數據與 AI

Evaluation and reporting for code quality, performance, security, architecture, team processes, AI/LLM outputs, A/B tests, ROI analysis, and compliance. Scoring systems, benchmarking, dashboard creation, and multi-format report generation (PDF, HTML, Markdown, JSON).

Plan multi-week Twitter/X campaigns for newsletter growth, content launches, or audience building.Use when creating content calendars, planning thread series, coordinating cross-platform promotion,or designing engagement strategies. Includes posting cadence, "reply guy" tactics, and campaigntemplates optimized for the December 2025 algorithm.

Four-phase debugging: root cause → patterns → hypothesis → implement. For complex bugs, test failures, multi-component issues. NOT for obvious syntax errors.

This skill should be used when setting up, managing, or optimizing Grail miners on Bittensor Subnet 81. Use it for GRAIL protocol tasks including miner setup, R2 storage configuration, model checkpoint management, GRPO rollout generation, performance optimization, competitive monitoring, and troubleshooting common issues like CUDA errors, upload failures, or low scores. Essential for miners working with verifiable post-training, SAT/GSM8K environments, or understanding the GRAIL incentive mechanism to improve competitiveness.

New agent startup checklist for Agent Mail and Beads. Use when starting a new agent session, when the user says "prime" or "startup", or when beginning work on a multi-agent project.

LLM evaluation and prompt optimization with Evidently.ai. Covers textdescriptors, dataset metrics, LLM-as-a-Judge patterns, and automatedprompt optimization for classification and generation tasks.

Use when facing 3+ independent failures that can be investigated without shared state or dependencies. Dispatches multiple Claude agents to investigate and fix independent problems concurrently.

Use when creating or editing reveal.js presentations, or when user mentions slides, presentations, reveal.js, code examples in slides, speaker notes, or slide design - enforces Tailwind CSS, proper code sizing, progressive reveal, semantic colors, and timing markers

Apache Airflow, dbt, Prefect, Dagster, and modern data orchestration for production data pipelines

Advanced Maximum Likelihood phylogenetics with model selection (AIC/BIC), tree search algorithms (NNI/SPR/TBR), and performance optimization (Numba/GPU)

Facilitates creative ideation sessions for mobile and web app features, generating structured ideas with user stories, technical considerations, and implementation suggestions. Use when planning new features, exploring product direction, generating app ideas, feature discovery, product brainstorming, or when user mentions 'brainstorm', 'ideate', 'app ideas', or 'feature suggestions'.

Build mithril-cache for torch.compile caching. Use when implementing content-addressable storage, cache keys, eviction, or framework hooks.

Automate Splunk queries and analyze results using Chrome DevTools MCP. Use when the user wants to run Splunk searches, export log data, or analyze Splunk results. Triggers on requests like "check error rates", "search Splunk for X", "run a Splunk query", "analyze logs from Splunk", or "find errors in payment-service".

Automatically adds timestamps and execution duration to all Claude responses

Implement event-driven communication using BlueprintEventBus for cross-module coordination. Use this skill when modules need to communicate without tight coupling, broadcasting domain events (task.created, member.added), subscribing to events with proper lifecycle management, and implementing event-driven workflows. Ensures events follow naming conventions ([module].[action]), include Blueprint context, and use takeUntilDestroyed() for automatic cleanup.

Security vulnerability scanning, secret detection, dependency auditing, and OWASP best practices. Use when performing security audits, scanning for vulnerabilities, detecting exposed secrets, checking dependencies, validating security headers, implementing OWASP patterns, or when user mentions security, vulnerabilities, secrets, CVE, OWASP, npm audit, security headers, or penetration testing.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks | Sử dụng khi: tạo Word, chỉnh sửa docx, tài liệu văn bản, track changes

Build computer vision solutions - image classification, object detection, and transfer learning

Expert on integrating Shelby Protocol decentralized storage into applications. Helps with use case evaluation, architecture design, migration strategies, cost optimization, performance tuning for video streaming, AI training, data analytics, content delivery, and read-heavy workloads. Triggers on keywords integrate Shelby, decentralized storage integration, video streaming storage, AI training data, data analytics storage, migration to Shelby, storage architecture, content delivery, Shelby use case.

Extract text and data from PDF documents