Claude Skills by anubhavg-icpl

Design a dialogue state tracker — schema, extractor, update policy, evaluation. Use when you need help with dst designer.

Triage a capability claim or incident report across the four CBRN domains. Use when you need help with dual use triage.

Plan a pipeline parallelism strategy (1F1B, Zero Bubble, DualPipe, DualPipeV) for a training cluster. Use when you need help with dualpipe planner.

Expert in DuckDB embedded analytics, extensions, and persistent storage. Use when working with duckdb for data processing, streaming, or analytics.

Expert in the Duolingo design system - Language-learning platform. Bright owl green, chunky shadows, gamified joy. Use when building UI components, applying design tokens, or implementing visual styles for duolingo.

Pick full-duplex (Moshi) vs pipeline (VAD + STT + LLM + TTS) architecture for a voice-agent workload. Use when you need help with duplex pipeline.

Review a proposed long-running agent deployment for correct durable-execution shape (activities, determinism, checkpoint backend, human-input state, HITL-on-resume). Use when you need help with durable execution review.

Expert in Microsoft Dynamics 365 development, Power Platform, and Dataverse. Use when you need help with dynamics 365.

Produce a staged EAGLE-3 speculative-decoding rollout plan that measures acceptance rate alpha on real traffic before shipping. Use when you need help with eagle3 rollout.

Pick and tune a speculative decoding strategy (vanilla / Medusa / EAGLE-1/2/3 / lookahead) for a new inference workload. Use when you need help with eagle3 tuner.

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when you need help with accessibility.

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when you need help with agent eval.

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when you need help with agent harness construction.

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when you need help with agent introspection debugging.

Add x402 payment execution to AI agents — per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents need to pay for APIs, services, or other agents.

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when you need help with agentic engineering.

Engineering operating model for teams where AI agents generate a large share of implementation output. Use when you need help with ai first engineering.

Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code. Use when you need help with ai regression testing.

Clean Architecture patterns for Android and Kotlin Multiplatform projects — module structure, dependency rules, UseCases, Repositories, and data layer patterns. Use when you need help with android clean architecture.

Build a new API connector or provider by matching the target repo's existing integration pattern exactly. Use when adding one more integration without inventing a second architecture.

REST API design patterns including resource naming, status codes, pagination, filtering, error responses, versioning, and rate limiting for production APIs. Use when building UI with api design language and visual style.

Capture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is. Use when you need help with architecture decision records.

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

Evidence-first automation inventory and overlap audit workflow for ECC. Use when the user wants to know which jobs, hooks, connectors, MCP servers, or wrappers are live, broken, redundant, or missing before fixing anything.

Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. Replaces standalone agent frameworks (Hermes, AutoGPT) by leveraging Claude Code's native crons, dispatch, MCP tools, and memory. Use when the user wants continuous autonomous operation, scheduled tasks, or a self-directing agent loop.

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems. Use when you need help with autonomous loops.

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes. Use when you need help with backend patterns.

Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives. Use when you need help with benchmark.

>-. Use when you need help with blueprint.

Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then reuse that profile across content, outreach, and social workflows. Use when the user wants voice consistency without generic AI writing tropes.

Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features. Use when you need help with browser qa.

Bun as runtime, package manager, bundler, and test runner. When to choose Bun vs Node, migration notes, and Vercel support. Use when you need help with bun runtime.

Use this skill to monitor a deployed URL for regressions after deploys, merges, or dependency upgrades. Use when you need help with canary watch.

>. Use when you need help with carrier relationship management.

Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions. Use when you need help with ck.

Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports. Use when you need help with claude devfleet.

Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI in an inconsistent state. Use when: systematic debugging found no bugs but users report broken buttons, or after any major refactor touching shared state stores.

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads. Use when you need help with clickhouse io.

Create CodeTour `.tour` files — persona-targeted, step-by-step walkthroughs with real file and line anchors. Use for onboarding tours, architecture walkthroughs, PR tours, RCA tours, and structured "explain how this works" requests.

Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md. Use when joining a new project or setting up Claude Code for the first time in a repo.

Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns. Use when you need help with coding standards.

Compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI. Use when you need help with compose multiplatform patterns.

Interactive installer for Everything Claude Code — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files. Use when you need help with configure ecc.

Reorganize the user's X and LinkedIn network with review-first pruning, add/follow recommendations, and channel-specific warm outreach drafted in the user's real voice. Use when the user wants to clean up following lists, grow toward current priorities, or rebalance a social graph around higher-signal relationships.

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation. Use when you need help with content hash cache pattern.

Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations. Use when you need help with context budget.

Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls. Use when you need help with continuous agent loop.

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination. Use when you need help with continuous learning v2.