Curiositech

Adversarial reviewer for The Federated Harbor whitepaper — the third paper in the Curiositech sequence after Anchor and Bonded Commons. Probes federation-specific threats: trust transitivity, cross-harbor token forgery, federated revocation under partition, cross-harbor Sybil, cross-domain settlement, equivocation, bond-pool draining, cold-start joining, federation-operator Sybil. Use during a versioned red-vs-white round; pairs with federated-harbor-whitehat. NOT for incident response, NOT for the Anchor or Bonded papers (use redteam-review).

The English summary is being prepared. Showing the original description.

Drafting and iterating sections of The Federated Harbor whitepaper — the third paper in the Curiositech sequence after Anchor (local identity) and Bonded Commons (local coordination), extending coordination across machines and administrative domains. Use when authoring a section, rewriting a section after a redteam/whitehat round, or composing a new chapter. NOT for marketing copy, NOT for the other two papers, NOT for production threat response.

The English summary is being prepared. Showing the original description.

Manage feature manifests for code traceability. Use when creating new features, updating existing features, checking feature health, or exploring the feature-to-code relationship. Activates for manifest validation, feature creation, changelog updates, and traceability queries.

The English summary is being prepared. Showing the original description.

Use when introducing a feature flag system, choosing between release flags / experiment flags / operational flags / kill switches / permission flags, designing percentage rollouts, building kill-switch + circuit-breaker patterns, structuring evaluation contexts (user IDs, plan tier, region), or building flag-cleanup discipline. Triggers: LaunchDarkly / GrowthBook / Unleash / Flagsmith / OpenFeature, percentage ramp, sticky bucketing, kill switch wired to alerting, "we still have flags from 2 years ago", flag debt, OpenFeature provider, evaluation context, default value on provider failure. NOT for A/B test statistical analysis (separate skill), traffic-split routing at the edge, build-time bundler defines, or environment-based config.

The English summary is being prepared. Showing the original description.

Apply practical DAG decomposition, transitive-edge reduction, and reachability indexing to dense dependency graphs. Use when low width and repeated queries justify preprocessing. NOT for cyclic graphs, one-off graph checks, or exact-minimum-chain requirements.

The English summary is being prepared. Showing the original description.

Expert landscape designer transforming yards through photo mapping, 3D visualization, seasonal planning, and deep plant knowledge. Specializes in fast-growing privacy screens (knows arborvitae pitfalls), architecture-appropriate design, outdoor living spaces, and realistic maintenance expectations. Activate on "landscape design", "yard design", "garden planning", "plant selection", "privacy screen", "outdoor living", "backyard makeover", "arborvitae", "hedge", "fast growing tree", "landscaping ideas". NOT for interior design (use interior-design-expert), hardscape construction (consult contractors), or lawn care chemicals (consult local experts).

The English summary is being prepared. Showing the original description.

Refute-before-prove research discipline: automated counterexample sweeps before any formalization, meter-integrity audits for information-bound experiments, mutation-tested model checkers, pre-registered commit-or-cut gates for speculative directions, wrong-turn reporting, and numeric-claim provenance. Use when validating any new theorem, bound, equilibrium, or security claim; when building or trusting a checker, simulator, or experiment; or when deciding whether a speculative research direction lives or dies. NOT for exploratory brainstorming, product prioritization, writing style, or literature review.

The English summary is being prepared. Showing the original description.

Build face recognition systems with InsightFace, ArcFace, enrollment pipelines, HDBSCAN clustering, and privacy-compliant architecture. Activate on: face recognition, face enrollment, face clustering, identity verification, facial search. NOT for: general object detection (computer-vision-pipeline), emotion analysis (ai-engineer).

The English summary is being prepared. Showing the original description.

Operationalizing an expungement website — user intake flows, document generation pipelines, court filing integrations, payment processing, state-by-state workflow variations, customer support for sensitive populations, and the handoff between automated systems and human legal review. Activate on 'expungement operations', 'legal tech SaaS', 'court filing integration', 'document automation pipeline', 'expungement business', 'legal service workflow', 'multi-state legal operations'. NOT for expungement law itself (use national-expungement-expert), web design (use legal-tech-web-design), or legal document drafting (use recovery-app-legal-terms).

The English summary is being prepared. Showing the original description.

Analytical methods for decomposing expert performance into cognitive and physical task components

The English summary is being prepared. Showing the original description.

Principled action selection for autonomous agents using Expected Free Energy (EFE) under the Active Inference framework. Each candidate action is scored as G(n) = w_prag * (-E[p_n] * damping) + w_epist * (-Var[p_n] * novelty(n)), where agent beliefs are maintained as per-node Beta distributions and updated via Bayesian observation. Selection is a softmax over -gamma * G, making exploration an automatic consequence of uncertainty rather than a hardcoded epsilon. Precision weights w_prag and w_epist self-adapt via surprise history, shifting the agent between exploitation and exploration regimes without any manually tuned schedule.

The English summary is being prepared. Showing the original description.

Design dashboards for migrations and runtimes. Use for authority drift, verifier status, burn-down, runtime health, or pain panels. NOT for vanity analytics, ad hoc charts, or duplicate reporting.

The English summary is being prepared. Showing the original description.

Message queues, pub/sub, event sourcing with Kafka, RabbitMQ, Redis Streams. Activate on: event-driven, message queue, pub/sub, Kafka, RabbitMQ, event bus, async messaging, dead letter queue. NOT for: CQRS projections (use cqrs-event-sourcing-architect), real-time WebSocket (use websocket-realtime-expert), observability (use observability-apm-expert).

The English summary is being prepared. Showing the original description.

Expert in temporal event detection, spatio-temporal clustering (ST-DBSCAN), and photo context understanding. Use for detecting photo events, clustering by time/location, shareability prediction, place recognition, event significance scoring, and life event detection. Activate on 'event detection', 'temporal clustering', 'ST-DBSCAN', 'spatio-temporal', 'shareability prediction', 'place recognition', 'life events', 'photo events', 'temporal diversity'. NOT for individual photo aesthetic quality (use photo-composition-critic), color palette analysis (use color-theory-palette-harmony-expert), face recognition implementation (use photo-content-recognition-curation-expert), or basic EXIF timestamp extraction.

The English summary is being prepared. Showing the original description.

Apply rapport-based elicitation to resistant or semi-cooperative humans and agents. Use when coercive prompting or brittle handoffs damage cooperation. NOT for routine cooperative tasks, pure technical debugging, or already reliable exchanges.

The English summary is being prepared. Showing the original description.

Design resilient React error handling with Error Boundaries, Sentry integration, recovery UI, retry patterns, and graceful degradation. Activate on: error boundary, crash recovery, Sentry, error fallback UI, retry logic, unhandled exceptions. NOT for: form validation errors (use form-validation-architect), API error codes (use api-architect).

The English summary is being prepared. Showing the original description.

Data structures and algorithms for AI agent episodic memory. Covers vector stores (HNSW, IVF, PQ), temporal indexing, knowledge graphs with triple stores, hierarchical summarization, forgetting curves, working/long-term/ procedural memory, and memory consolidation. Deep analysis of MemGPT/Letta, Zep/Graphiti, Mem0, and the Stanford generative agents memory architecture. Teaches the CS fundamentals behind how agents remember, retrieve, and forget. Activate on: "agent memory", "episodic memory", "vector search algorithm", "HNSW", "memory retrieval", "forgetting curve", "knowledge graph memory", "MemGPT", "Letta", "Zep", "Mem0", "memory consolidation", "temporal retrieval", "agent long-term memory", "memory layer". NOT for: conversation protocol design (use agent-conversation-protocols), agent infrastructure selection (use agentic-infrastructure-2026), building RAG pipelines (use ai-engineer).

The English summary is being prepared. Showing the original description.

Environment configuration manager for 12-factor config, feature flags, and multi-environment management. Activate on: environment variables, ConfigMap, feature flags, 12-factor config, dotenv management, config per environment, runtime config. NOT for: secret storage (use secret-management-expert), IaC provisioning (use terraform-module-builder), CI/CD variables (use github-actions-pipeline-builder).

The English summary is being prepared. Showing the original description.

Decision-theoretic framework for agents embedded within the environments they model and act upon

The English summary is being prepared. Showing the original description.

Draft professional emails for various contexts including business, technical, and customer communication. Use when the user needs help writing emails or composing professional messages.

The English summary is being prepared. Showing the original description.

Manage DAG execution lifecycles including start, stop, pause, resume, and cleanup. Activate on 'execution lifecycle', 'stop execution', 'abort DAG', 'graceful shutdown', 'kill process'. NOT for cost estimation, DAG building, or skill selection.

The English summary is being prepared. Showing the original description.

Expo managed workflow expert for EAS Build, Submit, Update, config plugins, and custom dev clients. Activate on: Expo project, EAS Build, EAS Update, config plugin, expo-dev-client, Expo Router, Expo SDK 52, app.json configuration. NOT for: bare React Native (use react-native-architect), native module authoring (use react-native-architect), Flutter (use flutter-bloc-state-manager).

The English summary is being prepared. Showing the original description.

Audit whether a "current product focus receipt" (Decision/Now/Why-now/Evidence/Not-now/Cut-suspend/First-visible-proof/ Acceptance-gate/Kill-revisit-trigger/Owner/Review-date) and the work order it gates state a real, testable decision and a real agent launch — not planning-placeholder prose that sounds like an assignment but can't be proven. Use when deciding whether to launch an agent chain against a milestone or a stated "focus," when a work order lacks explicit input/output/owner/proof-gate, or when an acceptance gate would only prove a cached UI state instead of daemon truth. NOT for distinguishing roadmap items from energy-driven sidequests (legible-roadmap-with-sidequests), reviewing a PRD/prototype for product-completeness gaps like cold start or pricing (product-reality-reviewer), or accepting already-finished work against a personal acceptance bar (port-daddy-user-surrogate-pm-review).

The English summary is being prepared. Showing the original description.

Apply practical DAG decomposition, transitive-edge reduction, and reachability indexing to dense dependency graphs. Use when low width and repeated queries justify preprocessing. NOT for cyclic graphs, one-off graph checks, or exact-minimum-chain requirements.

The English summary is being prepared. Showing the original description.