open new solution spaces by negating, reversing, and challenging fundamental assumptions.

assumption-enumeration

Systematically identify all assumptions in a method/model — structural, parametric, distributional, and scope assumptions.

assumption-excavation

Systematic extraction, challenge, and sensitivity analysis of assumptions underlying a decision to identify load-bearing beliefs.

assumption-extraction

Systematically extract all assumptions (stated, implicit, boundary, mathematical, practical) from a method or model.

assumption-negation

Classic reductio ad absurdum: negate the core claim, derive logical consequences, seek contradiction or absurdity.

assumption-perturbation

One-at-a-time assumption perturbation — extract assumptions, define negations, re-derive conclusions under each negation, measure sensitivity. Identifies which assumptions are load-bearing.

assumption-stress-test

Systematic stress testing of assumptions — surface, classify by vulnerability, attack, assess fragility. Combines assumption-surfacing (shared), abp-vulnerability-classification, and clr-validation SOPs.

assumption-surfacing

Systematically extract implicit assumptions from methods, frameworks, or arguments. Identifies what is taken for granted without explicit justification.

attack-resilience-scoring

Compute overall resilience score (0.0-1.0) based on attack results, coverage, and vulnerability severity distribution.

attack-vector-generation

Generate specific attack strategies for a given threat surface, producing concrete probes that can be executed.

axiom-negation

Identify and suspend fundamental assumptions via de Bono PO. Systematically negate axioms to reveal hidden solution spaces.

bad-fm

ballot-collection

Gather independent ranking ballots from multiple judges or perspectives for a given candidate set.

baseline-establishment

SOTA Performance Baseline Campaign — 5 strategies for systematically collecting, standardizing, and analyzing performance data across methods. Produces standardized comparison tables, progress curves, and headroom analysis.

baseline-selection

Select appropriate baselines for experimental comparison

baseline-synthesis

Produce final structured baseline report integrating all analysis results

benchmark-archaeology

Evaluation Methodology Archaeology Campaign — 5 strategies for systematic analysis of AI/ML benchmarks, metrics, and leaderboards. Reveals construct validity issues, saturation, data contamination, and evaluation protocol inconsistencies.

benchmark-audit

Systematic quality assessment using BetterBench 46-criterion framework — 5 benchmarks, 30 papers, 40 web searches

benchmark-challenge

Identify and negate benchmark assumptions. Deconstruct best practices to reveal hidden constraints and open new spaces.

benchmark-inventory

Identify and catalog all relevant benchmarks in target domain

benchmark-sweep

Systematically scan all known solutions, identify gaps in coverage and unexplored regions of the solution space.

benchmark-synthesis

Produce final structured audit report

best-option-selection

Select the single best candidate from a set using WSM, TOPSIS, AHP, MAUT, or VIKOR methods.

bias-detection

Assess systematic biases in the evidence body — publication bias, reporting bias, and selective outcome reporting. Budget: 40 studies, 40 effect sizes, 40 web searches.

biological-function-mapping

Map technical functions to biological systems. Orchestrates problem-biologization → organism-discovery → functional-model-biology.

biological-strategy-extraction

Extract strategy principles from organisms. Identify mechanism-level details of how biological systems achieve their function.

biologize-and-discover

Biomimicry Design Spiral: Define→Biologize→Discover→Abstract→Emulate. Translate technical challenges into biological questions and find nature's solutions.

biomimicry

Biomimicry Campaign — discover transferable solutions from biological systems via Design Spiral, BioTRIZ, functional analogy, ecosystem patterns, and evolution strategies.

biomimicry-synthesis

Synthesize all biomimicry outputs into a structured idea report. Integrate biological strategies, design principles, and technical solutions.

biotriz-principle-selection

Select applicable BioTRIZ principles for a given contradiction. Map to biological cases.

biotriz-resolution

BioTRIZ: biological 40 principles + bio contradiction matrix. Resolve technical contradictions using biological inventive principles.

bisociation-network-construction

Build multi-domain bridging concept network. Creates a network of collision points between multiple thinking matrices.

blend-completion

Complete blend with background knowledge

blend-composition

Compose new connections in blended space

blend-construction

Construct complete 4-space blends with emergent structure. Orchestrates input-space-construction → generic-space-extraction → blend-composition.

blend-elaboration

Run blend as mental simulation

bom-ub

bottleneck-identification

Identify bottleneck dimensions from radar data with severity ranking.

boundary-analysis

Boundary Analysis Campaign — probe where methods fail, map validity envelopes, test robustness, catalog failure modes, detect scaling limits. 5 strategies, 3 tactics, 11 subagent SOPs.

boundary-condition-specification

SOP: 指定假设成立的边界条件

boundary-critique

Apply CSH boundary critique — what is included/excluded, who benefits/is harmed, what expertise is privileged/marginalized. Identifies opportunities at the boundaries.

boundary-enumeration

Systematic Boundary Value Analysis: identify parameter boundaries, test at and beyond limits, detect breakpoints.

boundary-probing

Map parameter space, generate extreme values, test at boundaries, detect breakpoints, synthesize validity envelope.

boundary-synthesis

Compile all boundary analysis products into a coherent report — validity envelopes, robustness results, failure catalogs, scaling maps, safe operating conditions.

boundary-unfolding

Systematically expose hidden system boundaries — CSH 12-question is/ought comparison, identify excluded stakeholders, reveal blind spots. Combines csh-12-question, jtbd-mapping, and salience-classification SOPs.

breakpoint-detection

Test a claim at extreme parameter values and detect the precise point where it breaks down.

bridge-validation

Validate analogy depth and transfer viability. Ensures only deep structural analogies (not surface-level similarities) proceed to transfer.

broad-paper-search

Paper landscape scan within selected field(s). Strict import of literature-engine/literature-overview skill. Hard constraint: at least 80 papers scanned.

broad-web-search

Quick web scanning for field landscape understanding. Strict import of web-browsing/web-search skill. Hard constraint: ~10 results per call, at least 150 total search results before completing.

budget-constrained-design

Optimize experiment design under compute and time budget constraints

buffer-sizing

Calculate project, feeding, and resource buffers — shared with implementation-planning

campaign-selection

Structured questioning SOP to determine which campaigns to include, emphasize, or skip. Used during spec generation.

capability-taxonomy-mapping

Build capability taxonomy, map existing benchmark coverage

categorize-papers

Cluster papers by theme, method, or timeline. Produces natural groupings from a paper collection. Used by scoping-survey and narrative-review.

category-sorting

Classify candidates into predefined categories using ELECTRE-Tri, FlowSort, AHPSort, or DRSA methods.

catwoe-analysis

Apply Checkland's CATWOE analysis from a specific stakeholder perspective to reveal how the problem looks from that viewpoint.

causal-chain-tracing

Trace UDE to root cause via IF...THEN...BECAUSE logic chains

causal-claim-extraction

Extract all causal claims (X causes Y, X leads to Y, X enables Y) from an artifact, producing a structured list of cause-effect pairs.

causal-necessity-testing

Tactic: Extract causal claims, evaluate probability of necessity (PN) and sufficiency (PS) for each, classify into necessity-sufficiency quadrants.

causal-tree-building

Build logical causal trees from symptoms to root causes — list UDEs, connect causal chains, validate logic, locate root causes. Combines ishikawa-decomposition, current-reality-tree, and clr-validation SOPs.

challenge-operation

Non-threatening 'Why?' questioning of current practices (de Bono Challenge)

challenge-questioning

Non-threatening 'Why?' questioning of current practices to reveal historical accidents vs. genuine constraints.

checkpoint-and-recover

Checkpoint state before risky operations, detect anomalies, and recover gracefully

citation-chaining

Forward and backward citation tracing tactic — expand paper coverage by tracing citation networks in both directions from seed/key papers. Alternates forward (who cited this) and backward (what this cited) passes until saturation.

citation-network-analysis

Build and analyze patent citation networks — main path analysis, PageRank, cluster detection

claim-analysis

Deep claim scope analysis — decompose independent/dependent claims and assess protection scope breadth. Budget: 30 patent families, 30 claim parses, 20 web searches.

claim-decomposition

Independent/dependent claim parsing, element extraction, and feature mapping to technical domains

claim-negation

Formally negate the core claim, producing the logical complement for reductio testing.

claim-parsing

Patent claim syntax parsing — independent/dependent relationships and element extraction

claim-refinement

Propose a refined claim that survives counterexamples while preserving maximum explanatory power (Lakatos lemma-incorporation).

clarify-resources

Understand what resources the user has available for research — compute, timeline, collaboration, data access, experimental environment. Every item accepts 'TBD' as a valid answer.

classification-navigation

IPC/CPC hierarchy drill-down and lateral expansion for patent discovery

closest-worlds

Strategy: Lewis Possible Worlds — find the minimal change to reality that would flip the conclusion, measuring how close the nearest world where the conclusion fails.

clr-validation

Apply Goldratt's 8 Categories of Legitimate Reservation to validate causal claims. Tests clarity, existence, sufficiency, and logical integrity.

cluster-analysis

Identify natural opinion clusters from collected judgments and characterize each cluster.

coherence-diagnosis

Strategy for auditing preference consistency using Consistency Ratio, cycle enumeration, and mElo to detect and resolve intransitivities.

cold-start

Full crystallization strategy for users who have no research direction at all. Covers actor profiling, landscape reconnaissance, direction narrowing, obstacle analysis, goal decomposition, and north-star synthesis. Use when the user's first message reveals zero specificity about what they want to research.

collective-adjudication

Strategy for multi-judge ranking aggregation using Condorcet, Schulze, Borda, Kemeny-Young, and Copeland methods to produce consensus rankings from diverse perspectives.

combination-evaluation

Evaluate new combinations for feasibility and novelty

combination-mapping

Systematically enumerate parameter dimensions and generate viable combinations. Orchestrates parameter extraction → value enumeration → compatibility assessment → synthesis.

combinatorial-creativity

Combinatorial Creativity Campaign — produce emergent concepts via concept blending, multi-level bisociation, and function combination (Fauconnier-Turner)

combinatorial-synthesis

Synthesize all combinatorial creativity outputs

comparative-feasibility-ranking

Compare feasibility across multiple candidates using multi-dimensional radar and weighted feasibility index.

comparative-formulation

Strategy: 构建对比性研究问题 — A vs B 的系统化比较

comparison-design

Design fair comparison experiments against baselines and competing methods

comparison-executor

Execute a pairwise comparison between two candidates, producing a judgment with winner, confidence, and reasoning.

competing-hypothesis-construction

Strategy: 为同一现象构建多个竞争假设

competing-hypothesis-generation

SOP: 为同一现象生成机制上不同的竞争假设

competing-hypothesis-matrix

Tactic: 多假设管理——生成竞争假设，设计区分性预测，构建结构化比较矩阵

competitive-intelligence

Analyze competitor IP portfolios — comparative patent portfolio reports with strategy inference. Budget: 120 patent families, 15 claim parses, 40 web searches.

competitive-move-prediction

Predict competitor progress, publications, and strategic moves

competitive-scenario

What will competitors do? — Competitive method progress prediction and time window analysis

competitor-simulation

Competitor perspective — design strategies to defeat this solution, then use attack vectors to improve it.

component-decomposition

Decompose system into functional components, identify dependencies, and surface trimming candidates.

component-surgery

Component-level surgical operations (subtract/multiply/divide/unify/redirect) from Systematic Inventive Thinking (SIT).

compressed-conflict

Generate compressed conflicts (oxymorons) from problem contradictions and extract concrete idea directions from the symbolic tension.

compute-normalization

Normalize results by compute budget (Pareto analysis)

concept-blending

Fauconnier-Turner 4-space model: Generic + Input1 + Input2 → Blended Space

concept-fan

Expand from purpose to concepts to directions to ideas (de Bono Concept Fan)

concept-fan-expansion

Expand concept fan from purpose through concepts to directions to ideas (de Bono Concept Fan).

concept-hierarchy

Build concept levels from purpose through concepts to ideas, with escape and fractionation at each level.

concept-matrix-construction

Build articles × concepts coverage matrix to visualize research landscape and identify empty cells as gap candidates.

conclusion-sensitivity

Map which assumptions are load-bearing by assessing how the conclusion changes if each assumption fails.

conclusion-sensitivity-measurement

Quantify how much conclusions change across all assumption negations and produce a sensitivity ranking.

condition-cataloging

Record evaluation conditions (data splits, hyperparams, hardware, seeds) from a paper

condition-normalization

Compare and standardize experimental conditions across papers

condition-standardization

Standardize evaluation condition differences across papers — 20 methods, 60 data points, 30 web searches budget

confidence-calibration

Calibrates confidence scores based on debate progression. Determines whether to escalate, continue, or terminate based on cumulative evidence.

conflict-resolution

How do constraints conflict with each other? — Evaporating Cloud + assumption challenging + injection to resolve constraint conflicts

conjunctive-filter

Apply conjunctive screening rules to eliminate candidates that fail any threshold.

consensus-classification

Classify items as consensus or dissensus at a given threshold.

consensus-measurement

Compute consensus score from collected judgments using the appropriate statistical method.

consensus-synthesis

Synthesize all rounds into a final consensus report documenting agreements, dissent, and process.

consequence-following

Follow a provocation's logical consequences step by step to extract viable insights and new research directions.

consistency-audit-loop

Detect preference cycles, localize inconsistent judgments, request corrections, and recompute ratings until consistency threshold is met.

consistency-check

SOP: 检验 pairwise 判断矩阵的传递一致性，识别不一致项并建议修正

consistency-checking

Pairwise consistency evaluation to reduce solution space by identifying and removing inconsistent combinations.

consistency-pair-evaluation

Evaluate pairwise value consistency (logical/empirical/normative)

constraint-analysis

What limits us — identify bottlenecks, quantify constraints, analyze dependencies, resolve conflicts before experiment execution

constraint-breaking

Orchestrate the full constraint-breaking cycle: extract conflict, challenge assumptions, project resolution

constraint-classification

Classify constraints into hard constraints, soft constraints, and assumptions.

constraint-drilling

Identify constraints, classify them by type and severity, assess removability, and design removal paths for removable constraints.

constraint-driven-ideation

Inject extreme constraints to force innovation — impossibility breeds creativity.

constraint-elicitation

Structured questioning SOP to identify practical constraints that shape the research spec. Used during spec generation.

constraint-identification

Find blockers and showstoppers using TOC, TRIZ contradiction analysis, and Pre-mortem techniques.

constraint-identification-sop

Identify constraints for a candidate using TOC, TRIZ, and Pre-mortem methods.

constraint-injection

Inject artificial constraints to force creative divergence. Generates and applies constraints (resource, time, material, audience, scale) to existing ideas to produce variants.

constraint-protocol

Inject constraints → force creative response → extract transferable principles. Orchestrates constraint injection, response generation, and principle extraction.

constraint-response

Generate creative solutions under extreme constraints — no "impossible" allowed, find a way.

constraint-synthesis

Synthesize constraint analysis into actionable report with priorities

constraint-tree-building

Build Current Reality Tree from UDEs through causal chains to core conflicts

construct-validity-assessment

Evaluate whether benchmark measures its claimed capability

constructive-rebellion

Build constructive alternatives from destructive negation. Transform violated assumptions into viable innovation directions.

contamination-audit

Detect train-test data leakage and memorization artifacts

context-checkpoint

Append research process and results to the current Phase's context file. Each append MUST contain >=500 lines of markdown covering both process and results. Use this skill at plan-designated checkpoint points — typically after each strategy completes or at key decision nodes within a research Phase.

context-init

Create a new context file for a research Phase. Called once at Phase start to initialize the file that subsequent context-checkpoint calls will append to. Use this skill whenever a new research Phase begins and a fresh context file is needed.

contradiction-derivation

Negate a claim, derive logical consequences step by step, detect whether a genuine contradiction or absurdity emerges.

contradiction-detection

Evaluate whether a derivation chain has reached a genuine contradiction, absurdity, or inconclusive state.

contradiction-identification

Identify technical and physical contradictions in a system through functional modeling and matrix analysis.

contradiction-matrix-lookup

Query the 39x39 TRIZ contradiction matrix to find recommended inventive principles for a given technical contradiction.

controlled-perturbation

Systematically vary parameters along defined axes, recording performance at each point to identify degradation thresholds.

convergence-assessment

Compare results across multiple model variants — quantitative agreement metrics and qualitative conclusion stability.

convergence-check

Evaluate whether the ranking has stabilized by analyzing rating history and computing stability metrics.