Results for “contradiction-detection”

research-synthesis

Hard Negative Mixing for Contrastive Learning

Mathematical AI interpretability with sheaf cohomology, spectral analysis, causal inference, and hallucination prevention

Detects MSBuild projects with conflicting OutputPath or IntermediateOutputPath to diagnose build failures.

Reconcile a converted or built web page against its source prototype using pixel/layout and structural content diffs to catch fidelity regressions.

Layer 4 of the keyword research pipeline. Spawns a "skeptical SEO" adversarial sub-agent to argue against every survivor of Layers 1-3. Catches mechanical-classifier blind spots — wrong SERP intent, hidden link-graph gauntlets, AIO trajectory shifts, vanity-rank metrics. Same pattern as quality-check's adversarial draft read, applied to keyword selection.

Performs differential expression analysis on bulk RNA-seq or pseudo-bulk count matrices with QC, PCA, and contrast testing.

Detect C2 beaconing patterns in network traffic using frequency analysis, jitter detection, and domain reputation to identify compromised endpoints communicating with adversary infrastructure.

Detects and ranks trending market themes by analyzing cross-sector momentum, volume, and breadth signals with lifecycle maturity assessment.

Strategic patterns for solving intractable problems through cascading approximation, self-improvement, and heterogeneous evaluation from DeepMind's AlphaGo system

Build students' capacity to compare accounts across multiple historical sources — identifying agreements, contradictions, and gaps. Use when students treat individual documents as complete answers rather than partial perspectives.

当观察到或经历某种极端转化现象，或试图主动促成根本性观念转变时

Analyze candidate task nodes, dependencies, collisions, and critical path before a consumer accepts or rejects a final DAG.

Multi-phase dialectical stress-test for HIGH-STAKES decisions only (architecture choices, irreversible product calls, strategic bets). Heavy-cost skill — do NOT use for routine questions, brainstorming, or simple tradeoffs. User must explicitly invoke or describe a decision they call "high-stakes", "irreversible", or "needs stress-testing". Triggers: "stress test this decision", "dialectic on", "challenge this thesis", "should I really".

Use to analyse billing and pricing complaints, separating genuine pricing objections from billing defects and unclear communication. Trigger for "customers complaining about price", "billing complaint analysis", "why do customers dispute their invoice", "is our pricing a problem", unexpected-charge complaints, or a pricing decision that needs evidence from support.

Find adjacent vendors and subs (not top market primes) who fill a capability gap against a displacement target using USASpending flows and SAM entity signals. Use when user defines a teaming gap and wants vault-ready partner shortlist with citations.

Use this skill for dark mode tokens, contrast, theme persistence, system preference, color scheme QA. Trigger when the task involves web design work related to Dark Mode Theme System, implementation, audits, debugging, strategy, or validation.

Audits colour decisions on a screen for contrast ratios, palette coherence, semantic meaning, and accessibility, flagging deviations and recommending specific corrections.

VS-Enhanced Literature Review Strategist - Comprehensive support for multiple review methodologies Full VS 5-Phase process: Prevents Mode Collapse and presents creative search strategies Supports: Systematic Review (PRISMA 2020), Scoping Review (JBI/PRISMA-ScR), Meta-Synthesis, Realist Synthesis, Narrative Review, Rapid Review Use when: conducting any type of literature review, systematic reviews, meta-analyses, scoping reviews, finding prior research Triggers: literature review, PRISMA, systematic review, scoping review, meta-synthesis, realist synthesis, narrative review, rapid review

Diverga Memory System v7.0 - Context-persistent research support with checkpoint auto-trigger and cross-session continuity. Triggers: memory, remember, context, recall, checkpoint, decision, persist, 기억, 맥락, 세션, 체크포인트

Identifies recurring patterns across three or more domains to extract universal principles and apply them to new problems.

The layers trade timeliness against definitiveness.

Build a weekly cadence of customer touchpoints using Opportunity Solution Trees, assumption mapping, and interview snapshots to keep product decisions grounded in evidence.

Slow down interpretation from observation to action. Use when students or adults need to examine assumptions in conflict, dialogue, or inquiry.

DeepEval — LLM evaluation framework, RAG metrics, hallucination detection, red-teaming, CI/CD integration

Use to audit how payment disputes, chargebacks and unrecognised-transaction claims are handled against scheme deadlines and evidence standards. Trigger for "audit our dispute handling", "chargeback quality review", "are we meeting scheme deadlines", unrecognised transaction claims, provisional credit decisions, or a customer complaining their dispute was rejected unfairly.

Detect and triage infrastructure drift by comparing declared Terraform state against live cloud resources using scheduled pipelines and audit logs.

Forces unrelated concepts together to spark novel solutions and emergent properties.

Detect and resolve naming collisions, overlapping intent triggers, and insufficient intent diversity across the skill library. Load when a new skill is created (called by universal-skill-creator), during improvement passes (called by improve-skills), or when the user asks to deconflict skills, check for naming collisions, audit trigger overlap, review intent coverage, find duplicate triggers, check skill names, or says "are any skills too similar", "which skills overlap", "deconflict the library", "check for confusing skill names", "intent audit".

Reverse-engineers a federal RFP we received — given the SOW/PWS and evaluation criteria already in the Theseus KG, reconstructs the CO's hidden decision tree (upstream `sow-pws-builder` 6 scope blocks + 3 intake answers), surfaces hot buttons, ghost language, discriminator hooks, missing-section signals, and CPFF-form / Section-5 / QASP / Key-Personnel traps. USE WHEN the user asks "what scope decisions did the CO already make?", "reverse engineer this RFP", "what hot buttons are hiding in this PWS?", "where are the discriminator hooks?", "did they pick CPFF completion or term form?", "anything suspiciously missing?", or any variant of decoding CO intent. Pulls `requirement`, `deliverable`, `proposal_instruction`, `evaluation_factor`, `clause`, `performance_standard` from the active workspace KG and emits a JSON envelope feeding `proposal-generator`. DO NOT USE FOR proposal prose (`proposal-generator`), pricing (`price-to-win`), clause audit (`compliance-auditor`), or sub SOW (`subcontractor-sow-builder`).

First-principles assumption auditor. Classifies each hidden assumption (fact / convention / belief / interest-driven), ranks by fragility × impact, and rebuilds conclusions from verified premises. Bilingual: auto-detects Chinese or English.

COCO: Microsoft COCO: Common Objects in Context

Merges multiple research, analysis, or brainstorming inputs into a single coherent synthesis with key insights and a recommended action.

Hierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization enforcement, and short task cycles.

Multi-perspective dialectical reasoning with cross-evaluative synthesis. Spawns parallel evaluative lenses (STRUCTURAL, EVIDENTIAL, SCOPE, ADVERSARIAL, PRAGMATIC) that critique thesis AND critique each other's critiques, producing N-squared evaluation matrix before recursive aggregation. Triggers on /critique, /dialectic, /crosseval, requests for thorough analysis, stress-testing arguments, or finding weaknesses. Implements Hegelian refinement enhanced with interleaved multi-domain evaluation and convergent synthesis.