Claude Skills by anubhavg-icpl

PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading. Use when you need help with pytorch patterns.

>. Use when you need help with quality nonconformance.

RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration. Use when you need help with ralphinho rfc pipeline.

Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases. Use when you need help with regex vs llm structured text.

Best practices for Remotion - Video creation in React. 29 domain-specific rules covering 3D, animations, audio, captions, charts, transitions, and more. Use when you need help with remotion video creation.

Cross-stack source code asset audit — classifies every file, detects embedded third-party libraries, and delivers actionable four-level verdicts per module with interactive HTML reports. Use when you need help with repo scan.

Evidence-first current-state research workflow for ECC. Use when the user wants fresh facts, comparisons, enrichment, or a recommendation built from current public evidence and any supplied local context.

>. Use when you need help with returns reverse logistics.

Scan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files. Use when you need help with rules distill.

Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications. Use when you need help with rust patterns.

Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology. Use when you need help with rust testing.

Use this skill to prevent destructive operations when working on production systems or running agents autonomously. Use when you need help with safety guard.

Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships. Use when you need help with santa method.

Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent. Use when you need help with search first.

Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings. Use when you need help with security bounty hunter.

Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.

Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions. Use when you need help with security scan.

Audit, plan, and implement SEO improvements across technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy. Use when the user wants better search visibility, SEO remediation, schema markup, sitemap/robots work, or keyword mapping.

Visualize whether skills, rules, and agent definitions are actually followed — auto-generates scenarios at 3 prompt strictness levels, runs agents, classifies behavioral sequences, and reports compliance rates with full tool call timelines. Use when you need help with skill comply.

Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.

Weighted social-graph ranking for warm intro discovery, bridge scoring, and network gap analysis across X and LinkedIn. Use when the user wants the reusable graph-ranking engine itself, not the broader outreach or network-maintenance workflow layered on top of it.

Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.

Spring Security best practices for authn/authz, validation, CSRF, secrets, headers, rate limiting, and dependency security in Java Spring Boot services. Use when you need help with springboot security.

Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.

Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR. Use when you need help with springboot verification.

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction. Use when you need help with strategic compact.

Thread-safe data persistence in Swift using actors — in-memory cache with file-backed storage, eliminating data races by design. Use when you need help with swift actor persistence.

Swift 6.2 Approachable Concurrency — single-threaded by default, @concurrent for explicit background offloading, isolated conformances for main actor types. Use when you need help with swift concurrency 6 2.

Protocol-based dependency injection for testable Swift code — mock file system, network, and external APIs using focused protocols and Swift Testing. Use when you need help with swift protocol di testing.

SwiftUI architecture patterns, state management with @Observable, view composition, navigation, performance optimization, and modern iOS/macOS UI best practices. Use when you need help with swiftui patterns.

Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

Interactive agent picker for composing and dispatching parallel teams. Use when you need help with team builder.

Evidence-first repo execution workflow for ECC. Use when the user wants a command run, a repo checked, a CI failure debugged, or a narrow fix pushed with exact proof of what was executed and verified.

>-. Use when you need help with token budget advisor.

Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen recording, or tutorial video of a web application. Produces WebM videos with visible cursor, natural pacing, and professional feel.

Operate notifications as one ECC-native workflow across GitHub, Linear, desktop alerts, hooks, and connected communication surfaces. Use when the real problem is alert routing, deduplication, escalation, or inbox collapse.

A comprehensive verification system for Claude Code sessions. Use when you need help with verification loop.

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...

Translate visa application documents (images) to English and create a bilingual PDF with original and translation. Use when you need help with visa doc translate.

Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.

X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.

Design a minimal agent economy — identity, credit attribution, payment mechanism, reputation. Picks the smallest stack that solves the user's multi-agent incentive problem. Use when you need help with economy designer.

Produce a full Phase 13 ecosystem architecture given a product need; name primitives, security posture, telemetry, and packaging. Use when you need help with ecosystem blueprint.

Map an alignment claim or evaluation to the organisation, methodology, and cross-checks. Use when you need help with ecosystem map.

Expert in edge computing and serverless at the edge. Use when you need help with edge computing.

Pick an edge inference target (Apple ANE, Qualcomm Hexagon, WebGPU/WebLLM, NVIDIA Jetson) and matching quantization format given device, model, and latency budget. Use when you need help with edge target picker.

Plan an image-editing pipeline from source + edit description to a ready-to-ship output. Use when you need help with editing pipeline.

|. Use when you need help with editorial burgundy principles template.

Expert in the Editorial design system - Magazine-inspired editorial layout with refined serif typography, structured grids, and elegant reading experiences. Use when building UI components, applying design tokens, or implementing visual styles for editorial.