Claude Skills by anubhavg-icpl

Security audit orchestrator - parallel dependency scanning, SAST pattern detection, auth/config review. Dispatches 3 audit agents simultaneously, consolidates into OWASP-mapped severity report. Triggers on: security review, security audit, OWASP, XSS, SQL injection, CSRF, authentication, authorization, secrets management, input validation, secure coding, vulnerability scan, dependency audit. Use when you need help with security ops.

Set tool permissions for Claude Code. Configures allowed commands, rules, and preferences in .claude/ directory. Triggers on: setperms, init tools, configure permissions, setup project, set permissions, init claude. Use when you need help with setperms.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when you need help with skill creator.

Generate PhD-level expert agent prompts for Claude Code. Creates comprehensive 500-1000 line agents with detailed patterns, code examples, and best practices. Triggers on: spawn agent, create agent, generate expert, new agent, agent genesis. Use when you need help with spawn.

Quick reference for common SQL patterns, CTEs, window functions, and indexing strategies. Triggers on: sql patterns, cte example, window functions, sql join, index strategy, pagination sql. Use when you need help with sql ops.

Patterns for SQLite databases in Python projects - state management, caching, and async operations. Triggers on: sqlite, sqlite3, aiosqlite, local database, database schema, migration, wal mode. Use when you need help with sqlite ops.

Search code by AST structure using ast-grep. Find semantic patterns like function calls, imports, class definitions instead of text patterns. Triggers on: find all calls to X, search for pattern, refactor usages, find where function is used, structural search, ast-grep, sg. Use when you need help with structural search.

Transfer Claude Desktop Code-tab sessions between Claude accounts — copy (default) or move (--move) the session metadata file so the session shows up in another account's left-hand sidebar (the session picker on the left side of Desktop's Code tab). Two natural framings: push (run while still on your current near-limit account, send sessions to the next one, then Logout/Login as the natural switch) or pull (after switching accounts, bring earlier sessions into the now-active one). Push is the...

Tailwind CSS utility patterns, responsive design, component patterns, v4 migration, and configuration. Use for: tailwind, tailwindcss, utility classes, responsive design, dark mode, tailwind v4, tailwind config, tw, container queries, @apply, prose, typography, animation.

Run project commands with just. Check for justfile in project root, list available tasks, execute common operations like test, build, lint. Triggers on: run tests, build project, list tasks, check available commands, run script, project commands. Use when you need help with task runner.

Technical debt detection and remediation. Run at session end to find duplicated code, dead imports, security issues, and complexity hotspots. Triggers: 'find tech debt', 'scan for issues', 'check code quality', 'wrap up session', 'ready to commit', 'before merge', 'code review prep'. Always uses parallel subagents for fast analysis. Use when you need help with techdebt.

Generate tests with expert routing, framework detection, and auto-TaskCreate. Triggers on: generate tests, write tests, testgen, create test file, add test coverage. Use when you need help with testgen.

Cross-language testing strategies and patterns. Triggers on: test pyramid, unit test, integration test, e2e test, TDD, BDD, test coverage, mocking strategy, test doubles, test isolation. Use when you need help with testing ops.

Recommend the right agents and skills for any task. Covers both heavyweight agents (Task tool) and lightweight skills (Skill tool). Triggers on: which agent, which skill, what tool should I use, help me choose, recommend agent, find the right tool. Use when you need help with tool discovery.

TypeScript type system, generics, utility types, strict mode, and ecosystem patterns. Use for: typescript, ts, type, generic, utility type, Partial, Pick, Omit, Record, Exclude, Extract, ReturnType, Parameters, keyof, typeof, infer, mapped type, conditional type, template literal type, discriminated union, type guard, type assertion, type narrowing, tsconfig, strict mode, declaration file, zod, valibot.

Django Unfold admin theme - build, configure, and enhance modern Django admin interfaces with Unfold. Use when working with: (1) Django admin UI customisation or theming, (2) Unfold ModelAdmin, inlines, actions, filters, widgets, or decorators, (3) Admin dashboard components and KPI cards, (4) Sidebar navigation, tabs, or conditional fields, (5) Any mention of 'unfold', 'django-unfold', or 'unfold admin'. Covers the full Unfold feature set: site configuration, actions system, display decorato...

Vue 3 development patterns, Composition API, Pinia state management, Vue Router, and Nuxt 3. Use for: vue, vuejs, composition api, pinia, vue router, nuxt, nuxt3, script setup, composable, reactive, defineProps, defineEmits, defineModel, v-model, provide inject, vue3.

code-commenter. Use when you need help with code commenter.

code-educator. Use when you need help with code educator.

Deep expertise in code-specific embedding models — voyage-code-3, jina-embeddings-v2-base-code, jina-code-embeddings, CodeRankEmbed, GraphCodeBERT. Use when implementing vector search, embeddings storage, or similarity queries with code embed.

Expert in code quality metrics, static analysis, and codebase health assessment. Use when you need help with code metrics.

Expert in migrating codebases between languages, frameworks, and platforms. Use when you need help with code migration.

Teaches code review skills through practice and constructive feedback examples. Use when you need help with code review teacher.

Build a cross-repo semantic search system with AST-aware chunking, hybrid retrieval, incremental re-index, and cited answers. Use when you need help with codebase rag.

Pick a neural audio codec (EnCodec / DAC / SNAC / Mimi) for a given generative or compression task. Use when you need help with codec picker.

Audit a proposed coding-agent scaffold (retrieval, verifier loop, sandbox, benchmark fit) before adopting it for production code changes. Use when you need help with coding scaffold audit.

CogVideoX, Mochi-1, Hunyuan, LTX video diffusion - training and inference patterns. Use when working with multimodal AI (images, audio, video) using cog video.

Expert in the Cohere design system - Enterprise AI platform. Vibrant gradients, data-rich dashboard aesthetic. Use when building UI components, applying design tokens, or implementing visual styles for cohere.

Expert in the Coinbase design system - Crypto exchange. Clean blue identity, trust-focused, institutional feel. Use when building UI components, applying design tokens, or implementing visual styles for coinbase.

ColBERT v2 / late interaction retrieval, MaxSim, RAGatouille, indexing tradeoffs. Use when building or optimizing retrieval-augmented generation pipelines with colbert.

Pick and stack cold-start mitigations for serverless LLM deployments. Budget phases (node, image, weights, engine, first forward) and match mitigations to SLA. Use when you need help with cold start planner.

Expert in the Colorful design system - Vibrant, high-contrast palettes and gradients for engaging, memorable, and modern user experiences. Use when building UI components, applying design tokens, or implementing visual styles for colorful.

ComfyUI as backend - API mode, websocket polling, queue management for production. Use when working with multimodal AI (images, audio, video) using comfyui api.

ComfyUI graph design, custom nodes, workflow JSON, queue, API integration. Use when working with multimodal AI (images, audio, video) using comfyui.

Evaluate whether a safety report can detect alignment faking, via the monitored / unmonitored compliance gap. Use when you need help with compliance gap.

Produce the required-framework matrix for an LLM SaaS given customer geography, segment, and contract scope. Map controls across SOC 2, HIPAA, GDPR, PCI-DSS, EU AI Act, Colorado AI Act, ISO 42001. Use when you need help with compliance matrix.

Recomposition discipline, stability, Strong Skipping, derivedStateOf, baseline profiles, and Layout Inspector for production Compose apps. Use when developing Android apps with compose performance.

Automate 21risk tasks via Rube MCP (Composio). Always search tools first for current schemas. Use when you need help with 21risk automation.

Automate 2chat tasks via Rube MCP (Composio). Always search tools first for current schemas. Use when you need help with 2chat automation.

Automate Ably tasks via Rube MCP (Composio). Always search tools first for current schemas. Use when you need help with ably automation.

Automate Abstract tasks via Rube MCP (Composio). Always search tools first for current schemas. Use when you need help with abstract automation.

Automate Abuselpdb tasks via Rube MCP (Composio). Always search tools first for current schemas. Use when you need help with abuselpdb automation.

Automate Abyssale tasks via Rube MCP (Composio). Always search tools first for current schemas. Use when you need help with abyssale automation.

Automate Accelo tasks via Rube MCP (Composio). Always search tools first for current schemas. Use when you need help with accelo automation.

Automate Accredible Certificates tasks via Rube MCP (Composio). Always search tools first for current schemas. Use when you need help with accredible certificates automation.

Automate Acculynx tasks via Rube MCP (Composio). Always search tools first for current schemas. Use when you need help with acculynx automation.

Automate ActiveCampaign tasks via Rube MCP (Composio). Always search tools first for current schemas. Use when you need help with active campaign automation.

Automate Addresszen tasks via Rube MCP (Composio). Always search tools first for current schemas. Use when you need help with addresszen automation.

Automate Adobe tasks via Rube MCP (Composio). Always search tools first for current schemas. Use when you need help with adobe automation.

Automate Adrapid tasks via Rube MCP (Composio). Always search tools first for current schemas. Use when you need help with adrapid automation.