← all publishers

BejeweledMe

@bejeweledme source repo

Report this profile Claim this profile

• 46 skills
• 0 followers
• 7 hours ago last updated

1. ▌
   QA Testing · bejeweledme bundle

   Use when designing, reviewing, validating, debugging, or improving classic software QA strategy and automated test suites. Trigger for autotests, unit tests, integration tests, contract tests, end-to-end tests, test pyramid decisions, flaky tests, test doubles, mocks, fakes, stubs, test coverage, test maintainability, CI/CD quality gates, release validation, exploratory testing, and production feedback for non-LLM software systems.
   0 installs
2. ▌
   LLM Council · bejeweledme bundle

   Run, design, review, or debug multi-model councils using independent first answers, peer critique, and synthesis traceable to intermediate outputs.
   0 installs
3. ▌
   Swift Skill · bejeweledme bundle

   Use for implementation and review of native iOS applications or modules built with Swift, SwiftUI, UIKit, SwiftData, and Apple frameworks. Use directly for a known native stack; use ios-app-development first when choosing Swift versus Flutter or defining a mixed-stack boundary.
   0 installs
4. ▌
   Flutter Skill · bejeweledme bundle

   Use for Flutter application architecture, implementation, and review, including Dart/UI/state/data work and iOS delivery concerns. Use directly for a known Flutter stack; use ios-app-development first when choosing Flutter versus native Swift or defining a mixed-stack boundary.
   0 installs
5. ▌
   Humanize Text · bejeweledme

   Make Russian or English prose sound natural and less formulaic while preserving meaning and the author's voice. Use when asked to humanize text, make it less AI-sounding, remove robotic phrasing, or apply a natural-voice pass to a draft. A style companion to the primary writing or editing skill, not an authorship detector.
   0 installs
6. ▌
   System Design · bejeweledme bundle

   Design, review, and evolve classical software and distributed service architecture: boundaries, data authority, capacity, consistency, caching, queues/streams, replication, sharding, recovery architecture, security, and safe migration. Use for architecture documents, production-readiness reviews, and system design interviews. Route HTTP/OpenAPI artifact and wire compatibility work to api-contract-engineering.
   0 installs
7. ▌
   Product Design · bejeweledme bundle

   Use for user-centered product discovery, UX, product requirements, AI/ML experiences, design systems, and hypothesis validation. Own the path from user outcome and evidence to an experience and measurable product change; use business-product-consulting for strategy, operating-model, or executive tradeoff decisions.
   0 installs
8. ▌
   Agent LLM Evals · bejeweledme bundle

   Design, debug, or review LLM and agent evaluations: task datasets, tool/state grading, calibrated judges, traces, candidate selection, repeated trials, and release gates. Use when evaluating model, prompt, tool, or workflow changes; domain owners define the behavior being measured.
   0 installs
9. ▌
   Agent Workflows · bejeweledme bundle

   Design, implement, operate, or debug LLM agent execution: pipeline-versus-agent decisions, single- or multi-agent orchestration, tool and MCP contracts, durable state and memory, checkpoints, retries, handoffs, stopping, and scaffold evolution. Use llm-system-design for product composition and agent-llm-evals for evaluation.
   0 installs
10. ▌
    RAG Engineering · bejeweledme bundle

    Use when designing, implementing, reviewing, debugging, evaluating, or operating retrieval-augmented generation systems. Trigger for ingestion, OCR, chunking, metadata and provenance, embeddings, sparse/dense/hybrid retrieval, ANN, reranking, context assembly, citations, abstention, GraphRAG, agentic retrieval, index versioning, or stage-by-stage RAG diagnosis.
    0 installs
11. ▌
    Security Review · bejeweledme bundle

    Assess security claims for a scoped design, application change, release, repository, or OSS dependency. Use for abuse-path review, application-verification evidence, supplier posture, and security findings or release recommendations; ordinary maintainability review belongs to software-engineering.
    0 installs
12. ▌
    Data Engineering · bejeweledme bundle

    Build, diagnose, and recover batch and streaming data pipelines: event-time windows, CDC/outbox consumption, retry-safe orchestration, replay/backfill, dataset publication, quality, freshness, lineage, and Iceberg/Parquet/Arrow boundaries. Database engine tuning and model or retrieval semantics have separate owners.
    0 installs
13. ▌
    Ml System Design · bejeweledme bundle

    Design, review and debug predictive/classical ML systems: whether ML is needed, build or buy, metrics, data, validation, baselines, lifecycle pipelines, predictive serving, benchmark claims, placement, A/B versus canary, monitoring, drift, degradation and ownership. Includes ML system design interviews. Modality-specific CV/LLM work and neural execution have dedicated owners.
    0 installs
14. ▌
    Execution Writing · bejeweledme

    Create status reports, decision memos, and engineering execution plans that make progress, choices, ownership, dependencies, risks, and next actions clear.
    0 installs
15. ▌
    LLM System Design · bejeweledme bundle

    Use when designing, reviewing, or evolving an LLM product as a system. Trigger for prompt versus RAG versus agent versus adaptation decisions, model or provider routing, prompt and context architecture, token/cost/latency budgets, degradation and fallbacks, tenant isolation, and versioned LLM releases. Not for detailed retrieval, agent-loop, model-training, eval-harness, security-test, or GPU-runtime implementation.
    0 installs
16. ▌
    Technical Writing · bejeweledme bundle

    Create or revise technical documentation, architecture and design docs, API references, runbooks, troubleshooting guides, benchmarks, experiment reports, and engineering analyses.
    0 installs
17. ▌
    AI Platform Llmops · bejeweledme bundle

    Build, diagnose, and operate shared AI infrastructure for predictive and GenAI serving (KServe, Triton, vLLM Production Stack), accelerator capacity, replica controllers, model registry releases, training-job placement, and edge fleet rollout. Runtime tuning and training update semantics stay with their execution owners.
    0 installs
18. ▌
    Telegram Mini Apps · bejeweledme bundle

    Use when designing, building, reviewing, validating, debugging, deploying, or operating Telegram Mini Apps and Telegram Web Apps. Trigger for Telegram bot + mini app architecture, launch modes, BotFather setup, initData authentication, backend validation, HMAC/Ed25519 checks, tma.js, Telegram WebApp API, native buttons, theme/viewport/safe area, CloudStorage/DeviceStorage/SecureStorage, biometrics, sensors, location, Telegram Stars/payments, WebView testing, mobile debugging, production readiness, security reviews, and long-term maintenance.
    0 installs
19. ▌
    Audience Adaptation · bejeweledme bundle

    Adapt a primary informational artifact for technical, nontechnical, executive, or execution readers. Use alongside the skill that owns the source, research, explanation, decision, edit, or deliverable; it is a reader-model companion rather than a primary content operation.
    0 installs
20. ▌
    Information Editing · bejeweledme bundle

    Edit existing informational text through copyediting, faithful rewrite, audience adaptation, restructuring, or compression.
    0 installs
21. ▌
    Information Writing · bejeweledme bundle

    Write substantive user-facing answers and informational artifacts in Russian or English, using this as the shared writing discipline. Route source-bound summaries, research, explanations, decisions, edits, technical documents, execution artifacts, and presentations to their primary skill while retaining the task contract and reader calibration here.
    0 installs
22. ▌
    IOS App Development · bejeweledme bundle

    Use for cross-stack iOS product and platform decisions: select Swift, Flutter, or a mixed boundary; shape iOS architecture, native capabilities, privacy, lifecycle, integration, release, and long-term ownership. For framework-specific implementation after stack selection, use swift-skill or flutter-skill.
    0 installs
23. ▌
    Database Engineering · bejeweledme bundle

    Design, diagnose, and change relational and embedded databases, especially PostgreSQL and SQLite. Use for constraints, transaction anomalies, locks, SQL plans and indexes, schema changes, maintenance, and restore. Store topology and cross-system guarantees belong to system-design.
    0 installs
24. ▌
    Software Engineering · bejeweledme bundle

    Design and review long-lived software changes: maintainability, code health, Hyrum's Law, tests, review, builds, dependencies, static analysis, CI, deprecation, migrations, and release evidence. Owns cross-cutting change lifecycle; framework/runtime implementation belongs to the language or frontend owner.
    0 installs
25. ▌
    Genai Security Testing · bejeweledme bundle

    Use when threat-modeling, hardening, or authorized testing of LLM, RAG, and agent systems the user controls. Trigger for prompt or indirect injection, RAG ACL or tenant leakage, tool/data-flow misuse, excessive agency, guardrails, sandboxing, least privilege, service identities, self-test/red-team planning, false-refusal evaluation, security evidence, stop conditions, and regression loops.
    0 installs
26. ▌
    Information Explanation · bejeweledme bundle

    Explain a concept, mechanism, system, or distinction so the reader builds a correct and usable mental model.
    0 installs
27. ▌
    Neural Training Systems · bejeweledme bundle

    Diagnose, optimize, scale, or recover neural training runs: OOM, slow steps, mixed precision, gradient accumulation, DDP/FSDP, collectives, and checkpoint consistency. Owns training execution; model/objective choices belong to modeling skills and serving execution to inference skills.
    0 installs
28. ▌
    API Contract Engineering · bejeweledme bundle

    Author, diagnose, and evolve HTTP API contracts: OpenAPI, schema/reference context, serialization, HTTP outcomes, errors, and provider/consumer compatibility. Use for contract artifacts and observable interoperability; system-design owns service boundaries.
    0 installs
29. ▌
    Information Presentation · bejeweledme bundle

    Create presentation and slide content for live delivery or independent reading, with supported claims, informative visuals, and a decision- or learning-oriented narrative.
    0 installs
30. ▌
    Web Frontend Engineering · bejeweledme bundle

    Build and debug browser UI, including React and Next.js state, rendering, hydration, route loading, performance, accessible interaction, and browser checks. Product discovery and interaction acceptance belong to product-design.
    0 installs
31. ▌
    Computer Vision Evaluation · bejeweledme bundle

    Use when designing, reviewing, validating, or debugging computer-vision evaluation. Trigger for product-linked and task metrics, thresholds, calibration, class/scale/source slices, visual error analysis, imbalance, robustness, corruptions and OOD, regression suites, human review, and release gates. Not for training procedure, annotation operations, or generic LLM and agent evals.
    0 installs
32. ▌
    Information Source Summary · bejeweledme

    Faithfully summarize supplied articles, lectures, transcripts, or documents without silently adding external research.
    0 installs
33. ▌
    LLM Inference Optimization · bejeweledme bundle

    Diagnose and optimize self-hosted LLM runtime latency, goodput, cost, and capacity through prefill/decode profiling, KV cache, batching, admission, quantization, and inference parallelism. Use for execution bottlenecks and runtime scaling signals; replica provisioning and fleet placement belong to ai-platform-llmops.
    0 installs
34. ▌
    Python Backend Engineering · bejeweledme bundle

    Build, review, and debug Python services and background tasks using Django, FastAPI, asyncio, Pydantic, SQLAlchemy, Alembic, or Celery. Covers validation, transactions, resource lifetime, side effects, and Python packaging/tests; HTTP contract compatibility and database engine design have separate owners.
    0 installs
35. ▌
    Business Product Consulting · bejeweledme bundle

    Use for product and engineering strategy, business cases, market or portfolio choices, operating-model and ownership decisions, executive recommendations, and structured tradeoff analysis. For user discovery, UX, design systems, or product requirements, use product-design as the primary owner.
    0 installs
36. ▌
    Nlp Modeling And Adaptation · bejeweledme bundle

    Use when choosing or adapting a text model. Trigger for rules, TF-IDF or BM25 baselines, encoder or reranker selection, embeddings, BERT-style discriminative models, seq2seq or decoder LLMs, tokenizer changes, continued pretraining, SFT, PEFT/LoRA/QLoRA, preference optimization, distillation, or training-data and adaptation evaluation. Not for LLM product topology, detailed RAG, agent loops, eval harnesses, or serving bottlenecks.
    0 installs
37. ▌
    Platform Devops Engineering · bejeweledme bundle

    Provision, deliver, debug, or recover infrastructure through Terraform/OpenTofu state transitions, container builds, Kubernetes, GitOps reconciliation, CI identity, and deployment admission. Own apply mechanisms; application behavior and live reliability acceptance stay with their engineering owners.
    0 installs
38. ▌
    Sre Reliability Engineering · bejeweledme bundle

    Define and operate user reliability through SLIs/SLOs, error budgets, observability, alerting, incidents, on-call, recovery, Kubernetes reliability, and resilience validation. Use for production-readiness and reliability decisions; infrastructure provisioning and reconciliation belong to platform engineering.
    0 installs
39. ▌
    Information Decision Support · bejeweledme

    Compare realistic alternatives under constraints and produce a defensible recommendation with trade-offs and next steps.
    0 installs
40. ▌
    Computer Vision System Design · bejeweledme bundle

    Use when framing, designing, reviewing, or decomposing a computer-vision product or pipeline. Trigger for visual task formulation, sensor and input contracts, classification/detection/segmentation/retrieval/OCR/video decomposition, deterministic versus learned stage boundaries, end-to-end topology, hardware constraints, fallbacks, and build-versus-buy decisions. Route model-family selection, data, evaluation, and measured runtime work to the dedicated CV skills.
    0 installs
41. ▌
    Information Research Synthesis · bejeweledme

    Research a question across sources and synthesize evidence into a decision-useful finding, survey, or report.
    0 installs
42. ▌
    Application Security Engineering · bejeweledme bundle

    Design, implement, or remediate general application security controls: code-linked threat models, authentication and recovery, sessions, authorization and tenant isolation, OAuth/JWT, browser/API/uploads, secrets and data protection, secure failure, dependency policy, or ASVS implementation. Independent assessments belong to security-review; specialist LLM/RAG/agent threat modeling, security design/review, hardening and authorized testing belong to genai-security-testing.
    0 installs
43. ▌
    Computer Vision Data And Labeling · bejeweledme bundle

    Use when designing, collecting, labeling, validating, versioning, or improving computer-vision datasets. Trigger for annotation schemas and QA, source/camera/scene coverage, class and object balance, duplicates, grouped splits, temporal or spatial leakage, augmentation, active learning, auto-labeling, synthetic data, provenance, and production data feedback. Not for choosing model architectures or declaring model quality.
    0 installs
44. ▌
    Node Typescript Backend Engineering · bejeweledme bundle

    Build, review, and debug Node.js/TypeScript backend services, including async lifecycle, streams, workers, Fastify/Express adapters, and runtime validation. Browser rendering belongs to web-frontend-engineering; HTTP/OpenAPI artifacts to api-contract-engineering; engine proof to database-engineering.
    0 installs
45. ▌
    Computer Vision Modeling And Training · bejeweledme bundle

    Use when choosing, training, adapting, or debugging computer-vision models for image classification, metric learning and retrieval, detection, segmentation, OCR and documents, multimodal vision, or video and tracking. Covers classical feature-based baselines, deep and foundation models, transfer learning, fine-tuning, PEFT, self-supervised learning, objectives, and reproducible experiments. Not for dataset governance, release metrics, or serving optimization.
    0 installs
46. ▌
    Computer Vision Inference Optimization · bejeweledme bundle

    Use when profiling, deploying, or optimizing computer-vision inference pipelines for latency, throughput, memory, cost, FPS, or device constraints. Trigger for decode/preprocess/model/postprocess/index stages, tiling, batching, export and runtime compatibility, precision and quantization, streaming video, frame timing, and capacity planning. Not for model training or generic service and SRE ownership.
    0 installs